Qwen3.5-2B
Qwen3.5-2B.
Qwen Released 24 Feb 2026 4
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Qwen Feb 2026 Qwen3.5-2B
Open weights
No Epoch Capabilities Index score yet
- CritPt 0% #153 /160
- ParseBench 27.3% #42 /42
- AgentIF (2026-10 setting) 55.8% #20 /24
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 | 55.3% | #126 of 212 | Official leaderboard | |
| AgentIF (2026-10 setting) | 55.8% | #20 of 24 | Official leaderboard |
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| CritPt | 0% | #153 of 160 | Epoch AI |
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| ParseBench | 27.3% | #42 of 42 | Official leaderboard |