Updated Oct 9, 2026
The superintelligence leaderboard
Every frontier AI model ranked on one score, built only from public benchmarks. Refreshed daily, with every number traced to its source.
The leaderboard
Full catalog142 text models ranked from 58 benchmarks across 29 sources. Scores run 0 to 100; confidence shows how much of the expected evidence has reported. How the SI Score works
| 1 | Claude Fable 5.1 Anthropic | 80.2 | 100% confidence 100 percent, Full | $10.00Anthropic models & pricingOfficial Claude API; lowest short-context on-demand tier; batch/cache/long-context rates excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 1MAnthropic models & pricingOfficial Claude API; lowest short-context on-demand tier; batch/cache/long-context rates excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | — |
| 2 | Claude Opus 5.5 Anthropic | 78.4 | 100% confidence 100 percent, Full | $4.00Anthropic models & pricingOfficial Claude API; lowest short-context on-demand tier; batch/cache/long-context rates excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 1MAnthropic models & pricingOfficial Claude API; lowest short-context on-demand tier; batch/cache/long-context rates excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | — |
| 3 | GPT-6 Astra OpenAI | 77.5 | 100% confidence 100 percent, Full | $10.00OpenAI pricingOfficial Standard short-context rate; excludes Batch/Flex/cache discounts
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 1.1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 4 | Claude Fable 5 Anthropic | 76.8 | 100% confidence 100 percent, Full | $10.00Anthropic API pricingOfficial Claude API base tokens; lowest short-context global Standard rate; cache, batch, fast and regional premiums excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 5 | Claude Opus 5 Anthropic | 74.9 | 100% confidence 100 percent, Full | $5.00Anthropic API pricingOfficial Claude API base tokens; lowest short-context global Standard rate; cache, batch, fast and regional premiums excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 6 | GPT-6.1 Sol OpenAI | 73.0 | 100% confidence 100 percent, Full | $2.00OpenAI pricingOfficial Standard short-context rate; excludes Batch/Flex/cache discounts
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 1.1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 7 | GPT-5.6 Sol OpenAI | 72.1 | 100% confidence 100 percent, Full | $4.00models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://platform.openai.com/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; openai/gpt-5.6-sol
Retrieved Oct 9, 2026 · MIT Open source ↗ | 1.1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 8 | Claude Opus 4.7 Anthropic | 71.2 | 100% confidence 100 percent, Full | $5.00Anthropic API pricingOfficial Claude API base tokens; lowest short-context global Standard rate; cache, batch, fast and regional premiums excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 9 | Kimi K3 Moonshot AI | 71.0 | 100% confidence 100 percent, Full | $3.00models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://platform.moonshot.ai/docs/api/chat. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; moonshotai/kimi-k3
Retrieved Oct 9, 2026 · MIT Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 10 | Claude Opus 4.6 Anthropic | 70.8 | 100% confidence 100 percent, Full | $5.00Anthropic API pricingOfficial Claude API base tokens; lowest short-context global Standard rate; cache, batch, fast and regional premiums excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 11 | Muse Spark 1.3 Meta | 70.1 | 93% confidence 93 percent, High | $1.25Meta API pricingOfficial Meta Standard tier; applies only to the versions explicitly listed by the provider. Contributor training-data-discount tier and cached input excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 12 | Gemini 3.7 Flash Google | 70.0 | 100% confidence 100 percent, Full | $0.75Google Gemini pricingOfficial paid Standard text rate, lowest short-context tier; current promotional price if dated; excludes free/Batch/Flex/audio
Retrieved Oct 9, 2026 · CC-BY-4.0 factual citation Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 13 | GPT-5.4 OpenAI | 69.7 | 100% confidence 100 percent, Full | $2.50models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://platform.openai.com/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; openai/gpt-5.4
Retrieved Oct 9, 2026 · MIT Open source ↗ | 1.1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 14 | GPT-5.5 OpenAI | 69.5 | 100% confidence 100 percent, Full | $5.00models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://platform.openai.com/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; openai/gpt-5.5
Retrieved Oct 9, 2026 · MIT Open source ↗ | 1.1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 15 | Claude Sonnet 5.5 Anthropic | 69.4 | 93% confidence 93 percent, High | $2.00Anthropic models & pricingOfficial Claude API; lowest short-context on-demand tier; batch/cache/long-context rates excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 1MAnthropic models & pricingOfficial Claude API; lowest short-context on-demand tier; batch/cache/long-context rates excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | — |
| 16 | GPT-6 Sol OpenAI | 68.9 | 100% confidence 100 percent, Full | $2.00models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://platform.openai.com/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; openai/gpt-6-sol
