Qwen · model passport
Qwen3 4b Instruct 2507
qwen3-4b-instruct-2507- Best percentile
- 52.4BFCL v4 (function calling)
- Composite standing
- 44.7shrunk · 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: 25.7 percentile points between its best and worst axis — 52.4 pct on BFCL v4 (function calling) versus 26.7 pct on GPQA Diamond.
- BFCL v4 (function calling)Dormant board52.4 pct35.7%Verify →
- AIME (math)39 pct52.2%Verify →
- GPQA Diamond26.7 pct45.8%Verify →
- OverallNot benchmarked
- WebDev ArenaNot benchmarked
- Vision ArenaNot benchmarked
- Factuality ArenaNot benchmarked
- Search ArenaNot benchmarked
- Document ArenaNot benchmarked
- Agent ArenaNot benchmarked
- FrontierMathNot benchmarked
- SimpleQA VerifiedNot benchmarked
- ARC-AGI-2Not benchmarked
- Humanity's Last ExamNot benchmarked
- SimpleBenchNot benchmarked
- LiveBenchNot benchmarked
- SWE-bench Verified (live board)Not benchmarked
- Terminal-Bench 4.0Not benchmarked
- MMLU-Pro (Artificial Analysis)Not benchmarked
- LiveCodeBench (Artificial Analysis)Not benchmarked
- IFBench (Artificial Analysis)Not 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.
qwen3-4b-instruct-2507 stands at 44.7 (raw mean 39.4) — measured on 3 of 27 axes.
qwen3-4b-instruct-2507 ranks between #338 and #592 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 →