Qwen3 32B
| Released | 2025-04-28 |
|---|---|
| Price per 1M | $0.15 in · $0.60 out |
| Overall score | 42.2 · rank 181 |
| Context window | 131,072 tokens |
| Provider | Alibaba |
| Weights | Open weights |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 42.2 | 181 | 9 |
| Overall: Coding | 40.8 | 184 | 6 |
| Overall: Reasoning | 44.9 | 161 | 4 |
| Overall: Agentic work | 42.0 | 180 | 6 |
| Overall: Frontend | 39.8 | 173 | 2 |
| Coding | 39.8 | 176 | 2 |
| Agents | 42.9 | 144 | 1 |
| Reasoning | 42.5 | 170 | 3 |
| Math | 48.0 | 130 | 1 |
| General | 40.9 | 159 | 2 |
| Value vs price | −1.5 | 140 |
Configurations
| Configuration | Balanced | Benchmarks |
|---|---|---|
| Unspecified setting | 42.2 ±1.8 | 8 |
| Non-reasoning | 40.2 ±5.5 | 3 |
Evidence
Coding 39.8 ±1.5
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Aider Polyglot | 40.0% | Epoch AI | 2026-11-11 |
| SciCode | 35.4% | Epoch AI | 2026-11-11 |
Agents 42.9 ±3.6
Reasoning 42.5 ±4.3
| Benchmark | Result | Source | Date |
|---|---|---|---|
| GPQA Diamond | 65.7% | Epoch AI | 2026-08-28 |
| CritPt | 0.3% | Epoch AI | 2026-11-11 |
| Kagi Reasoning Benchmark | 48.7% | Kagi | 2026-11-11 |
Math 48.0 ±3.6
| Benchmark | Result | Source | Date |
|---|---|---|---|
| OTIS Mock AIME 2024-2025 | 66.9% | Epoch AI | 2026-08-30 |
General 40.9 ±3.3
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LMArena Text | 1,347 | LMArena | 2026-11-09 |
| EQ-Bench Longform Creative Writing | 40.5% | EQ-Bench | 2026-11-11 |
Results not used in the score
| Benchmark | Result | Source | Why not used |
|---|---|---|---|
| BFCL v4 | 46.8% | BFCL | A stronger configuration result was used |
| GPQA Diamond | 54.1% | Epoch AI | A stronger configuration result was used |
| OTIS Mock AIME 2024-2025 | 23.1% | Epoch AI | A stronger configuration result was used |
Names matched to this model
qwen3-32b