InternVL2-26B
InternVL2-26B.
12
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Shanghai AI Lab Jul 2024 InternVL2-26B
Open weights Mid-size
No Epoch Capabilities Index score yet
- OCRBench v2 41.8% #38 /65
- A-Bench 74.3% #39 /116
- VCR (Visual Caption Restoration) 38.8% #8 /42
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 | 80.9% | #40 of 178 | Official leaderboard |
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| CCBench (MMBench Chinese Culture) | 73.9% | #21 of 152 | Official leaderboard | |
| MMBench | 83.4% | #27 of 155 | Official leaderboard | |
| VCR (Visual Caption Restoration) | 38.8% | #8 of 42 | Official leaderboard | |
| MMBench-EN v1.1 | 81.5% | #43 of 178 | Official leaderboard | |
| MMStar | 61% | #53 of 173 | Official leaderboard | |
| A-Bench | 74.3% | #39 of 116 | Official leaderboard | |
| CharXiv | 33.4% | #36 of 77 | Official leaderboard | |
| OCRBench v2 | 41.8% | #38 of 65 | Official leaderboard | |
| TOMATO | 23.3% | #17 of 22 | Official leaderboard | |
| Vision Arena | 1,025 | #124 of 136 | Official leaderboard |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| OpenVLM Leaderboard | 66.4 | #51 of 173 | Official leaderboard |