DeepSeek V4.1 Flash 1017
DeepSeek·Released Oct 17, 2026Open weights
Updated Oct 22, 6:20 AM ET
The score is on the board's scale (reference average 50, about 15 points per standard deviation), not a percentage.
By domain
Each domain is scored on the same scale as the overall score. Coverage is the share of the domain's kinds of evaluation with a result; it says how much evidence there is, not how good the model is.
Every result behind the score
The result as the evaluator publishes it, and the reading it gives on the board's scale. A hard evaluation can give a high reading for a modest result; results near 95% or 5% only say "at least" or "at most".
Coding
6 results · 65.2- Vibe Code BenchVals AI · max effort87.7%Reading 70.2
- Terminal-Bench 4.0 (AA run)Artificial Analysis · max effort33.8%Reading 68.3
- APEX-SWEMercor · max effort49.1%Reading 64.2
- SciCodeArtificial Analysis · max effort55.9%Reading 64.1
- Terminal-Bench 4.0Vals AI · max effort31.8%Reading 64.1
- Code MigrationVals AI · max effort44.2%Reading 62.5
Research and reasoning
5 results · 62.5- Mystery Game PuzzlesEpoch AI · max effort49.0%Reading 70.0
- Chess PuzzlesEpoch AI · max effort46.0%Reading 61.1
- Humanity's Last Exam (AA run)Artificial Analysis · max effort43.3%Reading 60.0
- FrontierMath Tier 4Epoch AI · max effort46.3%Reading 59.4
- FrontierMath Tiers 1–3Epoch AI · max effort71.2%Reading 58.0
Professional work
5 results · 66.4- Tax Agent BenchVals AI · max effort44.4%Reading 79.3
- Legal Research BenchVals AI · max effort45.2%Reading 66.4
- Finance AgentVals AI · max effort57.0%Reading 66.0
- Harvey Legal Agent BenchmarkVals AI · max effort14.2%Reading 63.7
- EMBVals AI · max effort61.8%Reading 58.3
Knowledge and accuracy
2 results · 51.8- AA-LCRArtificial Analysis · max effort82.7%Reading 53.8
- SimpleQA VerifiedEpoch AI · max effort42.5%Reading 44.2
Shown, not scored
Composite indices, saturated or older evaluations, evaluations still being checked, and vision, writing and multilingual results. They do not move the score.
- OTIS Mock AIMEEpoch AI · Research and reasoningReference only99.4%
- GPQA DiamondEpoch AI · Knowledge and accuracyReference only93.2%
- AA Intelligence IndexArtificial Analysis · Composite indicesReference only45.1
- Vals IndexVals AI · Composite indicesReference only61.3%
No result yet
Scored evaluations this model has not taken. A missing result neither adds nor subtracts.
- LiveBench Coding · LiveBench
- ProgramBench · Vals AI
- Vibe Code Bench 1–100 · Vals AI
- CyberBench Patch · Vals AI
- LiveBench Reasoning · LiveBench
- MysteryMechanism · Vals AI
- Terminal-Bench Science · Vals AI
- ProofBench · Vals AI
- APEX-Agents · Mercor
- MedCode · Vals AI
- LiveBench Data Analysis · LiveBench
- τ²-Bench Telecom (AA run) · Artificial Analysis
- τ-Bench Banking (AA run) · Artificial Analysis
- LiveBench Language · LiveBench
- LiveBench Instruction Following · LiveBench
- BullshitBench · BullshitBench
- IFBench (AA run) · Artificial Analysis
- Arena Text · LMArena