Retrieved Oct 9, 2026 · MIT Open source ↗ | 1.1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 17 | Gemini 3.8 Flash Google | 68.8 | 100% confidence 100 percent, Full | $0.75Google Gemini pricingOfficial paid Standard text rate, lowest short-context tier; current promotional price if dated; excludes free/Batch/Flex/audio
Retrieved Oct 9, 2026 · CC-BY-4.0 factual citation Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 18 | Qwen3.8 Max Alibaba / Qwen | 68.7 | 85% confidence 85 percent, High | $1.65Alibaba Model Studio pricingOfficial Alibaba Model Studio Global USD on-demand API; 0<Token≤1M; Non-Thinking and Thinking modes. Output uses non-thinking rate when both modes are available; thinking-only products use their thinking rate. Cache, Batch, free quotas and regional rates excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 19 | Gemini 3.5 Flash Google | 68.3 | 100% confidence 100 percent, Full | $1.50Google Gemini pricingOfficial paid Standard text rate, lowest short-context tier; current promotional price if dated; excludes free/Batch/Flex/audio
Retrieved Oct 9, 2026 · CC-BY-4.0 factual citation Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 20 | Claude Sonnet 4.6 Anthropic | 68.3 | 100% confidence 100 percent, Full | $3.00Anthropic API pricingOfficial Claude API base tokens; lowest short-context global Standard rate; cache, batch, fast and regional premiums excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 21 | GPT-5.6 Terra OpenAI | 68.2 | 100% confidence 100 percent, Full | $2.00models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://platform.openai.com/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; openai/gpt-5.6-terra
Retrieved Oct 9, 2026 · MIT Open source ↗ | 1.1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 22 | Gemini 3.1 Pro Preview Google | 68.1 | 100% confidence 100 percent, Full | $2.00Google Gemini pricingOfficial paid Standard text rate, lowest short-context tier; current promotional price if dated; excludes free/Batch/Flex/audio
Retrieved Oct 9, 2026 · CC-BY-4.0 factual citation Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 23 | MiniMax-M3 MiniMax | 68.0 | 100% confidence 100 percent, Full | $0.30MiniMax API pricingOfficial MiniMax global on-demand API; lowest short-context tier and displayed permanent promotional discount; excludes high-context, fast tier and subscriptions
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 24 | GLM-5.3 Z.ai | 67.7 | 93% confidence 93 percent, High | $1.40Z.ai API pricingOfficial Z.ai global Standard uncached token rate; coding-plan subscriptions, cache and Batch excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 25 | Claude Sonnet 5 Anthropic | 67.7 | 93% confidence 93 percent, High | $2.00Anthropic API pricingOfficial Claude API base tokens; lowest short-context global Standard rate; cache, batch, fast and regional premiums excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 26 | Claude Opus 4.8 Anthropic | 67.5 | 100% confidence 100 percent, Full | $5.00Anthropic API pricingOfficial Claude API base tokens; lowest short-context global Standard rate; cache, batch, fast and regional premiums excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 27 | Grok 4.6 xAI | 66.6 | 100% confidence 100 percent, Full | $2.00models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://docs.x.ai/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; xai/grok-4.6
Retrieved Oct 9, 2026 · MIT Open source ↗ | 500Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 28 | Inkling Thinking Machines Lab | 66.5 | 100% confidence 100 percent, Full | not yet reported | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 29 | Qwen3.6 Max Preview Alibaba / Qwen | 66.4 | 64% confidence 64 percent, Medium | $1.30Alibaba Model Studio pricingOfficial Alibaba Model Studio International USD on-demand API; 0<Token≤128K; Non-Thinking and Thinking modes. Output uses non-thinking rate when both modes are available; thinking-only products use their thinking rate. Cache, Batch, free quotas and regional rates excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 262Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 30 | GLM-5.3-Flash Z.ai | 66.2 | 100% confidence 100 percent, Full | $0.15Z.ai API pricingOfficial Z.ai global Standard uncached token rate; coding-plan subscriptions, cache and Batch excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 31 | DeepSeek V4.1 Flash DeepSeek | 66.2 | 69% confidence 69 percent, Medium | $0.15DeepSeek pricingOfficial off-peak uncached rate; peak is 2x; time schedule at source
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 32 | Kimi K2 Thinking Turbo Moonshot AI | 66.1 | 64% confidence 64 percent, Medium | not yet reported | 262Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 33 | GPT-5.2 OpenAI | 65.9 | 100% confidence 100 percent, Full | $1.75models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://platform.openai.com/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; openai/gpt-5.2
Retrieved Oct 9, 2026 · MIT Open source ↗ | 400Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 34 | GLM-5.2 Z.ai | 65.7 | 100% confidence 100 percent, Full | $1.40Z.ai API pricingOfficial Z.ai global Standard uncached token rate; coding-plan subscriptions, cache and Batch excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 35 | Gemini 3.6 Flash Google | 65.5 | 100% confidence 100 percent, Full | $0.75Google Gemini pricingOfficial paid Standard text rate, lowest short-context tier; current promotional price if dated; excludes free/Batch/Flex/audio
Retrieved Oct 9, 2026 · CC-BY-4.0 factual citation Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 36 | Grok 4.7 xAI | 65.5 | 100% confidence 100 percent, Full | $2.00xAI models & pricingPublished source fact
