Qwen3 8B
| Released | 2025-04-29 |
|---|---|
| Price per 1M | $0.070 in · $0.18 out |
| Overall score | 36.6 · rank 210 |
| Context window | 32,768 tokens |
| Provider | Alibaba |
| Weights | Open weights (Apache-2.0) |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 36.6 | 210 | 5 |
| Overall: Coding | 32.1 | 224 | 4 |
| Overall: Reasoning | 42.9 | 175 | 3 |
| Overall: Agentic work | 37.1 | 204 | 4 |
| Overall: Frontend | 27.6 | 220 | 1 |
| Coding | 27.6 | 207 | 1 |
| Agents | 40.3 | 154 | 1 |
| Reasoning | 40.3 | 193 | 2 |
| Math | 46.2 | 142 | 1 |
| Value vs price | −4.2 | 155 |
Configurations
| Configuration | Balanced | Benchmarks |
|---|---|---|
| Unspecified setting | 36.6 ±2.9 | 5 |
| Non-reasoning | 38.0 ±5.7 | 2 |
Evidence
Coding 27.6 ±4.7
Agents 40.3 ±3.6
Reasoning 40.3 ±3.5
| Benchmark | Result | Source | Date |
|---|---|---|---|
| GPQA Diamond | 56.8% | Epoch AI | 2026-08-27 |
| CritPt | 0.0% | Epoch AI | 2026-11-11 |
Math 46.2 ±3.6
| Benchmark | Result | Source | Date |
|---|---|---|---|
| OTIS Mock AIME 2024-2025 | 56.1% | Epoch AI | 2026-08-27 |
Results not used in the score
| Benchmark | Result | Source | Why not used |
|---|---|---|---|
| BFCL v4 | 40.4% | BFCL | A stronger configuration result was used |
| GPQA Diamond | 47.5% | Epoch AI | A stronger configuration result was used |
| OTIS Mock AIME 2024-2025 | 22.2% | Epoch AI | A stronger configuration result was used |
Names matched to this model
qwen3-8b