InternVL2-1B
InternVL2-1B places in the top three on OCRBench.
12
Benchmarks with a score
0
Ranked first, out of five or more models
1
In the top three
Shanghai AI Lab Jul 2024 InternVL2-1B
Open weights Small
No Epoch Capabilities Index score yet
- MM-Vet 31.5% #149 /164
- SEED-Bench-2-Plus 54.5% #96 /136
- CoreCognition 46% #106 /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 | 57.7% | #151 of 178 | Official leaderboard |
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| CCBench (MMBench Chinese Culture) | 76.3% | #16 of 152 | Official leaderboard | |
| OCRBench | 77.9% | #3 of 11 | Official leaderboard | |
| VCR (Visual Caption Restoration) | 26.1% | #16 of 42 | Official leaderboard | |
| SEED-Bench-2-Plus | 54.5% | #96 of 136 | Official leaderboard | |
| MMStar | 45.6% | #124 of 173 | Official leaderboard | |
| MMBench | 65.2% | #131 of 155 | Official leaderboard | |
| A-Bench | 64% | #100 of 116 | Official leaderboard | |
| MMBench-EN v1.1 | 61.6% | #155 of 178 | Official leaderboard | |
| CoreCognition | 46% | #106 of 119 | Official leaderboard | |
| MM-Vet | 31.5% | #149 of 164 | Official leaderboard |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| OpenVLM Leaderboard | 48.4 | #132 of 173 | Official leaderboard |