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 500KxAI models & pricingPublished source fact
Retrieved Oct 9, 2026 · factual citation Open source ↗ | — |
| 37 | Grok 4.5 xAI | 64.8 | 100% confidence 100 percent, Full | $2.00models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://docs.x.ai/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; xai/grok-4.5
Retrieved Oct 9, 2026 · MIT Open source ↗ | 500Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 38 | Kimi K2.6 Moonshot AI | 64.0 | 85% confidence 85 percent, High | $0.95models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://platform.moonshot.ai/docs/api/chat. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; moonshotai/kimi-k2.6
Retrieved Oct 9, 2026 · MIT Open source ↗ | 262Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 39 | Qwen3.5 397B-A17B Alibaba / Qwen | 64.0 | 69% confidence 69 percent, Medium | $0.17Alibaba Model Studio pricingOfficial Alibaba Model Studio Global USD on-demand API; 0<Token≤128K; . Output uses non-thinking rate when both modes are available; thinking-only products use their thinking rate. Cache, Batch, free quotas and regional rates excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 262Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 40 | GPT-5.5 Pro OpenAI | 63.5 | 53% confidence 53 percent, Medium | $30.00models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://platform.openai.com/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; openai/gpt-5.5-pro
Retrieved Oct 9, 2026 · MIT Open source ↗ | 1.1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 41 | GPT-5.6 Luna OpenAI | 63.4 | 100% confidence 100 percent, Full | $0.20models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://platform.openai.com/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; openai/gpt-5.6-luna
Retrieved Oct 9, 2026 · MIT Open source ↗ | 1.1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 42 | Gemma 4 26B A4B IT Google | 63.4 | 64% confidence 64 percent, Medium | $0.00LiteLLMFirst-party API Standard token rate; MIT LiteLLM transcription. Provider documentation: https://ai.google.dev/gemini-api/docs/pricing. Exact endpoint only; cache/batch/long-context rates excluded
Retrieved Oct 9, 2026 · MIT Open source ↗ | 262Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 43 | GLM-5.1 Z.ai | 63.3 | 64% confidence 64 percent, Medium | $1.40Z.ai API pricingOfficial Z.ai global Standard uncached token rate; coding-plan subscriptions, cache and Batch excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 200Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 44 | DeepSeek V4 Pro DeepSeek | 63.1 | 85% confidence 85 percent, High | $1.32LiteLLMFirst-party API Standard token rate; MIT LiteLLM transcription. Provider documentation: https://api-docs.deepseek.com/quick_start/pricing. Exact endpoint only; cache/batch/long-context rates excluded
Retrieved Oct 9, 2026 · MIT Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 45 | Gemma 4 31B IT Google | 63.0 | 64% confidence 64 percent, Medium | $0.00LiteLLMFirst-party API Standard token rate; MIT LiteLLM transcription. Provider documentation: https://ai.google.dev/gemini-api/docs/pricing. Exact endpoint only; cache/batch/long-context rates excluded
Retrieved Oct 9, 2026 · MIT Open source ↗ | 262Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 46 | DeepSeek V4 Pro 0813 DeepSeek | 63.0 | 69% confidence 69 percent, Medium | $0.66DeepSeek pricingOfficial off-peak uncached rate; peak is 2x; time schedule at source
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 47 | Muse Spark 1.1 Meta | 62.9 | 61% confidence 61 percent, Medium | $1.25Meta API pricingOfficial Meta Standard tier; applies only to the versions explicitly listed by the provider. Contributor training-data-discount tier and cached input excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 48 | Qwen3.7 Plus Alibaba / Qwen | 62.7 | 64% confidence 64 percent, Medium | $0.28Alibaba Model Studio pricingOfficial Alibaba Model Studio Global USD on-demand API; 0<Token≤256K; . Output uses non-thinking rate when both modes are available; thinking-only products use their thinking rate. Cache, Batch, free quotas and regional rates excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 49 | Qwen3.5 35B-A3B Alibaba / Qwen | 62.7 | 64% confidence 64 percent, Medium | $0.06Alibaba Model Studio pricingOfficial Alibaba Model Studio Global USD on-demand API; 0<Token≤128K; . Output uses non-thinking rate when both modes are available; thinking-only products use their thinking rate. Cache, Batch, free quotas and regional rates excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 262Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 50 | Claude Opus 4.5 Anthropic | 62.6 | 100% confidence 100 percent, Full | $5.00models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://docs.anthropic.com/en/docs/about-claude/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; anthropic/claude-opus-4-5-20251101
Retrieved Oct 9, 2026 · MIT Open source ↗ | 200Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 51 | MiMo-V2.5-Pro Xiaomi | 62.6 | 88% confidence 88 percent, High | $0.43models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://platform.xiaomimimo.com/#/docs. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; xiaomi/mimo-v2.5-pro
