BlogLLM Benchmark Scores as Published, Side by Side
HumanEval: Results as Published
Every result the catalog holds for HumanEval: 11 models from 7 developers, read from 3 pages. Each number is as printed by the company named beside it; nothing is ranked or rescored. Models are listed by developer, newest first.
Area Code GenerationMaintainer OpenAI (Mark Chen and co-authors)Introduced 2021Data version 2026103001, as of 2026-10-30
HumanEval tests Python code generation with 164 hand-written programming problems given as function signatures and docstrings, each checked by unit tests. The score is the share of problems solved, usually pass@1.
HumanEval
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| GPT-4oOpenAI, released 2024-05-13 | 91.5% | Mistral AI, Medium is the new largechecked 2026-10-15 | - |
| Claude 3.7 SonnetAnthropic, released 2025-02-24 | 92.1% | Mistral AI, Medium is the new largechecked 2026-10-15 | - |
| Llama 4 MaverickMeta, released 2025-04-05 | 85.4% | Mistral AI, Medium is the new largechecked 2026-10-15 | - |
| DeepSeek-V4-Flash-BaseDeepSeek, released 2026-04-24 | 69.5% | DeepSeek, DeepSeek-V4-Pro (preview) model cardchecked 2026-10-15 | - |
| DeepSeek-V4-Pro-BaseDeepSeek, released 2026-04-24 | 76.8% | DeepSeek, DeepSeek-V4-Pro (preview) model cardchecked 2026-10-15 | - |
| DeepSeek-V3.2-BaseDeepSeek, released 2025-12-01 | 62.8% | DeepSeek, DeepSeek-V4-Pro (preview) model cardchecked 2026-10-15 | - |
| DeepSeek-V3-0324DeepSeek, released 2025-03-24 | 93.3% | Mistral AI, Medium is the new largechecked 2026-10-15 | - |
| Mistral Medium 3Mistral AI, released 2025-05-07 | 92.1% | Mistral AI, Medium is the new largechecked 2026-10-15 | - |
HumanEval+
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| Kimi K2 BaseMoonshot AI, released 2025-07-11 | 84.8% | Xiaomi, Xiaomi MiMo-V2.5-Pro model cardchecked 2026-10-15 | Harness: 1-shot |
| MiMo-V2.5 BaseXiaomi, released 2026-04-27 | 71.3% | Xiaomi, Xiaomi MiMo-V2.5-Pro model cardchecked 2026-10-15 | Harness: 1-shot |
| MiMo-V2.5-Pro BaseXiaomi, released 2026-04-27 | 75.6% | Xiaomi, Xiaomi MiMo-V2.5-Pro model cardchecked 2026-10-15 | Harness: 1-shot |
Every number here is read from the same catalog file as the benchmark table, data version 2026103001, and is the number the table shows for that model and test. Where one page printed a model under several setups, each value is listed. The catalog is public in armanobosyan/sugra-llm-benchmarks; a wrong number can be reported from the table, with Report an error under the value, or as an issue in that repository.