InternVL2-4B
InternVL2-4B.
16
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Shanghai AI Lab Jul 2024 InternVL2-4B
Open weights Small
No Epoch Capabilities Index score yet
- VLADBench 45% #7 /7
- MM-Vet 50.9% #86 /164
- SEED-Bench-2-Plus 63.7% #62 /136
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 | 71.4% | #94 of 178 | Official leaderboard |
Coding
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| ChartMimic | 36.1 | #6 of 14 | Official leaderboard |
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| CCBench (MMBench Chinese Culture) | 66.3% | #29 of 152 | Official leaderboard | |
| OCRBench | 77.6% | #4 of 11 | Official leaderboard | |
| MMBench | 78.5% | #66 of 155 | Official leaderboard | |
| SEED-Bench-2-Plus | 63.7% | #62 of 136 | Official leaderboard | |
| MMBench-EN v1.1 | 75.8% | #84 of 178 | Official leaderboard | |
| CoreCognition | 55.6% | #62 of 119 | Official leaderboard | |
| MM-Vet | 50.9% | #86 of 164 | Official leaderboard | |
| MMStar | 53.9% | #91 of 173 | Official leaderboard | |
| VCR (Visual Caption Restoration) | 22.1% | #23 of 42 | Official leaderboard | |
| A-Bench | 70.6% | #67 of 116 | Official leaderboard | |
| OVBench | 44.1% | #5 of 7 | Official leaderboard | |
| Vision Arena | 959 | #134 of 136 | Official leaderboard | |
| VLADBench | 45% | #7 of 7 | Official leaderboard |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| OpenVLM Leaderboard | 60.6 | #81 of 173 | Official leaderboard |