Qwen3.7 Max
Alibaba·Released May 19, 2026
Updated Oct 8, 11:55 PM 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
5 results · 40.5- SciCodeArtificial Analysis49.5%Reading 48.3
- Vibe Code BenchVals AI47.7%Reading 45.7
- LiveBench CodingLiveBench58.9%Reading 38.7
- Terminal-Bench 4.0 (AA run)Artificial AnalysisNear the floor1.5%Reading at most 34.5
- Code MigrationVals AI13.1%Reading 31.9
Research and reasoning
6 results · 47.7- Humanity's Last Exam (AA run)Artificial Analysis40.5%Reading 57.4
- Mystery Game PuzzlesEpoch AI32.0%Reading 53.4
- FrontierMath Tier 4Epoch AI34.1%Reading 52.8
- FrontierMath Tiers 1–3Epoch AI64.6%Reading 52.7
- LiveBench ReasoningLiveBench84.3%Reading 46.8
- Chess PuzzlesEpoch AI19.0%Reading 28.6
Professional work
9 results · 40.8- τ²-Bench Telecom (AA run)Artificial Analysis94.7%Reading 59.0
- EMBVals AI57.0%Reading 53.5
- Finance AgentVals AI47.8%Reading 49.4
- LiveBench Data AnalysisLiveBench71.8%Reading 48.0
- Legal Research BenchVals AI25.5%Reading 43.7
- Tax Agent BenchVals AI15.8%Reading 38.4
- MedCodeVals AI38.8%Reading 29.6
- Harvey Legal Agent BenchmarkVals AINear the floor1.7%Reading at most 24.8
- τ-Bench Banking (AA run)Artificial Analysis11.8%Reading 13.1
Knowledge and accuracy
6 results · 59.8- LiveBench Instruction FollowingLiveBench74.0%Reading 79.9
- IFBench (AA run)Artificial Analysis80.5%Reading 67.0
- SimpleQA VerifiedEpoch AI55.8%Reading 62.8
- LiveBench LanguageLiveBench79.7%Reading 57.1
- BullshitBenchBullshitBench · xhigh effort38.2%Reading 51.1
- AA-LCRArtificial Analysis79.0%Reading 47.4
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.
- LiveCodeBenchVals AI · CodingReference only87.1%
- SWE-bench VerifiedEpoch AI · CodingReference only77.3%
- SWE-bench VerifiedVals AI · CodingReference only68.8%
- OTIS Mock AIMEEpoch AI · Research and reasoningReference only95.6%
- CorpFinVals AI · Professional workReference only63.7%
- EBR-benchEpoch AI · Professional workWatching9.5%
- LegalBenchVals AI · Professional workReference only84.9%
- MedScribeVals AI · Professional workWatching79.4%
- TaxEvalVals AI · Professional workReference only75.3%
- GPQA DiamondEpoch AI · Knowledge and accuracyReference only90.9%
- GPQA DiamondVals AI · Knowledge and accuracyReference only90.2%
- MMLU-ProVals AI · Knowledge and accuracyReference only89.3%
- AA Intelligence IndexArtificial Analysis · Composite indicesReference only29.5
- LiveBench averageLiveBench · Composite indicesReference only73.1%
- Arena WebDevLMArena · Writing and designReference only1,515.1
No result yet
Scored evaluations this model has not taken. A missing result neither adds nor subtracts.
- Terminal-Bench 4.0 · Vals AI
- ProgramBench · Vals AI
- Vibe Code Bench 1–100 · Vals AI
- CyberBench Patch · Vals AI
- APEX-SWE · Mercor
- MysteryMechanism · Vals AI
- Terminal-Bench Science · Vals AI
- ProofBench · Vals AI
- APEX-Agents · Mercor
- Arena Text · LMArena