Retrieved Oct 9, 2026 · MIT Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 52 | Muse Spark 1.2 Meta | 62.3 | 53% confidence 53 percent, Medium | $1.25Meta API pricingOfficial Meta Standard tier; applies only to the versions explicitly listed by the provider. Contributor training-data-discount tier and cached input excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 53 | Mistral Large 4 Mistral AI | 62.2 | 64% confidence 64 percent, Medium | $0.68Mistral API pricingOfficial Mistral Serverless API Standard rate, displayed sale price where applicable; cache, Batch, specialist units and hosted third-party models excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 54 | Qwen3.8 27B Alibaba / Qwen | 61.9 | 69% confidence 69 percent, Medium | $0.50Alibaba Model Studio pricingOfficial Alibaba Model Studio International USD on-demand API; 0<Token≤1M; Non-Thinking and Thinking modes. Output uses non-thinking rate when both modes are available; thinking-only products use their thinking rate. Cache, Batch, free quotas and regional rates excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 262Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 55 | GPT-6 Luna OpenAI | 61.6 | 100% confidence 100 percent, Full | $0.10OpenAI pricingOfficial Standard short-context rate; excludes Batch/Flex/cache discounts
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 1.1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 56 | Qwen3.6 Plus Alibaba / Qwen | 61.6 | 80% confidence 80 percent, High | $0.28Alibaba Model Studio pricingOfficial Alibaba Model Studio Global USD on-demand API; 0<Token≤256K; . Output uses non-thinking rate when both modes are available; thinking-only products use their thinking rate. Cache, Batch, free quotas and regional rates excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 57 | GLM-4.7 Z.ai | 61.3 | 69% confidence 69 percent, Medium | $0.60Z.ai API pricingOfficial Z.ai global Standard uncached token rate; coding-plan subscriptions, cache and Batch excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 205Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 58 | GPT-5.4 Pro OpenAI | 61.3 | 69% confidence 69 percent, Medium | $30.00models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://platform.openai.com/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; openai/gpt-5.4-pro
Retrieved Oct 9, 2026 · MIT Open source ↗ | 1.1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 59 | Nemotron 3 Ultra 550B A55B NVIDIA | 61.2 | 100% confidence 100 percent, Full | not yet reported | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 60 | DeepSeek V4 Flash 0731 DeepSeek | 61.0 | 69% confidence 69 percent, Medium | not yet reported | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 61 | Hy3 Tencent | 60.7 | 88% confidence 88 percent, High | $0.00models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://cloud.tencent.com/document/product/1823/130050. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; tencent-tokenhub/hy3
Retrieved Oct 9, 2026 · MIT Open source ↗ | 256Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 62 | Claude Haiku 4.5 Anthropic | 60.5 | 64% confidence 64 percent, Medium | $1.00models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://docs.anthropic.com/en/docs/about-claude/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; anthropic/claude-haiku-4-5-20251001
Retrieved Oct 9, 2026 · MIT Open source ↗ | 200Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 63 | Qwen3.5 Flash Alibaba / Qwen | 59.5 | 64% confidence 64 percent, Medium | $0.03Alibaba Model Studio pricingOfficial Alibaba Model Studio Global USD on-demand API; 0<Token≤128K; . Output uses non-thinking rate when both modes are available; thinking-only products use their thinking rate. Cache, Batch, free quotas and regional rates excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 64 | Claude Haiku 5.5 Anthropic | 59.4 | 68% confidence 68 percent, Medium | $0.10Anthropic models & pricingOfficial Claude API; lowest short-context on-demand tier; batch/cache/long-context rates excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 1MAnthropic models & pricingOfficial Claude API; lowest short-context on-demand tier; batch/cache/long-context rates excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | — |
| 65 | GLM-5 Z.ai | 59.4 | 90% confidence 90 percent, High | $1.00Z.ai API pricingOfficial Z.ai global Standard uncached token rate; coding-plan subscriptions, cache and Batch excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 205Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 66 | Kimi K2.5 Moonshot AI | 59.0 | 100% confidence 100 percent, Full | $0.60LiteLLMFirst-party API Standard token rate; MIT LiteLLM transcription. Provider documentation: https://platform.moonshot.ai/docs/guide/kimi-k2-5-quickstart. Exact endpoint only; cache/batch/long-context rates excluded
Retrieved Oct 9, 2026 · MIT Open source ↗ | 262Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 67 | Qwen3.7 Max Alibaba / Qwen | 58.6 | 53% confidence 53 percent, Medium | $1.65Alibaba Model Studio pricingOfficial Alibaba Model Studio Global USD on-demand API; 0<Token≤1M; Non-Thinking and Thinking modes. Output uses non-thinking rate when both modes are available; thinking-only products use their thinking rate. Cache, Batch, free quotas and regional rates excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 68 | Gemini 3 Pro Preview Google | 58.6 | 68% confidence 68 percent, Medium | not yet reported | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 69 | GPT-5.5 Instant OpenAI | 58.3 | 64% confidence 64 percent, Medium | not yet reported | 400Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 70 | MiniMax-M2.7 MiniMax | 57.9 | 88% confidence 88 percent, High | $0.30MiniMax API pricingOfficial MiniMax global on-demand API; lowest short-context tier and displayed permanent promotional discount; excludes high-context, fast tier and subscriptions
