Qwen3-VL-8B-Instruct
Qwen3-VL-8B-Instruct.
15
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Qwen Oct 2025 Qwen3-VL-8B-Instruct
Open weights Small
No Epoch Capabilities Index score yet
- ChartMuseum 40% #17 /21
- RefAdv-S 52.3% #12 /19
- ParseBench 62% #25 /44
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 | 56.6 | #55 of 71 | Official leaderboard |
Agents and tools
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| ADeptS-Bench Desktop | 40.5% | #5 of 7 | Official leaderboard | |
| ADeptS-Bench Mobile | 37.4% | #5 of 7 | Official leaderboard | |
| SnakeBench | 13 | #177 of 188 | Official leaderboard |
Professional work
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| LMBuild | 16.9% | #18 of 18 | Official leaderboard |
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| RoboRewardBench | 0.89 | #6 of 22 | Official leaderboard | |
| LEGO-Puzzles | 46.2% | #5 of 16 | Official leaderboard | |
| ParseBench | 62% | #25 of 44 | Official leaderboard | |
| GSM8K-V | 26% | #14 of 24 | Official leaderboard | |
| RefAdv-S | 52.3% | #12 of 19 | Official leaderboard | |
| Daily-Omni | 56.8% | #10 of 14 | Official leaderboard | |
| WorldVQA | 16.1% | #16 of 22 | Official leaderboard | |
| MDPBench | 68.3 | #9 of 12 | Official leaderboard | |
| ChartMuseum | 40% | #17 of 21 | Official leaderboard |
Safety and security
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| nocot-bench (NCRI) | 56.0 | #151 of 185 | Official leaderboard |