Updated daily at 05:00 UTC
- Released
- 12 Nov 2024
- Status
- Legacy
- Context
- 131.1K
- Max output
- —
- Input per 1M tokens
- —
- Output per 1M tokens
- —
- Open weights
- Yes
- License
- apache-2.0
- Parameters
- 32B
- Knowledge cutoff
- —
- Reasoning
- No
- Modalities
- text → text
Category scores
Out of 100, from independent and third-party results only, by method category-2026-09-29.1.
| Category | Score | Rank | Coverage |
|---|---|---|---|
| Coding & software engineering | 16.4 | Not ranked | 1 of 5 |
Benchmark results
Every result we hold for this model, with who ran it and where it was published.
Mathematics
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| GSM8K | Exact match | 93.0% | Self-reported | — | — | Qwen2.5-Coder Technical Report via Epoch AI |
Coding & software engineering
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| Aider Polyglot | Percent correct | 16.4% | Third party | — | — | Aider LLM Leaderboards via Epoch AI |
| Aider Polyglot | Percent correct | 8.0% | Third party | — | — | Aider LLM Leaderboards via Epoch AI |
Human preference
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| Text Arena (arena.ai) | Arena score (Elo scale) | 1271 | Independent | — | 25 Sep 2026 | Arena |
| Text Arena (arena.ai) | Votes | 5432 | Independent | — | 25 Sep 2026 | Arena |
Other Qwen-Coder versions
- Qwen3-Coder-NextFeb 2026
- Qwen3-Coder-30B-A3B-Instruct31 Jul 2025
- Qwen3-Coder-Flash28 Jul 2025
- Qwen3-Coder-480B-A35B-Instruct22 Jul 2025
- Qwen3-Coder-Plus22 Jul 2025
- Qwen-Coder-Plus12 Nov 2024
- Qwen2.5-Coder-0.5B-Instruct12 Nov 2024
- Qwen2.5-Coder-14B-Instruct12 Nov 2024
- Qwen2.5-Coder-3B-Instruct12 Nov 2024
- Qwen-Coder-Turbo19 Sep 2024
- Qwen2.5-Coder-1.5B-Instruct19 Sep 2024
- Qwen2.5-Coder-7B-Instruct19 Sep 2024
- CodeQwen1.5-7B-Chat16 Apr 2024