Model profile
Qwen3 4B Thinking 2507
2025-08-05release date
1eval lineages
Evidence summary
Published evidence spans 1 evals and 1 of 7 behavior components. Its strongest relative result is BrokenMath (sycophancy, #7 of 9); its weakest is BrokenMath (sycophancy, #7 of 9).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Hugging Face ↗Qwen/Qwen3-4B-Thinking-2507
- Official model page ↗Exact model document · Reviewed official Hugging Face owner · official repository
Published eval results
Rank is within that sub-eval. Black marks the observed result; the grey dot marks the value implied by the global rank. Values stay on each source’s native scale.
| Eval / sub-eval | Rank | Value | Distribution | Better | Source |
|---|---|---|---|---|---|
| BrokenMathsycophancy | #7 / 9 | 55.6 | ↓ lower | Source ↗official |
Values evaluations
Descriptive values and political-framing results are separate from safety/ethics ranks. Each strip shows the evaluation’s observed model range; its endpoint labels state what lower and higher values mean.