OpenAI, released May 13, 2024
GPT-4oprice, context, benchmarks and release details
59% confidence 59 percent, Medium confidence, 3 of 6 expected sources in
31.2
SI Score
#140 of 142 ranked models
- Input, per 1M tokens
- $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 ↗ - Output, per 1M tokens
- $10.00models.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-4o
Retrieved Oct 9, 2026 · MIT
Open source ↗ - Context window
- 128Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT
Open source ↗ - Max output
- 16.4Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT
Open source ↗ - Released
- May 13, 2024OpenAI API changelogPublished source fact
Retrieved Oct 9, 2026 · factual citation
Open source ↗
How the score breaks down
Coding (weight 40 percent) 16.7
Math (weight 15 percent) —
Preference (weight 15 percent) —
Reasoning (weight 30 percent) 1.5
Weights: reasoning 30%, math 15%, coding 40%, preference 15%. Results use fixed 0–100 scales before averaging, and thin evidence is pulled toward 50. Method si-v3-retained-evidence-2, computed Oct 9, 2026, 05:13 UTC.
Around it on the leaderboard
- 138 Llama-3.2-1B 32.1
- 139 GPT-4.1 nano 32.1
- 140 GPT-4o 31.2
- 141 Llama 4 Maverick 17B Instruct 30.0
- 142 GPT-4o mini 22.9
Benchmark results
5 benchmarks, 11 resultsEach row shows the best published result. Where a model was tested at several settings, such as reasoning effort, open the row to see each one. Hover or tap a value for its source.
ARC-AGI-1 (semi-private)reasoning 4.5%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] gpt-4o-2024-11-20Published Oct 6, 2026
Retrieved Oct 9, 2026 · factual citation
Open source ↗ 4.5
Open source ↗ 4.5
ARC-AGI-2 (public eval)reasoning 0%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] gpt-4o-2024-11-20Published Oct 6, 2026
Retrieved Oct 9, 2026 · factual citation
Open source ↗ 0.0
Open source ↗ 0.0
ARC-AGI-2 (semi-private)reasoning 0%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] gpt-4o-2024-11-20Published Oct 6, 2026
Retrieved Oct 9, 2026 · factual citation
Open source ↗ 0.0
Open source ↗ 0.0
SWE-bench Pro (public)coding 3.6%SWE-bench Pro (public)Published steward score [variant] Published Sep 19, 2025
Retrieved Oct 9, 2026 · factual citation
Open source ↗ 3.6
Open source ↗ 3.6
SWE-bench Verifiedcoding 38.8%SWE-bench VerifiedSWE-bench published model plus agent result; harness retained, not a base model evaluation [variant] Agentless-1.5Published Oct 28, 2024
Retrieved Oct 9, 2026 · factual citation
Open source ↗
38.8 7 settings
- Setting 1 38.8%SWE-bench VerifiedSWE-bench published model plus agent result; harness retained, not a base model evaluation [variant] Agentless-1.5Published Oct 28, 2024
Retrieved Oct 9, 2026 · factual citation
Open source ↗ - Setting 2 26.2%SWE-bench VerifiedSWE-bench published model plus agent result; harness retained, not a base model evaluation [variant] AppMap NaviePublished Jun 15, 2024
Retrieved Oct 9, 2026 · factual citation
Open source ↗ - Setting 3 38.4%SWE-bench VerifiedSWE-bench published model plus agent result; harness retained, not a base model evaluation [variant] AutoCodeRoverPublished Jun 28, 2024
Retrieved Oct 9, 2026 · factual citation
Open source ↗ - Setting 4 27%SWE-bench VerifiedSWE-bench published model plus agent result; harness retained, not a base model evaluation [variant] EPAM AI/Run Developer AgentPublished Oct 16, 2024
Retrieved Oct 9, 2026 · factual citation
Open source ↗ - Setting 5 32.6%SWE-bench VerifiedSWE-bench published model plus agent result; harness retained, not a base model evaluation [variant] MASAIPublished Jun 12, 2024
Retrieved Oct 9, 2026 · factual citation
Open source ↗ - Setting 6 21.6%SWE-bench VerifiedSWE-bench published model plus agent result; harness retained, not a base model evaluation [variant] mini-SWE-agent; 0.0.0Published Jul 20, 2025
Retrieved Oct 9, 2026 · factual citation
Open source ↗ - Setting 7 23.2%SWE-bench VerifiedSWE-bench published model plus agent result; harness retained, not a base model evaluation [variant] SWE-agentPublished Jul 28, 2024
Retrieved Oct 9, 2026 · factual citation
Open source ↗
Normalization uses a fixed 0–100 scale for each unit, independent of other models. Compare evaluation conditions before reading a small gap as decisive. “Lab-reported” marks the provider's own published figure.
Details and sources
- Open weights
- Nomodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT
Open source ↗ - License
- not yet reported
- Input modalities
- text, image, pdfmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT
Open source ↗ - First seen by SuperIndex
- Oct 8, 2026
- Coverage
- 47% of expected source weight
Reported (3)
- ARC PrizeOct 8, 2026
- SWE-bench VerifiedOct 8, 2026
- SWE-bench Pro (public)Oct 8, 2026
Awaiting (3)
- Official model cards via models.dev6% of weight
- LiveBench16% of weight
- LMArena / Arena31% of weight
Confidence rises as pending sources publish. Some sources never cover some models, so confidence reaches 100% at 80% of expected weight.