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 205Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 71 | Fugu Ultra Sakana AI | 57.9 | 100% confidence 100 percent, Full | not yet reported | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 72 | MiniMax-M2.5 MiniMax | 57.8 | 100% confidence 100 percent, Full | $0.30MiniMax API pricingOfficial MiniMax global on-demand API; lowest short-context tier and displayed permanent promotional discount; excludes high-context, fast tier and subscriptions
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 205Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 73 | Grok 4.20 (Reasoning) xAI | 57.7 | 80% confidence 80 percent, High | $1.25models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://docs.x.ai/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; xai/grok-4.20-0309-reasoning
Retrieved Oct 9, 2026 · MIT Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 74 | MiMo-V2.6-Pro Xiaomi | 57.4 | 88% confidence 88 percent, High | $0.43models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://platform.xiaomimimo.com/#/docs. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; xiaomi/mimo-v2.6-pro
Retrieved Oct 9, 2026 · MIT Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 75 | GPT-5.4 nano OpenAI | 57.4 | 100% confidence 100 percent, Full | $0.20models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://platform.openai.com/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; openai/gpt-5.4-nano
Retrieved Oct 9, 2026 · MIT Open source ↗ | 400Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 76 | GPT-5.4 mini OpenAI | 56.9 | 100% confidence 100 percent, Full | $0.75models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://platform.openai.com/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; openai/gpt-5.4-mini
Retrieved Oct 9, 2026 · MIT Open source ↗ | 400Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 77 | LongCat-2.0 Meituan | 56.6 | 100% confidence 100 percent, Full | not yet reported | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 78 | MiMo-V2.5 Xiaomi | 56.4 | 88% confidence 88 percent, High | $0.14models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://platform.xiaomimimo.com/#/docs. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; xiaomi/mimo-v2.5
Retrieved Oct 9, 2026 · MIT Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 79 | DeepSeek V4 Flash DeepSeek | 56.2 | 53% confidence 53 percent, Medium | $0.30LiteLLMFirst-party API Standard token rate; MIT LiteLLM transcription. Provider documentation: https://api-docs.deepseek.com/quick_start/pricing. Exact endpoint only; cache/batch/long-context rates excluded
Retrieved Oct 9, 2026 · MIT Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 80 | Fugu Sakana AI | 55.9 | 100% confidence 100 percent, Full | not yet reported | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 81 | MiMo-V2.6-Flash Xiaomi | 55.8 | 88% confidence 88 percent, High | $0.14models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://platform.xiaomimimo.com/#/docs. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; xiaomi/mimo-v2.6-flash
Retrieved Oct 9, 2026 · MIT Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 82 | DeepSeek V3 0324 DeepSeek | 55.7 | 74% confidence 74 percent, Medium | not yet reported | 164Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 83 | GPT-5 OpenAI | 55.7 | 100% confidence 100 percent, Full | $1.25models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://platform.openai.com/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; openai/gpt-5
Retrieved Oct 9, 2026 · MIT Open source ↗ | 400Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 84 | MiniMax-M2 MiniMax | 55.7 | 96% confidence 96 percent, High | $0.30MiniMax API pricingOfficial MiniMax global on-demand API; lowest short-context tier and displayed permanent promotional discount; excludes high-context, fast tier and subscriptions
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 205Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 85 | GPT-5.1 OpenAI | 55.7 | 85% confidence 85 percent, High | $1.25models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://platform.openai.com/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; openai/gpt-5.1
Retrieved Oct 9, 2026 · MIT Open source ↗ | 400Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 86 | Qwen3.6 27B Alibaba / Qwen | 55.6 | 53% confidence 53 percent, Medium | $0.60Alibaba Model Studio pricingOfficial Alibaba Model Studio International USD on-demand API; 0<Token≤256K; . Output uses non-thinking rate when both modes are available; thinking-only products use their thinking rate. Cache, Batch, free quotas and regional rates excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 262Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 87 | Claude Opus 4 Anthropic | 55.5 | 100% confidence 100 percent, Full | $15.00Anthropic API pricingOfficial Claude API base tokens; lowest short-context global Standard rate; cache, batch, fast and regional premiums excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 200Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 88 | o3 OpenAI | 55.4 | 87% confidence 87 percent, High | $2.00models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://platform.openai.com/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; openai/o3
