MiniCPM-V 2.0
MiniCPM-V 2.0 places in the top three on GMAI-MMBench.
OpenBMB (ModelBest) Released April 9th, 2024 Family MiniCPM-V The lab's model card Compare with others 17
Benchmarks with a score
0
Ranked first, out of five or more models
1
In the top three
OpenBMB (ModelBest) Apr 2024 MiniCPM-V 2.0
Open weights Small
No Epoch Capabilities Index score yet
- MM-Vet 41% #119 /164
- SEED-Bench-2-Plus 51.9% #101 /136
- A-Bench 68% #86 /116
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 | 64.5% | #127 of 178 | Official leaderboard |
Professional work
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| GMAI-MMBench | 42.5% | #2 of 13 | Official leaderboard |
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| CCBench (MMBench Chinese Culture) | 45.3% | #75 of 152 | Official leaderboard | |
| MM-Vet | 41% | #119 of 164 | Official leaderboard | |
| OCRBench | 60.5% | #8 of 11 | Official leaderboard | |
| A-Bench | 68% | #86 of 116 | Official leaderboard | |
| SEED-Bench-2-Plus | 51.9% | #101 of 136 | Official leaderboard | |
| MMBench | 69.1% | #118 of 155 | Official leaderboard | |
| MMBench-EN v1.1 | 67% | #138 of 178 | Official leaderboard | |
| MathVista | 40.6% | #36 of 43 | Official leaderboard | |
| MMStar | 39.1% | #147 of 173 | Official leaderboard | |
| MME | 1443.2 | #15 of 17 | Official leaderboard | |
| MMMU | 37.1% | #121 of 136 | Official leaderboard | |
| CharXiv | 18.5% | #69 of 77 | Official leaderboard | |
| CharXiv (DQ) | 35.8% | #61 of 67 | Official leaderboard | |
| MTVQA-Test | 7.40% | #17 of 18 | Official leaderboard |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| OpenVLM Leaderboard | 47.9 | #135 of 173 | Official leaderboard |