InternVL2.5-2B
InternVL2.5-2B.
Shanghai AI Lab Released December 5th, 2024 Family InternVL2.5 The lab's model card Compare with others 16
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Shanghai AI Lab Dec 2024 InternVL2.5-2B
Open weights Small
No Epoch Capabilities Index score yet
- ViewSpatial-Bench 35% #5 /7
- MM-Vet 62.6% #46 /164
- CoreCognition 50.6% #89 /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 | 69.4% | #103 of 178 | Official leaderboard |
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| MM-Vet | 62.6% | #46 of 164 | Official leaderboard | |
| MMSI-Bench | 29% | #10 of 28 | Official leaderboard | |
| MMStar | 54.3% | #89 of 173 | Official leaderboard | |
| ChartQA Pro | 17.8% | #4 of 7 | Official leaderboard | |
| MMBench-EN v1.1 | 72.4% | #102 of 178 | Official leaderboard | |
| ViewSpatial-Bench | 35% | #5 of 7 | Official leaderboard | |
| CharXiv (DQ) | 49.7% | #49 of 67 | Official leaderboard | |
| CoreCognition | 50.6% | #89 of 119 | Official leaderboard | |
| MMMU | 43.6% | #105 of 136 | Official leaderboard | |
| CharXiv | 21.3% | #65 of 77 | Official leaderboard | |
| MMMU-Pro | 23.7% | #50 of 57 | Official leaderboard | |
| SpaCE-10 | 31.4% | #32 of 36 | Official leaderboard | |
| All-Angles Bench | 41% | #16 of 18 | Official leaderboard | |
| MATH-Vision (MathVision) | 14.7% | #97 of 105 | Official leaderboard |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| OpenVLM Leaderboard | 59.9 | #83 of 173 | Official leaderboard |