Alibaba · model passport
Qwen3 235B A22B 2507 Instruct
qwen3-235b-a22b-2507-instruct- Best percentile
- 82.4MMLU-Pro (Artificial Analysis)
- Composite standing
- 57.3shrunk · 3/27 axes
What the data says
Benchmarked on 3 of 27 tracked axes. Every figure below is the model's own published result on that board.
Uneven: 29.9 percentile points between its best and worst axis — 82.4 pct on MMLU-Pro (Artificial Analysis) versus 52.5 pct on IFBench (Artificial Analysis).
- MMLU-Pro (Artificial Analysis)82.4 pct82.8%Verify →
- LiveCodeBench (Artificial Analysis)59.2 pct52.4%Verify →
- IFBench (Artificial Analysis)52.5 pct46.1%Verify →
- OverallNot benchmarked
- WebDev ArenaNot benchmarked
- Vision ArenaNot benchmarked
- Factuality ArenaNot benchmarked
- Search ArenaNot benchmarked
- Document ArenaNot benchmarked
- Agent ArenaNot benchmarked
- GPQA DiamondNot benchmarked
- AIME (math)Not benchmarked
- FrontierMathNot benchmarked
- SimpleQA VerifiedNot benchmarked
- ARC-AGI-2Not benchmarked
- Humanity's Last ExamNot benchmarked
- SimpleBenchNot benchmarked
- LiveBenchNot benchmarked
- BFCL v4 (function calling)Not benchmarked
- SWE-bench Verified (live board)Not benchmarked
- Terminal-Bench 4.0Not benchmarked
- HHEM Hallucination (Vectara)Not benchmarked
- SWE-bench VerifiedNot benchmarked
- Terminal-BenchNot benchmarked
- CodingNot benchmarked
- Instruction followingNot benchmarked
- Hard promptsNot benchmarked
Percentiles are the model's standing within each board's own population. Axes marked "not benchmarked" have no published result for this model — that is an absence of data, not a low score.
Qwen3 235B A22B 2507 Instruct stands at 57.3 (raw mean 64.7) — measured on 3 of 27 axes.
Every claim is a computed fact from the current board data, phrased by a low-temperature model call and rejected by a validation gate if any number is not in the source row. How the leaderboards work →