Qwen2.5-VL-7B
Qwen2.5-VL-7B ranks first on ODV-Bench.
86
Benchmarks with a score
1
Ranked first, out of five or more models
8
In the top three
Qwen2.5-VL-7B
Open weights Small
No Epoch Capabilities Index score yet
- MMLongBench-Doc 25.1% #17 /17
- MM-BrowseComp 0% #11 /11
- HiPhO 12.2% #34 /36
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 | |
| SimpleVQA | 43.2% | #5 of 13 | Official leaderboard | |
| Kaleidoscope | 39.6% | #3 of 7 | Official leaderboard | |
| Video SimpleQA | 25.3% | #12 of 27 | Official leaderboard | |
| Creation-MMBench | -29.80 | #13 of 19 | Official leaderboard | |
| Stick to Your Role! | 0.26 | #11 of 15 | Official leaderboard |
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| HiPhO | 12.2% | #34 of 36 | Official leaderboard |
Coding
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| SArena | 0.78 | #15 of 17 | Official leaderboard |
Agents and tools
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| ScreenSpot-Pro | 26.8% | #6 of 11 | Official leaderboard | |
| OSWorld-G | 31.4% | #2 of 3 | Official leaderboard | |
| UI-Vision Element Grounding | 0.85% | #4 of 5 | Official leaderboard | |
| GameHorizon | 56.7 | #34 of 37 | Official leaderboard | |
| SnakeBench | 8 | #185 of 188 | Official leaderboard | |
| MM-BrowseComp | 0% | #11 of 11 | Official leaderboard | |
| AndroidWorld | 27.6% | #9 of 9 | Official leaderboard | |
| WARC-Bench | 4.67% | #8 of 8 | Official leaderboard | |
| BrowseComp-VL | 2.70% | #4 of 4 | Official leaderboard |
Professional work
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| BizFinBench | 56.7% | #11 of 13 | Official leaderboard |
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| SEED-Bench-2-Plus | 70.7% | #13 of 136 | Official leaderboard | |
| CoreCognition | 62.7% | #13 of 119 | Official leaderboard | |
| MM-Vet | 69.7% | #22 of 164 | Official leaderboard | |
| MMBench-EN v1.1 | 82.4% | #34 of 178 | Official leaderboard | |
| ODV-Bench | 55.6% | #1 of 5 | 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 | |
| CausalVQA | 49% | #1 of 4 | Official leaderboard | |
| CharXiv (DQ) | 73.9% | #18 of 67 | Official leaderboard | |
| CCBench (MMBench Chinese Culture) | 59.2% | #41 of 152 | Official leaderboard | |
| VLADBench | 50.8% | #2 of 7 | Official leaderboard | |
| VideoEval-Pro | 27.7% | #3 of 10 | Official leaderboard | |
| SITE | 31.4% | #2 of 6 | Official leaderboard | |
| VHELM | 60.9 | #14 of 41 | Official leaderboard | |
| VRBench | 56.5% | #7 of 19 | Official leaderboard | |
| We-Math | 36.2% | #8 of 21 | Official leaderboard | |
| Do You See Me | 44.9% | #2 of 5 | Official leaderboard | |
| MeasureBench Real-world | 14.6% | #8 of 19 | Official leaderboard | |
| ViewSpatial-Bench | 36.9% | #3 of 7 | 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 | |
| QIVD | 50.6% | #2 of 4 | Official leaderboard | |
| Progress-Bench | 36.5 | #5 of 9 | Official leaderboard | |
| MMBench-Video | 1.49 | #16 of 28 | Official leaderboard | |
| VideoReasonBench | 1.30% | #8 of 14 | Official leaderboard | |
| Video-MMMU | 47.4% | #14 of 24 | Official leaderboard | |
| VisualPuzzles | 33.7% | #17 of 29 | Official leaderboard | |
| Video-Holmes | 27.8% | #3 of 5 | Official leaderboard | |
| MMMU-Pro | 38.3% | #36 of 57 | Official leaderboard | |
| MeasureBench Synthetic | 10.9% | #13 of 19 | Official leaderboard | |
| VisuLogic | 26% | #12 of 17 | Official leaderboard | |
| SpatialViz-Bench | 30.8% | #10 of 14 | Official leaderboard | |
| EmoBench-M | 52.9% | #11 of 15 | Official leaderboard | |
| LEGO-Puzzles | 31.5% | #12 of 16 | Official leaderboard | |
| OmniVideoBench | 29.8% | #6 of 8 | Official leaderboard | |
| ERQA | 34.4% | #13 of 17 | Official leaderboard | |
| MATH-Vision (MathVision) | 25.1% | #81 of 105 | Official leaderboard | |
| VCR-Bench | 30.4% | #7 of 9 | Official leaderboard | |
| OCR-Reasoning | 15.7% | #12 of 15 | Official leaderboard | |
| OVO-S-Bench | 44.2% | #12 of 15 | Official leaderboard | |
| VideoMME v2 (with subtitles) | 14.4% | #25 of 31 | Official leaderboard | |
| RoboRewardBench | 1.17 | #18 of 22 | Official leaderboard | |
| MORSE-500 | 11.2% | #9 of 11 | Official leaderboard | |
| EmbodiedBench EB-Manipulation | 9.60% | #14 of 17 | Official leaderboard | |
| SpaCE-10 | 33.3% | #30 of 36 | Official leaderboard | |
| GSM8K-V | 15.2% | #20 of 24 | Official leaderboard | |
| JointAVBench | 47.7% | #5 of 6 | Official leaderboard | |
| MMSI-Bench | 25.9% | #24 of 28 | Official leaderboard | |
| Daily-Omni | 40.7% | #12 of 14 | Official leaderboard | |
| MindCube | 29.3% | #6 of 7 | Official leaderboard | |
| EmbodiedBench EB-ALFRED | 4.70% | #15 of 17 | Official leaderboard | |
| RefAdv-S | 39.3% | #17 of 19 | Official leaderboard | |
| CrossVid | 18.3% | #12 of 13 | Official leaderboard | |
| MathCanvas-Bench | 8.90% | #15 of 16 | Official leaderboard | |
| EmbodiedBench EB-Habitat | 14.3% | #16 of 17 | Official leaderboard | |
| EmbodiedBench EB-Navigation | 20.3% | #16 of 17 | Official leaderboard | |
| MM-HELIX | 8.00% | #16 of 17 | Official leaderboard | |
| Math-VR | 3.00% | #26 of 26 | Official leaderboard | |
| MMLongBench-Doc | 25.1% | #17 of 17 | Official leaderboard | |
| MME-CC | 7.50% | #12 of 12 | Official leaderboard | |
| MME-Reasoning | 26.8% | #11 of 11 | Official leaderboard | |
| ViVerBench | 57% | #8 of 8 | Official leaderboard | |
| Video-Oasis | 29.2% | #4 of 4 | Official leaderboard |
Safety and security
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Video-SafetyBench | 2.20 | #10 of 15 | Official leaderboard |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| OpenVLM Leaderboard | 70.9 | #32 of 173 | Official leaderboard |