Qwen3.5 35B-A3B
| Released | 2026-02-23 |
|---|---|
| Price per 1M | $0.15 in · $1.00 out |
| Overall score | 43.3 · rank 170 |
| Context window | 262,144 tokens |
| Provider | Alibaba |
| Weights | Open weights |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 43.3 | 170 | 9 |
| Overall: Coding | 39.3 | 190 | 5 |
| Overall: Reasoning | 48.4 | 130 | 4 |
| Overall: Agentic work | 42.5 | 178 | 4 |
| Overall: Frontend | 35.7 | 198 | 3 |
| Coding | 39.1 | 178 | 2 |
| Reasoning | 48.2 | 128 | 2 |
| Math | 48.7 | 125 | 2 |
| Frontend | 34.0 | 126 | 1 |
| General | 46.1 | 137 | 2 |
| Value vs price | −1.4 | 137 |
Configurations
| Configuration | Balanced | Benchmarks |
|---|---|---|
| Unspecified setting | 44.9 ±2.8 | 7 |
| Non-reasoning | 41.6 ±4.1 | 4 |
Evidence
Coding 39.1 ±2.5
| Benchmark | Result | Source | Date |
|---|---|---|---|
| SWE-rebench | 17.1% | SWE-rebench | 2026-07-01 |
| SciCode | 29.3% | Epoch AI | 2026-11-11 |
Reasoning 48.2 ±3.5
| Benchmark | Result | Source | Date |
|---|---|---|---|
| GPQA Diamond | 83.5% | Epoch AI | 2026-08-28 |
| CritPt | 0.6% | Epoch AI | 2026-11-11 |
Math 48.7 ±2.8
| Benchmark | Result | Source | Date |
|---|---|---|---|
| OTIS Mock AIME 2024-2025 | 70.0% | Epoch AI | 2026-08-30 |
| MathArena Final-Answer Competitions | 56.0% | MathArena | 2026-11-11 |
Frontend 34.0 ±3.0
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LMArena WebDev | 1,253 | LMArena | 2026-11-10 |
General 46.1 ±3.3
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LMArena Text | 1,394 | LMArena | 2026-11-09 |
| EQ-Bench Longform Creative Writing | 44.5% | EQ-Bench | 2026-11-11 |
Results not used in the score
| Benchmark | Result | Source | Why not used |
|---|---|---|---|
| GPQA Diamond | 81.2% | Epoch AI | A stronger configuration result was used |
| OTIS Mock AIME 2024-2025 | 54.4% | Epoch AI | A stronger configuration result was used |
Names matched to this model
qwen3-5-35b-a3b