HumanEval Multi
DeepSeek-V3 82.6% leads since Dec 2024 Dropped Models complete HumanEval problems in Python and seven more languages, including C++, Java, PHP, and Bash. Unit tests score pass@1.
The non-Python versions come from MultiPL-E translations.
- Level
- School Students, from grade school to high school
- Scored
- Checked automatically A program checks the result against an answer key, unit tests or the expected final state.
- Answers
- Code A program or patch run against tests.
DeepSeek-V3 leads with 82.6% among models released by Jan 2025
Best score per model as labs report them in their own cards. Labs pick their own settings, so these compare less cleanly than independent runs.
The newest model with a score here came out in Jan 2025, and nobody has reported a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6 Astra
- Claude Opus 5.5
- GPT-6.1 Terra
- GPT-6.1 Sol
- and 16 more
- 1 DeepSeek-V3 82.6%
- 2 Kimi k1.5 81.5%
- 3 DeepSeek-V2.5 Sep 2024 73.8%
- 4
Codestral 71.4% - 5 DeepSeek LLM 67B 53.3%
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | DeepSeek-V3 | 82.6% | Dec 2024 | Model card | |
| 2 | Kimi k1.5 | 81.5% | Jan 2025 | Model card | |
| 3 | DeepSeek-V2.5 Sep 2024 | 73.8% | Sep 2024 | Model card | |
| 4 | Codestral | 71.4% | Jan 2025 | Model card | |
| 5 | DeepSeek LLM 67B | 53.3% | Jan 2024 | Model card |
3 models have held number one since its release in Nov 2023
Lab claims count from the day the card came out, independent runs from the model’s release.
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
No launch post has listed it since Jan 2025
Launch posts from every lab that has listed it, one tick per post. Tall colored ticks include it, and short gray ones leave it out.
| Date | Launch post | Score | As the post writes it |
|---|---|---|---|
| 20 Jan 2025 | Kimi k1.5 | 81.5 | HumanEval-Mul (Pass@1), short-CoT |
| 13 Jan 2025 | Codestral | 71.4 | HumanEval (average on several languages) |
| 26 Dec 2024 | DeepSeek-V3 | 82.6 | HumanEval-Mul (Pass@1) |
| 5 Sep 2024 | DeepSeek-V2.5 | 73.8 | HumanEval Multi |
3 system cards report it, from 2 labs
Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.
| Date | Document | Score | As the document writes it | Section |
|---|---|---|---|---|
| 20 Jan 2025 | Kimi k1.5 technical report | 81.5 | HumanEval-Mul (Pass@1), short-CoT (Table 3) | Capabilities |
| 26 Dec 2024 | DeepSeek-V3 technical report | 82.6 | HumanEval-Mul (Pass@1), DeepSeek-V3 (Table 6) | Capabilities |
| 5 Jan 2024 | DeepSeek LLM 67B technical report | 53.3 | HumanEval Multilingual, DeepSeek-LLM-Chat 67B (Table 15) | Capabilities |
More in Coding
- SWE-bench Verified In use 500 human-validated GitHub issues from 12 Python repos. Agent writes a patch that must pass hidden tests. Claude Opus 4.7 83.5%
- SWE-bench Multilingual In use 300 GitHub-issue tasks across nine programming languages in SWE-bench format. Patch graded by repository tests. Claude Opus 5.5 93.9%
- LiveCodeBench v6 In use Competitive programming problems collected after model cutoffs from LeetCode, AtCoder, Codeforces. Scored pass@1 on hidden tests. DeepSeek-V4-Pro 93.5%
- DeepSWE In use 113 original long-horizon engineering tasks across 91 repos and five languages, written from scratch. Hand-written verifiers accept alternative solutions. GPT-6 Astra 74.1%
- SciCode In use Scientist-curated research coding problems split into subproblems across natural sciences. Code checked against test cases.
Seed2.1 Pro 59.8% - Codeforces rating In use Model solves recent Codeforces contest problems. An Elo-style rating is computed from simulated contest performance. DeepSeek V4.1 Flash 3,471