Qwen2.5-VL-7B
Qwen2.5-VL-7B.
27
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Qwen Jan 2025 Qwen2.5-VL-7B
Open weights Small
No Epoch Capabilities Index score yet
- OCRBench v2 41.8% #39 /65
- HiPhO 12.2% #33 /35
- VisualPuzzles 33.7% #17 /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 | 82.1% | #32 of 178 | Official leaderboard | |
| Creation-MMBench | -29.80 | #13 of 19 | Official leaderboard |
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| HiPhO | 12.2% | #33 of 35 | Official leaderboard |
Agents and tools
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| ScreenSpot-Pro | 26.8% | #6 of 11 | Official leaderboard | |
| SnakeBench | 8 | #180 of 183 | Official leaderboard | |
| AndroidWorld | 27.6% | #10 of 10 | Official leaderboard |
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| MMBench-EN v1.1 | 82.4% | #34 of 178 | Official leaderboard | |
| MMBench | 83.2% | #32 of 155 | Official leaderboard | |
| MMStar | 64.1% | #37 of 173 | Official leaderboard | |
| A-Bench | 75.7% | #27 of 116 | Official leaderboard | |
| CharXiv | 42.5% | #18 of 77 | Official leaderboard | |
| CCBench (MMBench Chinese Culture) | 59.2% | #41 of 152 | Official leaderboard | |
| VHELM | 60.9 | #14 of 41 | Official leaderboard | |
| MMMU | 58.6% | #63 of 136 | Official leaderboard | |
| KRETA | 68.5% | #8 of 17 | Official leaderboard | |
| Point-Bench | 56.3% | #8 of 17 | Official leaderboard | |
| Video-MMMU | 47.4% | #13 of 23 | Official leaderboard | |
| VisualPuzzles | 33.7% | #17 of 29 | Official leaderboard | |
| OCRBench v2 | 41.8% | #39 of 65 | Official leaderboard | |
| MMMU-Pro | 38.3% | #36 of 57 | Official leaderboard | |
| VisuLogic | 26% | #12 of 17 | Official leaderboard | |
| ERQA | 34.4% | #13 of 17 | Official leaderboard | |
| MATH-Vision (MathVision) | 25.1% | #81 of 105 | Official leaderboard | |
| RoboRewardBench | 1.17 | #15 of 19 | Official leaderboard | |
| VideoMME v2 (with subtitles) | 14.4% | #25 of 31 | Official leaderboard | |
| Math-VR | 3.00% | #26 of 26 | Official leaderboard |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| OpenVLM Leaderboard | 70.9 | #32 of 173 | Official leaderboard |