Codesota · Models · DeepSeek-R1DeepSeek3 results · 3 benchmarks
Model card

DeepSeek-R1.

DeepSeekopen-sourceReasoning LLM

Open-source reasoning model trained via reinforcement learning.

§ 02 · Benchmarks

Every benchmark DeepSeek-R1 has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01livecodebench—pass@165.9%#3/222026-04-20source ↗
02MATHLanguage & Knowledge · Mathematical Reasoningaccuracy97.3%#6/292026-04-20unverified
03SWE-Bench VerifiedCode & Software Engineering · Code Generationresolve-rate49.2%#33/392026-04-20unverified
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 actually performs.

Language & Knowledge
1
benchmark
avg rank #6.0
Code & Software Engineering
1
benchmark
avg rank #33.0
§ 06 · Sources & freshness

Where these numbers come from.

src
2
results
codesota-api
1
result
1 of 3 rows marked verified.