Idefics3-8B-Llama3
Idefics3-8B-Llama3.
16
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Hugging Face Aug 2024 Idefics3-8B-Llama3
Open weights Small
No Epoch Capabilities Index score yet
- MM-Vet 41.7% #115 /164
- SEED-Bench-2-Plus 66.2% #47 /136
- CoreCognition 51.2% #87 /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 | 71.9% | #87 of 178 | Official leaderboard |
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| SEED-Bench-2-Plus | 66.2% | #47 of 136 | Official leaderboard | |
| MMStar | 55% | #82 of 173 | Official leaderboard | |
| MMBench | 77.5% | #74 of 155 | Official leaderboard | |
| MMBench-EN v1.1 | 75% | #90 of 178 | Official leaderboard | |
| CCBench (MMBench Chinese Culture) | 38.8% | #92 of 152 | Official leaderboard | |
| MM-Vet | 41.7% | #115 of 164 | Official leaderboard | |
| MMMU | 46.6% | #98 of 136 | Official leaderboard | |
| CoreCognition | 51.2% | #87 of 119 | Official leaderboard | |
| CSVQA | 10.1% | #9 of 12 | Official leaderboard | |
| MMVU | 35.3% | #25 of 28 | Official leaderboard | |
| MMMU-Pro | 22.9% | #51 of 57 | Official leaderboard | |
| MMBench-Video | 1.00 | #27 of 28 | Official leaderboard | |
| MEGA-Bench | 13.8% | #22 of 22 | Official leaderboard | |
| LEGO-Puzzles | 26.6% | #16 of 16 | Official leaderboard |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| OpenVLM Leaderboard | 56.3 | #103 of 173 | Official leaderboard |