InternVL2-8B-MPO
InternVL2-8B-MPO.
8
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Shanghai AI Lab Nov 2024 InternVL2-8B-MPO
Open weights Small
No Epoch Capabilities Index score yet
- A-Bench 72.4% #55 /116
- MMBench-EN v1.1 76.5% #81 /178
- MMBench-CN v1.1 76.4% #72 /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 | 76.4% | #72 of 178 | Official leaderboard |
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| CCBench (MMBench Chinese Culture) | 74.7% | #20 of 152 | Official leaderboard | |
| MMStar | 62.5% | #45 of 173 | Official leaderboard | |
| MathVista | 67.3% | #13 of 43 | Official leaderboard | |
| MMBench | 79.2% | #61 of 155 | Official leaderboard | |
| MMBench-EN v1.1 | 76.5% | #81 of 178 | Official leaderboard | |
| A-Bench | 72.4% | #55 of 116 | Official leaderboard |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| OpenVLM Leaderboard | 64.9 | #57 of 173 | Official leaderboard |