DeepSeek · model passport
DeepSeek R1 Distill Qwen 32b
deepseek-r1-distill-qwen-32b- Best percentile
- 47.2MMLU-Pro (Artificial Analysis)
- Composite standing
- 40.2shrunk · 6/27 axes
What the data says
Benchmarked on 6 of 27 tracked axes. Every figure below is the model's own published result on that board.
Weakest axes
- 6.5 pct — IFBench (Artificial Analysis) (22.9%)
Uneven: 40.7 percentile points between its best and worst axis — 47.2 pct on MMLU-Pro (Artificial Analysis) versus 6.5 pct on IFBench (Artificial Analysis).
- MMLU-Pro (Artificial Analysis)47.2 pct73.9%Verify →
- GPQA Diamond45.2 pct64.1%Verify →
- AIME (math)40.5 pct55.6%Verify →
- LiveBench39.4 pct47.5%Verify →
- LiveCodeBench (Artificial Analysis)33 pct27.0%Verify →
- IFBench (Artificial Analysis)6.5 pct22.9%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
- 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.
DeepSeek-R1-Distill-Qwen-32B (DeepSeek) has a shrunk composite score of 40.2 and a raw composite score of 35.3, with coverage across 6 of 27 axes.
standingVerify →
DeepSeek-R1-Distill-Qwen-32B, from DeepSeek, ranks at percentile 6.5 on IFBench (Artificial Analysis), a weakness for the model.
weaknessVerify →
DeepSeek-R1-Distill-Qwen-32B (DeepSeek) ranks between 252 and 740 across the 3 templates covered, a spread of 488, with its best rank under the All-rounder template and its worst under the All sources template.
rank swingVerify →
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 →