Qwen3.5-9B
Qwen3.5-9B.
Qwen Released 24 Feb 2026 28
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Qwen Feb 2026 Qwen3.5-9B
Open weights
139.4
#128 of 271
Epoch Capabilities Index
- Terminal-Bench 2.0 9.21% #42 /43
- CritPt 0.57% #103 /160
- OCRBench v2 58.7% #12 /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 | |
|---|---|---|---|---|
| AgentIF (2026-10 setting) | 65.3% | #4 of 24 | Official leaderboard | |
| MMLU-Pro | 82.5% | #46 of 212 | Official leaderboard | |
| Judgemark v2.1 | 75.0 | #21 of 42 | Official leaderboard | |
| SEA-HELM | 69.1 | #34 of 62 | Official leaderboard | |
| HELM Arabic Enterprise | 62.4 | #17 of 23 | Official leaderboard | |
| HELM Arabic | 73.1 | #22 of 28 | Official leaderboard | |
| Judgemark v4 | 32.4 | #33 of 40 | Official leaderboard | |
| Wer wird Millionär? LLM Benchmark | 169.0 | #64 of 76 | Official leaderboard |
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| GPQA Diamond | 79% | #91 of 219 | Epoch AI | |
| OTIS Mock AIME 2024-2025 | 61.7% | #114 of 202 | Epoch AI | |
| DTBench | 52% | #109 of 178 | Official leaderboard | |
| CritPt | 0.57% | #103 of 160 | Epoch AI | |
| AIME 2026 | 92.5% | #24 of 31 | Official leaderboard | |
| HMMT 2026 | 71.2% | #29 of 31 | Official leaderboard | |
| MathArena (Apex, IMO, USAMO) | 0.52% | #46 of 47 | Official leaderboard |
Agents and tools
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| LLM Chess | -200 | #94 of 124 | Official leaderboard | |
| GAIA | 13.9% | #49 of 57 | Official leaderboard | |
| PinchBench | 34.8% | #46 of 48 | Official leaderboard | |
| Terminal-Bench 2.0 | 9.21% | #42 of 43 | Official leaderboard | |
| WitnessBench | 0.11% | #12 of 12 | Official leaderboard | |
| MyPCBench | 6.50% | #9 of 9 | Official leaderboard |
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| OCRBench v2 | 58.7% | #12 of 65 | Official leaderboard | |
| VideoMME v2 (with subtitles) | 26.2% | #13 of 31 | Official leaderboard | |
| MDPBench | 65.7 | #8 of 9 | Official leaderboard | |
| ParseBench | 31.9% | #39 of 42 | Official leaderboard |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| LMCA | 24.5% | #96 of 139 | Epoch AI | |
| Conceptual Reasoning Index | 35.1 | #107 of 149 | Official leaderboard | |
| ACCoRD | 50.2 | #110 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.