DeepSeek, released Aug 21, 2026
DeepSeek V4 Flash Vision Expprice, context, benchmarks and release details
Provisional: not enough results to rank yet Open weights 21% confidence 21 percent, Low confidence, 2 of 7 expected sources in
54.8
SI Score
Not ranked yet
- Input, per 1M tokens
- $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 ↗ - Output, per 1M tokens
- $1.20LiteLLMFirst-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 ↗ - Context window
- 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT
Open source ↗ - Max output
- 384Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT
Open source ↗ - Released
- Aug 21, 2026models.devPublished source fact
Retrieved Oct 9, 2026 · MIT
Open source ↗
How the score breaks down
Coding (weight 40 percent) 67.5
Math (weight 15 percent) 83.3
Preference (weight 15 percent) —
Reasoning (weight 30 percent) 88.5
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, 06:15 UTC.
Around it on the leaderboard
- 1 Claude Fable 5.1 80.2
- 2 Claude Opus 5.5 78.4
- 3 GPT-6 Astra 77.5
- 4 Claude Fable 5 76.8
- 5 Claude Opus 5 74.9
Benchmark results
17 benchmarks, 17 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.
LiveBench Reasoning: connectionsreasoning 99.3%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026
Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 99.3
Open source ↗ 99.3
LiveBench Reasoning: consecutive eventsreasoning 90.0%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026
Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 90.0
Open source ↗ 90.0
LiveBench Reasoning: logic with navigationreasoning 68%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026
Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 68.0
Open source ↗ 68.0
LiveBench Reasoning: spatialreasoning 96%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026
Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 96.0
Open source ↗ 96.0
LiveBench Reasoning: theory of mindreasoning 78.8%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026
Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 78.8
Open source ↗ 78.8
LiveBench Reasoning: zebra puzzlesreasoning 98.8%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026
Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 98.8
Open source ↗ 98.8
LiveBench Math: AMPS Hardmath 88%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026
Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 88.0
Open source ↗ 88.0
LiveBench Math: competition mathmath 97.1%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026
Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 97.1
Open source ↗ 97.1
LiveBench Math: integralsmath 76%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026
Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 76.0
Open source ↗ 76.0
LiveBench Math: olympiadmath 90.2%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026
Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 90.2
Open source ↗ 90.2
LiveBench Math: simplifymath 65.1%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026
Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 65.1
Open source ↗ 65.1
LiveBench Coding: code completioncoding 67.4%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026
Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 67.4
Open source ↗ 67.4
LiveBench Coding: code generationcoding 69.0%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026
Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 69.0
Open source ↗ 69.0
LiveBench Coding: JavaScriptcoding 63.6%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026
Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 63.6
Open source ↗ 63.6
LiveBench Coding: Pythoncoding 75%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026
Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 75.0
Open source ↗ 75.0
LiveBench Coding: TypeScriptcoding 56.7%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026
Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 56.7
Open source ↗ 56.7
Terminal-Bench 2.1coding 83.9%Official model cards via models.devLab-reported; metric score; transcribed by MIT models.dev catalog; not independently evaluated [variant] max effort; DeepSeek Harness minimal mode; 2.1
Retrieved Oct 9, 2026 · factual citation; MIT transcription
Open source ↗ 83.9
Open source ↗ 83.9
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
- YesHugging Face HubPublic Hub repo with weight files; gating/repo upload date is not release date
Retrieved Oct 9, 2026 · factual metadata; model-specific licenses
Open source ↗ - License
- mitHugging Face HubPublished source fact
Retrieved Oct 9, 2026 · factual metadata; model-specific licenses
Open source ↗ - Input modalities
- text, imagemodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT
Open source ↗ - First seen by SuperIndex
- Oct 8, 2026
- Coverage
- 17% of expected source weight
Reported (2)
- Official model cards via models.devOct 8, 2026
- LiveBenchOct 8, 2026
Awaiting (5)
- ARC Prize13% of weight
- Epoch AI Benchmarking25% of weight
- Humanity’s Last Exam13% of weight
- LMArena / Arena25% of weight
- Terminal-Bench6% of weight
Confidence rises as pending sources publish. Some sources never cover some models, so confidence reaches 100% at 80% of expected weight.