HumanEvalPack
Cohere Command A 76.2% leads since April 2025 Models write functions for HumanEval problems translated into Python, JavaScript, Java, Go, C++ and Rust. Hidden tests give pass@1.
The pack also has code repair and explanation tasks. Labs usually report the synthesize task.
- Made by
- Hugging Face and BigCode (Muennighoff et al., OctoPack)
- Released
- August 2023
- Kind
- Function-level problems
- Level
- University
- Scored
- Checked automatically
- Answers
- Code
- Tasks
- All public
- Strongest model tested
-
Qwen-14B #213 on the capability index - Last in a system card
- April 2025
- Last model added
- April 2025
Cohere Command A leads with 76.2% among models released by March 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 March 2025, and nobody has reported a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- Claude Fable 5.2
-
Gemini 4 Carbon - GPT-6 Astra
- Claude Opus 5.5
- and 16 more
- 1 Cohere Command A 76.2%
- 2 Qwen-14B 33.7%
- 3 Qwen-7B 24.2%
Source: Labs’ model cards
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Cohere Command A | 76.2% | Apr 2025 | Lab model card | |
| 2 | Qwen-14B | 33.7% | Sep 2023 | Lab model card | |
| 3 | Qwen-7B | 24.2% | Sep 2023 | Lab model card |
2 models have held number one in labs’ own numbers since its release in August 2023
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Labs’ model cards
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Labs’ model cards
Labs report it only in system cards
We read the headline results of 522 launch posts from 52 labs, and none of them list this benchmark. Some system cards do, below.
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 |
|---|---|---|---|---|
| Apr 1, 2025 | Cohere Command A technical report | 76.2 | HE (All), HumanEval in six languages (Table 12, Table 26) | Capabilities |
| Sep 28, 2023 | Qwen-7B technical report | 24.2 | HumanEvalPack (synthesize) zero-shot pass@1 average: Python 37.2, JavaScript 23.2, Java 32.9, Go 20.7, C++ 22.0, Rust 9.1 (Table 11) | Capabilities |
| Sep 28, 2023 | Qwen-14B technical report | 33.7 | HumanEvalPack (synthesize) zero-shot pass@1 average: Python 43.9, JavaScript 38.4, Java 42.7, Go 34.1, C++ 24.4, Rust 18.9 (Table 11) | 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%
- 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% - SWE-bench Multilingual In use 300 GitHub-issue tasks across nine programming languages in SWE-bench format. Patch graded by repository tests. Claude Fable 5.2 96.6%
- 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