Alibaba · model passport
Qwen3 4b
qwen3-4b- Best percentile
- 80.0HHEM Hallucination (Vectara)
- Composite standing
- 47.9shrunk · 5/27 axes
What the data says
Benchmarked on 5 of 27 tracked axes. Every figure below is the model's own published result on that board.
Uneven: 57.8 percentile points between its best and worst axis — 80 pct on HHEM Hallucination (Vectara) versus 22.2 pct on IFBench (Artificial Analysis).
- HHEM Hallucination (Vectara)80 pct94.3%Verify →
- LiveCodeBench (Artificial Analysis)54.2 pct46.5%Verify →
- MMLU-Pro (Artificial Analysis)40.1 pct69.6%Verify →
- GPQA Diamond36.7 pct52.3%Verify →
- IFBench (Artificial Analysis)22.2 pct32.5%Verify →
- OverallNot benchmarked
- WebDev ArenaNot benchmarked
- Vision ArenaNot benchmarked
- Factuality ArenaNot benchmarked
- Search ArenaNot benchmarked
- Document ArenaNot benchmarked
- Agent ArenaNot 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
- 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.
qwen3-4b stands at 47.9 (raw mean 46.6) — measured on 5 of 27 axes.
qwen3-4b ranks between #273 and #493 across 3 built-in weightings — best under "Reasoning", worst under "All sources".
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 →