Retrieved Oct 9, 2026 · MIT Open source ↗ | 200Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 89 | Gemini 3.5 Flash Lite Google | 55.2 | 100% confidence 100 percent, Full | $0.30Google Gemini pricingOfficial paid Standard text rate, lowest short-context tier; current promotional price if dated; excludes free/Batch/Flex/audio
Retrieved Oct 9, 2026 · CC-BY-4.0 factual citation Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 90 | GPT OSS 120B OpenAI | 54.8 | 79% confidence 79 percent, Medium | not yet reported | 131Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 91 | Gemini 3 Flash Preview Google | 54.8 | 93% confidence 93 percent, High | $0.50Google Gemini pricingOfficial paid Standard text rate, lowest short-context tier; current promotional price if dated; excludes free/Batch/Flex/audio
Retrieved Oct 9, 2026 · CC-BY-4.0 factual citation Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 92 | Grok 4.3 xAI | 54.6 | 80% confidence 80 percent, High | $1.25models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://docs.x.ai/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; xai/grok-4.3
Retrieved Oct 9, 2026 · MIT Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 93 | DeepSeek-V3 DeepSeek | 54.1 | 93% confidence 93 percent, High | $0.27LiteLLMFirst-party API Standard token rate; MIT LiteLLM transcription. Provider documentation: not supplied in the MIT entry; rate is a transcription, not independently verified. Exact endpoint only; cache/batch/long-context rates excluded
Retrieved Oct 9, 2026 · MIT Open source ↗ | 131Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 94 | Claude Sonnet 4.5 Anthropic | 53.9 | 80% confidence 80 percent, High | $3.00models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://docs.anthropic.com/en/docs/about-claude/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; anthropic/claude-sonnet-4-5-20250929
Retrieved Oct 9, 2026 · MIT Open source ↗ | 200Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 95 | Inkling Small Thinking Machines Lab | 53.6 | 100% confidence 100 percent, Full | not yet reported | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 96 | DeepSeek V3.2 DeepSeek | 53.3 | 56% confidence 56 percent, Medium | $0.28LiteLLMFirst-party API Standard token rate; MIT LiteLLM transcription. Provider documentation: not supplied in the MIT entry; rate is a transcription, not independently verified. Exact endpoint only; cache/batch/long-context rates excluded
Retrieved Oct 9, 2026 · MIT Open source ↗ | 128Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 97 | GLM-4.7-Flash Z.ai | 53.3 | 69% confidence 69 percent, Medium | $0.00models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://docs.z.ai/guides/overview/pricing. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; zai/glm-4.7-flash
Retrieved Oct 9, 2026 · MIT Open source ↗ | 200Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 98 | Step 3.5 Flash StepFun | 53.0 | 88% confidence 88 percent, High | $0.10models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://platform.stepfun.com/docs/zh/overview/concept. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; stepfun/step-3.5-flash
Retrieved Oct 9, 2026 · MIT Open source ↗ | 256Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 99 | Qwen3 30B A3B Alibaba / Qwen | 52.6 | 64% confidence 64 percent, Medium | $0.11Alibaba Model Studio pricingOfficial Alibaba Model Studio Global USD on-demand API; standard tier; Non-Thinking and Thinking modes. Output uses non-thinking rate when both modes are available; thinking-only products use their thinking rate. Cache, Batch, free quotas and regional rates excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 131Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 100 | GPT OSS 20B OpenAI | 52.5 | 64% confidence 64 percent, Medium | not yet reported | 131Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 101 | Claude Sonnet 3.5 v2 Anthropic | 51.9 | 100% confidence 100 percent, Full | not yet reported | 200Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 102 | Claude Opus 4.1 Anthropic | 51.5 | 80% confidence 80 percent, High | not yet reported | 200Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 103 | o4-mini OpenAI | 51.2 | 87% confidence 87 percent, High | $1.10LiteLLMFirst-party API Standard token rate; MIT LiteLLM transcription. Provider documentation: https://developers.openai.com/api/docs/pricing. Exact endpoint only; cache/batch/long-context rates excluded
Retrieved Oct 9, 2026 · MIT Open source ↗ | 200Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 104 | Llama 4 Scout 17B Instruct Meta | 51.0 | 64% confidence 64 percent, Medium | not yet reported | 10Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 105 | GPT-5 Mini OpenAI | 50.6 | 99% confidence 99 percent, High | $0.25models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://platform.openai.com/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; openai/gpt-5-mini
