Qwen3.5-35B-A3B
Qwen3.5-35B-A3B.
Qwen Released 24 Feb 2026 29
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Qwen Feb 2026 Qwen3.5-35B-A3B
Open weights
142.6
#107 of 271
Epoch Capabilities Index
- Toolathlon 28.7% #32 /50
- CritPt 0.57% #102 /160
- OCRBench v2 65.3% #5 /65
Where it ranks
Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.
Knowledge and language
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| MMLU-Pro | 85.3% | #29 of 212 | Official leaderboard | |
| Judgemark v2.1 | 81.4 | #12 of 42 | Official leaderboard | |
| SEA-HELM | 73.5 | #22 of 62 | Official leaderboard | |
| LMArena (Elo) | 1,394 | #136 of 333 | Official leaderboard | |
| Vectara Hallucination Leaderboard (2025 dataset) | 10.5% | #64 of 104 | Official leaderboard | |
| Judgemark v4 | 40.5 | #30 of 40 | Official leaderboard | |
| Longform Creative Writing (EQ-Bench) | 44.5 | #93 of 119 | Official leaderboard |
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| GPQA Diamond | 83.5% | #76 of 219 | Epoch AI | |
| OTIS Mock AIME 2024-2025 | 70% | #102 of 202 | Epoch AI | |
| DTBench | 66.7% | #91 of 178 | Official leaderboard | |
| MathArena (Apex, IMO, USAMO) | 4.17% | #28 of 47 | Official leaderboard | |
| CritPt | 0.57% | #102 of 160 | Epoch AI | |
| AIME 2026 | 93.3% | #23 of 31 | Official leaderboard | |
| HMMT 2026 | 81.8% | #26 of 31 | Official leaderboard |
Coding
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Code Arena | 1,254 | #111 of 124 | Official leaderboard | |
| SWE-rebench | 17.1% | #13 of 13 | Official leaderboard |
Agents and tools
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| SnakeBench | 25 | #74 of 183 | Official leaderboard | |
| LLM Chess | -26 | #65 of 124 | Official leaderboard | |
| LisanBench | 447.3 | #70 of 133 | Official leaderboard | |
| Toolathlon | 28.7% | #32 of 50 | Official leaderboard | |
| MyPCBench | 7.60% | #8 of 9 | Official leaderboard |
Professional work
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Vending-Bench 2 | $463 | #56 of 66 | Official leaderboard |
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| OCRBench v2 | 65.3% | #5 of 65 | Official leaderboard | |
| MATH-Vision (MathVision) | 83.9% | #15 of 105 | Official leaderboard | |
| VideoMME v2 (with subtitles) | 25.8% | #14 of 31 | Official leaderboard |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Political Science LLM Benchmark | 65% | #17 of 29 | Official leaderboard | |
| LMCA | 29.5% | #83 of 139 | Epoch AI | |
| Conceptual Reasoning Index | 42.1 | #92 of 149 | Official leaderboard | |
| ACCoRD | 55.3 | #104 of 150 | Official leaderboard |
Qwen's models over time
Qwen's models in color, against every other model on the Epoch Capabilities Index, by release date.