Qwen-VL-Chat
Qwen-VL-Chat.
Released 20 Aug 2023
16
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Unknown lab Aug 2023
Qwen-VL-Chat
No Epoch Capabilities Index score yet
- OCRBench v2 25.7% #55 /65
- A-Bench 63.1% #105 /116
- VCR (Visual Caption Restoration) 21.1% #25 /42
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 | 57.5% | #152 of 178 | Official leaderboard |
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| OlympicArena | 7.34% | #24 of 25 | Official leaderboard |
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| CCBench (MMBench Chinese Culture) | 41.2% | #88 of 152 | Official leaderboard | |
| VCR (Visual Caption Restoration) | 21.1% | #25 of 42 | Official leaderboard | |
| ScienceQA | 68.2% | #15 of 23 | Epoch AI | |
| MME | 1487.6 | #12 of 16 | Official leaderboard | |
| Image2Struct | 24.6 | #14 of 18 | Official leaderboard | |
| OCRBench v2 | 25.7% | #55 of 65 | Official leaderboard | |
| MMBench-EN v1.1 | 60.8% | #158 of 178 | Official leaderboard | |
| MMBench | 61.8% | #140 of 155 | Official leaderboard | |
| A-Bench | 63.1% | #105 of 116 | Official leaderboard | |
| MMMU | 35.9% | #126 of 136 | Official leaderboard | |
| MMStar | 34.5% | #163 of 173 | Official leaderboard | |
| VHELM | 4.73 | #40 of 41 | Official leaderboard | |
| Video-MME | 41.9% | #26 of 26 | Official leaderboard |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| OpenVLM Leaderboard | 45.2 | #146 of 173 | Official leaderboard |