PaliGemma-3B-mix-448
PaliGemma-3B-mix-448.
13
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Google DeepMind May 2024 PaliGemma-3B-mix-448
Open weights Small
No Epoch Capabilities Index score yet
- MM-Vet 33.1% #144 /164
- SEED-Bench-2-Plus 49.8% #106 /136
- CoreCognition 50.4% #91 /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 | 62.8% | #136 of 178 | Official leaderboard |
Agents and tools
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| GroundUI | 0% | #11 of 11 | Official leaderboard |
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| MMStar | 48.3% | #110 of 173 | Official leaderboard | |
| MMBench | 71% | #107 of 155 | Official leaderboard | |
| MMBench-EN v1.1 | 68.4% | #130 of 178 | Official leaderboard | |
| CCBench (MMBench Chinese Culture) | 29.6% | #114 of 152 | Official leaderboard | |
| CoreCognition | 50.4% | #91 of 119 | Official leaderboard | |
| SEED-Bench-2-Plus | 49.8% | #106 of 136 | Official leaderboard | |
| VCR (Visual Caption Restoration) | 16.3% | #33 of 42 | Official leaderboard | |
| MM-Vet | 33.1% | #144 of 164 | Official leaderboard | |
| VHELM | 20.6 | #38 of 41 | Official leaderboard | |
| A-Bench | 59.8% | #110 of 116 | Official leaderboard |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| OpenVLM Leaderboard | 46.5 | #141 of 173 | Official leaderboard |