InternVL3-2B
InternVL3-2B.
18
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Shanghai AI Lab Apr 2025 InternVL3-2B
Open weights Small
No Epoch Capabilities Index score yet
- Video SimpleQA 15.8% #23 /27
- OCR-Reasoning 10.8% #15 /15
- MM-Vet 67% #31 /164
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 | 77% | #65 of 178 | Official leaderboard | |
| Video SimpleQA | 15.8% | #23 of 27 | Official leaderboard |
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| CCBench (MMBench Chinese Culture) | 75.3% | #18 of 152 | Official leaderboard | |
| MM-Vet | 67% | #31 of 164 | Official leaderboard | |
| MMStar | 61.1% | #52 of 173 | Official leaderboard | |
| MMBench | 80.8% | #49 of 155 | Official leaderboard | |
| A-Bench | 74.2% | #40 of 116 | Official leaderboard | |
| MMBench-EN v1.1 | 79% | #63 of 178 | Official leaderboard | |
| SpaCE-10 | 44.2% | #15 of 36 | Official leaderboard | |
| SEED-Bench-2-Plus | 64.8% | #59 of 136 | Official leaderboard | |
| CharXiv | 28.3% | #49 of 77 | Official leaderboard | |
| CharXiv (DQ) | 54.7% | #44 of 67 | Official leaderboard | |
| MMMU | 48.6% | #91 of 136 | Official leaderboard | |
| MATH-Vision (MathVision) | 21.7% | #86 of 105 | Official leaderboard | |
| MMSI-Bench | 25.3% | #26 of 28 | Official leaderboard | |
| OCR-Reasoning | 10.8% | #15 of 15 | Official leaderboard | |
| SpatialViz-Bench | 26.2% | #14 of 14 | Official leaderboard |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| OpenVLM Leaderboard | 64.5 | #62 of 173 | Official leaderboard |