MiniCPM-Llama3-V 2.5
MiniCPM-Llama3-V 2.5.
14
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
OpenBMB (ModelBest) May 2024 MiniCPM-Llama3-V 2.5
Open weights Small
No Epoch Capabilities Index score yet
- A-Bench 73.3% #49 /116
- VCR (Visual Caption Restoration) 22.4% #22 /42
- OlympicArena 17.4% #20 /25
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 | 70.1% | #97 of 178 | Official leaderboard |
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| OlympicArena | 17.4% | #20 of 25 | Official leaderboard |
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| A-Bench | 73.3% | #49 of 116 | Official leaderboard | |
| MME | 1619.3 | #7 of 16 | Official leaderboard | |
| MMBench | 77.6% | #72 of 155 | Official leaderboard | |
| CCBench (MMBench Chinese Culture) | 45.9% | #74 of 152 | Official leaderboard | |
| VCR (Visual Caption Restoration) | 22.4% | #22 of 42 | Official leaderboard | |
| MMBench-EN v1.1 | 74% | #95 of 178 | Official leaderboard | |
| MMStar | 51.8% | #97 of 173 | Official leaderboard | |
| CharXiv | 24.9% | #55 of 77 | Official leaderboard | |
| MTVQA-Test | 17.3% | #13 of 18 | Official leaderboard | |
| MMMU | 45.8% | #101 of 136 | Official leaderboard | |
| MMMU-Pro | 19.6% | #53 of 57 | Official leaderboard |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| OpenVLM Leaderboard | 58.8 | #88 of 173 | Official leaderboard |