Qwen2.5-VL-3B
Qwen2.5-VL-3B.
39
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Qwen Jan 2025 Qwen2.5-VL-3B
Open weights Small
No Epoch Capabilities Index score yet
- Video SimpleQA 22.6% #18 /27
- OCR-Reasoning 12.2% #13 /15
- VisualPuzzles 31.2% #19 /29
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 | |
|---|---|---|---|---|
| MMBench-CN v1.1 | 76.5% | #71 of 178 | Official leaderboard | |
| Video SimpleQA | 22.6% | #18 of 27 | Official leaderboard | |
| Kaleidoscope | 35.6% | #5 of 7 | Official leaderboard | |
| Stick to Your Role! | 0.13 | #13 of 15 | Official leaderboard |
Agents and tools
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| ScreenSpot-Pro | 16.1% | #8 of 11 | Official leaderboard | |
| OSWorld-G | 27.3% | #3 of 3 | Official leaderboard |
Professional work
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| BizFinBench | 39% | #13 of 13 | Official leaderboard |
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| SEED-Bench-2-Plus | 68.5% | #25 of 136 | Official leaderboard | |
| CCBench (MMBench Chinese Culture) | 62% | #37 of 152 | Official leaderboard | |
| CoreCognition | 59.8% | #33 of 119 | Official leaderboard | |
| KRETA | 71.8% | #5 of 17 | Official leaderboard | |
| A-Bench | 74.9% | #35 of 116 | Official leaderboard | |
| MM-Vet | 60% | #56 of 164 | Official leaderboard | |
| MMBench | 79.1% | #62 of 155 | Official leaderboard | |
| MMStar | 56.3% | #73 of 173 | Official leaderboard | |
| MMBench-EN v1.1 | 77% | #80 of 178 | Official leaderboard | |
| CharXiv | 31.3% | #42 of 77 | Official leaderboard | |
| CharXiv (DQ) | 58.6% | #37 of 67 | Official leaderboard | |
| MMMU | 53.1% | #77 of 136 | Official leaderboard | |
| MindCube | 33.2% | #4 of 7 | Official leaderboard | |
| ViewSpatial-Bench | 35.9% | #4 of 7 | Official leaderboard | |
| VisualPuzzles | 31.2% | #19 of 29 | Official leaderboard | |
| Progress-Bench | 39.0 | #6 of 9 | Official leaderboard | |
| SITE | 29.5% | #4 of 6 | Official leaderboard | |
| VHELM | 40.7 | #29 of 41 | Official leaderboard | |
| MMMU-Pro | 31.6% | #41 of 57 | Official leaderboard | |
| MMSI-Bench | 26.5% | #21 of 28 | Official leaderboard | |
| All-Angles Bench | 45.2% | #14 of 18 | Official leaderboard | |
| SpaCE-10 | 34.8% | #29 of 36 | Official leaderboard | |
| MATH-Vision (MathVision) | 21.2% | #87 of 105 | Official leaderboard | |
| SpatialViz-Bench | 30.2% | #12 of 14 | Official leaderboard | |
| OCR-Reasoning | 12.2% | #13 of 15 | Official leaderboard | |
| ERQA | 32.6% | #15 of 17 | Official leaderboard | |
| Math-VR | 5.30% | #24 of 26 | Official leaderboard | |
| Daily-Omni | 37.4% | #13 of 14 | Official leaderboard | |
| RefAdv-S | 25.3% | #18 of 19 | Official leaderboard | |
| RoboRewardBench | 1.61 | #22 of 22 | Official leaderboard | |
| MORSE-500 | 7.60% | #11 of 11 | Official leaderboard |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| OpenVLM Leaderboard | 64.5 | #61 of 173 | Official leaderboard |