Qwen3.5 9B
| Released | 2026-02-23 |
|---|---|
| Price per 1M | $0.12 in · $0.18 out |
| Overall score | 40.3 · rank 190 |
| Context window | 262,144 tokens |
| Provider | Alibaba |
| Weights | Open weights |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 40.3 | 190 | 6 |
| Overall: Coding | 37.6 | 200 | 4 |
| Overall: Reasoning | 46.7 | 143 | 4 |
| Overall: Agentic work | 38.8 | 197 | 4 |
| Overall: Frontend | 35.7 | 197 | 1 |
| Coding | 35.7 | 188 | 1 |
| Agents | 38.1 | 164 | 1 |
| Reasoning | 46.5 | 142 | 2 |
| Math | 46.9 | 137 | 2 |
| Value vs price | −1.5 | 139 |
Configurations
| Configuration | Balanced | Benchmarks |
|---|---|---|
| Unspecified setting | 40.0 ±2.8 | 6 |
| Non-reasoning | 46.7 ±5.3 | 3 |
Evidence
Coding 35.7 ±4.7
Agents 38.1 ±2.5
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Terminal-Bench 2.0 | 9.2% | Epoch AI | 2026-03-02 |
Reasoning 46.5 ±3.5
| Benchmark | Result | Source | Date |
|---|---|---|---|
| GPQA Diamond | 79.0% | Epoch AI | 2026-08-27 |
| CritPt | 0.6% | Epoch AI | 2026-11-11 |
Math 46.9 ±2.8
| Benchmark | Result | Source | Date |
|---|---|---|---|
| OTIS Mock AIME 2024-2025 | 61.7% | Epoch AI | 2026-08-27 |
| MathArena Final-Answer Competitions | 48.5% | MathArena | 2026-11-11 |
Results not used in the score
| Benchmark | Result | Source | Why not used |
|---|---|---|---|
| CritPt | 0.3% | Epoch AI | A stronger configuration result was used |
| GPQA Diamond | 78.9% | Epoch AI | A stronger configuration result was used |
| OTIS Mock AIME 2024-2025 | 42.8% | Epoch AI | A stronger configuration result was used |
Names matched to this model
qwen3-5-9b