Qwen2.5 Coder 32B Instruct
Qwen / Qwen
24scores
23benchmarks
$0.66 / $1 per 1M tokenscost in/out
Metadata
Qwen Open source
Aliases: qwen-2.5-coder-32b-instruct, qwen-qwen-2.5-coder-32b-instruct, qwen/qwen-2.5-coder-32b-instruct
| Benchmark | Category | Rank | Score | Sampled |
|---|---|---|---|---|
| Clembench Text v3.0 | Agentic | 25 | 35.32 | 2026-05-06 |
| BigCodeBench | Coding | 6 | 49 | 2026-05-06 |
| BigCodeBench-Hard | Coding | 24 | 27.70 | 2026-05-05 |
| EvalPlus | Coding | 3 | 82.10 | 2026-05-05 |
| HumanEval+ | Coding | 3 | 87.20 | 2026-05-05 |
| MBPP+ | Coding | 3 | 77 | 2026-05-05 |
| SciCode | Coding | 297 | 27.1% | 2026-05-11 |
| TuRTLe Module Completion (NotSoTiny) | Coding | 11 | 11.85 | 2026-05-06 |
| React Native Evals | Frontend Development | 18 | 51.2244% overall | 2026-05-28 |
| MMLU-Redux | General Knowledge | 39 | 0.78 | 2026-05-06 |
| Open LLM Leaderboard v2 | General Knowledge | 276 | 39.89 | 2026-05-06 |
| Artificial Analysis Intelligence Index | Intelligence | 369 | 12.87 | 2026-05-11 |
| Humanity's Last Exam | Intelligence | 434 | 3.8% | 2026-05-11 |
| MMLU-Pro | Intelligence | 257 | 63.5% | 2026-05-11 |
| MuSR | Intelligence | 1112 | 13.72 | 2026-05-06 |
| Open Japanese LLM Leaderboard | Language | 174 | 61.96 | 2026-05-06 |
| Open Japanese LLM Leaderboard | Language | 496 | 46.49 | 2026-05-06 |
| Open Portuguese LLM Leaderboard | Language | 174 | 82.73 | 2026-05-06 |
| MATH Level 5 | Math | 157 | 49.55 | 2026-05-06 |
| TheoremQA | Mathematics | 3 | 0.43 | 2026-05-06 |
| GPQA Diamond | Reasoning | 386 | 41.7% | 2026-05-11 |
| Defects4J | Software Engineering | 22 | 0.271 | 2026-05-27 |
| RepairBench | Software Engineering | 23 | 0.25 | 2026-05-27 |
| TruthfulQA | Truthfulness | 13 | 0.54 | 2026-05-06 |
No matching rows.