Qwen3 30B A3B
| Released | 2025-04-28 |
|---|---|
| Price per 1M | $0.12 in · $0.50 out |
| Overall score | 42.5 (early, few results) |
| Context window | 131,072 tokens |
| Provider | Alibaba |
| Weights | Open weights |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 42.5 | 4 | |
| Overall: Coding | 42.1 | 1 | |
| Overall: Reasoning | 44.4 | 2 | |
| Overall: Agentic work | 42.1 | 1 | |
| Reasoning | 42.1 | 1 | |
| Math | 47.3 | 1 | |
| General | 38.1 | 2 | |
| Value vs price | −0.8 |
Configurations
| Configuration | Balanced | Benchmarks |
|---|---|---|
| Unspecified setting | 42.5 ±4.7 | 4 |
| Non-reasoning | 39.0 ±5.6 | 2 |
Evidence
Reasoning 42.1 ±4.6
| Benchmark | Result | Source | Date |
|---|---|---|---|
| GPQA Diamond | 61.7% | Epoch AI | 2026-08-30 |
Math 47.3 ±3.6
| Benchmark | Result | Source | Date |
|---|---|---|---|
| OTIS Mock AIME 2024-2025 | 62.8% | Epoch AI | 2026-08-28 |
General 38.1 ±3.3
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LMArena Text | 1,326 | LMArena | 2026-11-09 |
| EQ-Bench Longform Creative Writing | 35.6% | EQ-Bench | 2026-11-11 |
Results not used in the score
| Benchmark | Result | Source | Why not used |
|---|---|---|---|
| GPQA Diamond | 50.4% | Epoch AI | A stronger configuration result was used |
| OTIS Mock AIME 2024-2025 | 25.6% | Epoch AI | A stronger configuration result was used |
Names matched to this model
qwen3-30b-a3b