Emu2-Chat
Emu2-Chat.
8
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Beijing Academy of Artificial Intelligence Dec 2023
Emu2-Chat
Open weights Mid-size
No Epoch Capabilities Index score yet
- OCRBench v2 20.2% #61 /65
- MMMU 36.3% #123 /136
- MMBench-EN v1.1 61.3% #157 /178
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 | 44.3% | #167 of 178 | Official leaderboard |
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| MMStar | 40.7% | #136 of 173 | Official leaderboard | |
| MMBench | 63.6% | #136 of 155 | Official leaderboard | |
| MMBench-EN v1.1 | 61.3% | #157 of 178 | Official leaderboard | |
| MMMU | 36.3% | #123 of 136 | Official leaderboard | |
| CCBench (MMBench Chinese Culture) | 18.8% | #140 of 152 | Official leaderboard | |
| OCRBench v2 | 20.2% | #61 of 65 | Official leaderboard |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| OpenVLM Leaderboard | 39.2 | #163 of 173 | Official leaderboard |