Qwen3-VL-4B-Instruct
Qwen3-VL-4B-Instruct.
9
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Qwen Oct 2025 Qwen3-VL-4B-Instruct
Open weights Small
No Epoch Capabilities Index score yet
- ChartMuseum 37.7% #18 /21
- RefAdv-S 42.5% #16 /19
- ADeptS-Bench Desktop 36.7% #7 /7
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 | |
|---|---|---|---|---|
| SEA-HELM | 50.4 | #60 of 71 | Official leaderboard |
Agents and tools
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| ADeptS-Bench Desktop | 36.7% | #7 of 7 | Official leaderboard | |
| ADeptS-Bench Mobile | 32.6% | #7 of 7 | Official leaderboard |
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| GeoGuesser environment (FineEnvs) | 0.29 | #10 of 14 | Official leaderboard | |
| RoboRewardBench | 1.03 | #16 of 22 | Official leaderboard | |
| WorldVQA | 14.9% | #17 of 22 | Official leaderboard | |
| Daily-Omni | 55.1% | #11 of 14 | Official leaderboard | |
| RefAdv-S | 42.5% | #16 of 19 | Official leaderboard | |
| ChartMuseum | 37.7% | #18 of 21 | Official leaderboard |