instructblip-vicuna-7b
instructblip-vicuna-7b.
Released May 22nd, 2023 Compare with others
15
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Unknown lab May 2023
instructblip-vicuna-7b
No Epoch Capabilities Index score yet
- MM-Vet 33.1% #143 /164
- SEED-Bench-2-Plus 29.5% #133 /136
- CoreCognition 32.7% #118 /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 | 18.4% | #175 of 178 | Official leaderboard |
Professional work
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| GMAI-MMBench | 30.9% | #13 of 13 | Official leaderboard |
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| MM-Vet | 33.1% | #143 of 164 | Official leaderboard | |
| BLINK | 38.6% | #10 of 11 | Official leaderboard | |
| CCBench (MMBench Chinese Culture) | 12.7% | #144 of 152 | Official leaderboard | |
| MMStar | 32.7% | #167 of 173 | Official leaderboard | |
| MMBench-EN v1.1 | 38.4% | #172 of 178 | Official leaderboard | |
| MMBench | 33.9% | #151 of 155 | Official leaderboard | |
| MathVista | 25.3% | #42 of 43 | Official leaderboard | |
| SEED-Bench-2-Plus | 29.5% | #133 of 136 | Official leaderboard | |
| CoreCognition | 32.7% | #118 of 119 | Official leaderboard | |
| ScienceQA | 60.5% | #17 of 17 | Claim in VisionLLM v2: An End-to-End Generalist Multimodal Large L…, via Epoch AI | |
| WildVision Arena | 862 | #10 of 10 | Official leaderboard | |
| NaturalBench | 4.00% | #6 of 6 | Official leaderboard |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| OpenVLM Leaderboard | 31.1 | #168 of 173 | Official leaderboard |