MiniCPM-Llama3-V 2.5
MiniCPM-Llama3-V 2.5.
OpenBMB (ModelBest) Released May 19th, 2024 Family MiniCPM-V The lab's model card Compare with others 23
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
- MM-Vet 52.8% #76 /164
- SEED-Bench-2-Plus 61.4% #71 /136
- CoreCognition 55.8% #61 /119
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 |
Coding
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| ChartMimic | 39.4 | #4 of 14 | Official leaderboard |
Agents and tools
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| GroundUI | 0.90% | #9 of 11 | Official leaderboard |
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| MME-RealWorld | 45.6% | #4 of 11 | Official leaderboard | |
| A-Bench | 73.3% | #49 of 116 | Official leaderboard | |
| MM-Vet | 52.8% | #76 of 164 | Official leaderboard | |
| MMBench | 77.6% | #72 of 155 | Official leaderboard | |
| MME | 1619.3 | #8 of 17 | Official leaderboard | |
| CCBench (MMBench Chinese Culture) | 45.9% | #74 of 152 | Official leaderboard | |
| CoreCognition | 55.8% | #61 of 119 | Official leaderboard | |
| SEED-Bench-2-Plus | 61.4% | #71 of 136 | Official leaderboard | |
| VCR (Visual Caption Restoration) | 22.4% | #22 of 42 | Official leaderboard | |
| MMBench-EN v1.1 | 74% | #95 of 178 | Official leaderboard | |
| CharXiv (DQ) | 59.3% | #36 of 67 | Official leaderboard | |
| MMStar | 51.8% | #97 of 173 | Official leaderboard | |
| MMIU | 21.6% | #6 of 10 | 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 | |
| We-Math | 9.52% | #20 of 21 | Official leaderboard |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| OpenVLM Leaderboard | 58.8 | #88 of 173 | Official leaderboard |