Codesota · Models · DeepSeek-R1-Distill-Qwen-32BDeepSeek2 results · 2 benchmarks
Model card

DeepSeek-R1-Distill-Qwen-32B.

DeepSeekopen-source
§ 02 · Benchmarks

Every benchmark DeepSeek-R1-Distill-Qwen-32B has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01MATHReasoning · Mathematical Reasoningaccuracy94.3%#13/46—source ↗
02LiveCodeBenchComputer Code · Code Generationpass@162.1%#15/30—source ↗
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 03 · Strengths by area

Where DeepSeek-R1-Distill-Qwen-32B actually performs.

Reasoning
1
benchmark
avg rank #13.0
Computer Code
1
benchmark
avg rank #15.0
§ 05 · Related models

Other DeepSeek models scored on Codesota.

DeepSeek R1
671B MoE params · 19 results
DeepSeek-V3
15 results
DeepSeek-V3.2
14 results
DeepSeek-V3.2-Speciale
11 results
DeepSeek-R1-0528
10 results
DeepSeek-Coder-V2-Instruct
Unknown params · 9 results
DeepSeek-v3-0324
9 results
DeepSeek-v3.1 (no thinking)
7 results
§ 06 · Sources & freshness

Where these numbers come from.

deepseek-paper
1
result
arxiv-2501.12948
1
result
1 of 2 rows marked verified.