Retrieved Oct 9, 2026 · MIT Open source ↗ | 400Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 106 | Qwen3 32B Alibaba / Qwen | 50.4 | 67% confidence 67 percent, Medium | $0.16Alibaba Model Studio pricingOfficial Alibaba Model Studio Global USD on-demand API; standard tier; Non-Thinking and Thinking modes. Output uses non-thinking rate when both modes are available; thinking-only products use their thinking rate. Cache, Batch, free quotas and regional rates excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 131Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 107 | Qwen3 235B-A22B Alibaba / Qwen | 50.3 | 76% confidence 76 percent, Medium | $0.29Alibaba Model Studio pricingOfficial Alibaba Model Studio Global USD on-demand API; standard tier; Non-Thinking and Thinking modes. Output uses non-thinking rate when both modes are available; thinking-only products use their thinking rate. Cache, Batch, free quotas and regional rates excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 131Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 108 | Qwen3 Max Alibaba / Qwen | 50.2 | 69% confidence 69 percent, Medium | $0.36Alibaba Model Studio pricingOfficial Alibaba Model Studio Global USD on-demand API; 0<Token≤32K; Non-Thinking mode only. Output uses non-thinking rate when both modes are available; thinking-only products use their thinking rate. Cache, Batch, free quotas and regional rates excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 262Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 109 | GPT-4o (2024-05-13) OpenAI | 49.4 | 93% confidence 93 percent, High | $5.00LiteLLMFirst-party API Standard token rate; MIT LiteLLM transcription. Provider documentation: https://developers.openai.com/api/docs/pricing. Exact endpoint only; cache/batch/long-context rates excluded
Retrieved Oct 9, 2026 · MIT Open source ↗ | 128Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 110 | Claude Sonnet 3.7 Anthropic | 48.9 | 100% confidence 100 percent, Full | not yet reported | 200Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 111 | Mistral Small 3.1 24B Mistral AI | 48.4 | 64% confidence 64 percent, Medium | not yet reported | 128Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 112 | QwQ 32B Alibaba / Qwen | 48.2 | 67% confidence 67 percent, Medium | not yet reported | 131Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 113 | DeepSeek-R1 DeepSeek | 47.9 | 88% confidence 88 percent, High | $0.55LiteLLMFirst-party API Standard token rate; MIT LiteLLM transcription. Provider documentation: not supplied in the MIT entry; rate is a transcription, not independently verified. Exact endpoint only; cache/batch/long-context rates excluded
Retrieved Oct 9, 2026 · MIT Open source ↗ | 128Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 114 | GLM-4.6 Z.ai | 47.8 | 55% confidence 55 percent, Medium | $0.60Z.ai API pricingOfficial Z.ai global Standard uncached token rate; coding-plan subscriptions, cache and Batch excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 205Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 115 | Claude Sonnet 4 Anthropic | 46.6 | 100% confidence 100 percent, Full | $3.00Anthropic API pricingOfficial Claude API base tokens; lowest short-context global Standard rate; cache, batch, fast and regional premiums excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 200Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 116 | Nemotron 3.5 Lightning 30B A3B NVIDIA | 46.1 | 100% confidence 100 percent, Full | not yet reported | 262Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 117 | GPT-5 Pro OpenAI | 45.8 | 64% confidence 64 percent, Medium | $15.00models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://platform.openai.com/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; openai/gpt-5-pro
Retrieved Oct 9, 2026 · MIT Open source ↗ | 400Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 118 | Llama-3.1-70B-Instruct Meta | 45.7 | 93% confidence 93 percent, High | not yet reported | 128Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 119 | Gemini 2.5 Pro Google | 45.2 | 90% confidence 90 percent, High | $1.25Google Gemini pricingOfficial paid Standard text rate, lowest short-context tier; current promotional price if dated; excludes free/Batch/Flex/audio
Retrieved Oct 9, 2026 · CC-BY-4.0 factual citation Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 120 | Gemma 3 12B IT Google | 45.1 | 64% confidence 64 percent, Medium | not yet reported | 131Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 121 | GPT-4o (2024-11-20) OpenAI | 42.2 | 61% confidence 61 percent, Medium | $2.50models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://platform.openai.com/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; openai/gpt-4o-2024-11-20
Retrieved Oct 9, 2026 · MIT Open source ↗ | 128Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 122 | Gemma 3 27B IT Google | 42.0 | 74% confidence 74 percent, Medium | not yet reported | 131Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 123 | o3-mini OpenAI | 41.6 | 96% confidence 96 percent, High | $1.10LiteLLMFirst-party API Standard token rate; MIT LiteLLM transcription. Provider documentation: https://developers.openai.com/api/docs/pricing. Exact endpoint only; cache/batch/long-context rates excluded
Retrieved Oct 9, 2026 · MIT Open source ↗ | 200Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 124 | GPT-4.1 OpenAI | 41.5 | 100% confidence 100 percent, Full | $2.00models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://platform.openai.com/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; openai/gpt-4.1
Retrieved Oct 9, 2026 · MIT Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 125 | Claude Haiku 3.5 Anthropic | 40.8 | 100% confidence 100 percent, Full | $0.80Anthropic API pricingOfficial Claude API base tokens; lowest short-context global Standard rate; cache, batch, fast and regional premiums excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 200Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 126 | Claude Haiku 3 Anthropic | 39.9 | 93% confidence 93 percent, High | not yet reported | 200Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 127 | Qwen2.5-Coder-32B-Instruct Alibaba / Qwen | 39.6 | 90% confidence 90 percent, High | not yet reported | 131Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 128 | Gemma 3 4B IT Google | 39.2 | 64% confidence 64 percent, Medium | not yet reported | 131Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 129 | GPT-5 Nano OpenAI | 39.1 | 85% confidence 85 percent, High | $0.05models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://platform.openai.com/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; openai/gpt-5-nano
