Codesota · Models · MiniCPM-Llama3-V 2.55 results · 5 benchmarks
Model card
MiniCPM-Llama3-V 2.5.
unknown
§ 02 · Benchmarks
Every benchmark MiniCPM-Llama3-V 2.5 has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | MMBench | Multimodal · Visual Question Answering | accuracy | 77.2% | #16 | — | source ↗ |
| 02 | TextVQA | Multimodal · Visual Question Answering | accuracy | 76.6% | #18 | — | source ↗ |
| 03 | DocVQA | Computer Vision · Document Understanding | anls | 84.8% | #20 | — | source ↗ |
| 04 | RealWorldQA | Multimodal · Visual Question Answering | accuracy | 63.5% | #22 | — | source ↗ |
| 05 | MMMU | Multimodal · Image-Text-to-Text | accuracy | 45.8% | #34 | — | source ↗ |
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 03 · Strengths by area
Where MiniCPM-Llama3-V 2.5 actually performs.
§ 04 · Papers
1 paper with results for MiniCPM-Llama3-V 2.5.
- 2024-08-03· 5 results
MiniCPM-V: A GPT-4V Level MLLM on Your Phone
§ 06 · Sources & freshness
Where these numbers come from.
pwc-dump
5
results
0 of 5 rows marked verified.