Retrieved Oct 9, 2026 · MIT Open source ↗ | 400Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 130 | Llama-3.1-8B-Instruct Meta | 37.7 | 93% confidence 93 percent, High | not yet reported | 128Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 131 | Nova Pro Amazon | 37.4 | 100% confidence 100 percent, Full | not yet reported | 300Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 132 | GPT-4.1 mini OpenAI | 36.9 | 87% confidence 87 percent, High | $0.40models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://platform.openai.com/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; openai/gpt-4.1-mini
Retrieved Oct 9, 2026 · MIT Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 133 | GPT-4o (2024-08-06) OpenAI | 36.7 | 100% confidence 100 percent, Full | $2.50models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://platform.openai.com/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; openai/gpt-4o-2024-08-06
Retrieved Oct 9, 2026 · MIT Open source ↗ | 128Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 134 | Nova Lite Amazon | 36.6 | 100% confidence 100 percent, Full | not yet reported | 300Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 135 | Mistral Large 2.1 Mistral AI | 35.3 | 100% confidence 100 percent, Full | not yet reported | 131Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 136 | Mistral Medium 3 Mistral AI | 33.0 | 85% confidence 85 percent, High | not yet reported | 131Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 137 | Llama-3.3-70B-Instruct Meta | 32.7 | 100% confidence 100 percent, Full | not yet reported | 128Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 138 | Llama-3.2-1B Meta | 32.1 | 93% confidence 93 percent, High | not yet reported | 131Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 139 | GPT-4.1 nano OpenAI | 32.1 | 82% confidence 82 percent, High | $0.10LiteLLMFirst-party API Standard token rate; MIT LiteLLM transcription. Provider documentation: https://developers.openai.com/api/docs/pricing. Exact endpoint only; cache/batch/long-context rates excluded
Retrieved Oct 9, 2026 · MIT Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 140 | GPT-4o OpenAI | 31.2 | 59% confidence 59 percent, Medium | $2.50models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://platform.openai.com/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; openai/gpt-4o
Retrieved Oct 9, 2026 · MIT Open source ↗ | 128Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 141 | Llama 4 Maverick 17B Instruct Meta | 30.0 | 78% confidence 78 percent, Medium | not yet reported | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 142 | GPT-4o mini OpenAI | 22.9 | 100% confidence 100 percent, Full | $0.15models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://platform.openai.com/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; openai/gpt-4o-mini
Retrieved Oct 9, 2026 · MIT Open source ↗ | 128Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
Ranked text models appear first. The provisional toggle includes only text models awaiting evidence. Browse every kind in the model catalog. Prices are USD per 1M tokens (official first-party API). Dotted values carry their source: hover or tap to see it. “Not yet reported” means the source hasn’t published that figure for this model.
The frontier
Release timelineBest SI Score among models released by each date. Each dot is a ranked model at its current score.
What changed
- Oct 7 Claude Haiku 5.5 joined the ranking at #64 Anthropic. SI Score 59.4
- Oct 6 Mistral Large 4 joined the ranking at #53 Mistral AI. SI Score 62.2
- Sep 29 Ling 3.1 Flash was released inclusionAI. Awaiting enough benchmark results to rank
- Sep 29 GPT-6.1 Sol joined the ranking at #6 OpenAI. SI Score 73.0
- Sep 28 Claude Sonnet 5.5 joined the ranking at #15 Anthropic. SI Score 69.4
- Sep 27 MiniMax-M3.1-Flash-Preview was released MiniMax. Awaiting enough benchmark results to rank
Hear when the frontier moves
Get a notification on this device when a new model takes #1 or enters the top 10. No account, no email; turn it off any time.
Score against price
Best value modelsBlended API price per million tokens, log scale. Up and to the left means more score per dollar.
Best score at its price or lower Other ranked models (fainter means lower confidence) Open weights
Latest releases
All releasesOct 7, 2026
Claude Haiku 5.5
Anthropic
59.4#64
Oct 6, 2026
Mistral Large 4
Mistral AI
62.2#53
Sep 29, 2026
Ling 3.1 Flash
inclusionAI
Not ranked yet
Sep 29, 2026
GPT-6.1 Sol
OpenAI
73.0#6
Sep 28, 2026
Claude Sonnet 5.5
Anthropic
69.4#15
Sep 27, 2026
MiniMax-M3.1-Flash-Preview
MiniMax
Not ranked yet
Sep 25, 2026
LongCat-2.5-Preview
Meituan
Not ranked yet
Sep 23, 2026
Qwen 3.8 Max Prime
Alibaba / Qwen
Not ranked yet
Understand the numbers
Methodology
How the SI Score is built, what the confidence % means, and which sources feed it, with their licenses.
What is superintelligence?
The research term, the corporate lane name and the new government spelling, untangled and dated.
“Super Intelligence” in U.S. policy
Executive Order 14434 made it executive-branch vocabulary on Sep 29, 2026. What it says, verbatim.
Statements tracker
Who has adopted the term, who rejects it, and what comes next. Dated, sourced, neutral.