InternVL2.5-38B
InternVL2.5-38B places in the top three on 2 benchmarks.
Shanghai AI Lab Released December 5th, 2024 Family InternVL2.5 The lab's model card Compare with others 23
Benchmarks with a score
0
Ranked first, out of five or more models
2
In the top three
Shanghai AI Lab Dec 2024 InternVL2.5-38B
Open weights Mid-size
No Epoch Capabilities Index score yet
- MM-Vet 67.2% #29 /164
- CoreCognition 59.5% #37 /119
- SpaCE-10 45.1% #14 /36
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 | 85.6% | #12 of 178 | Official leaderboard |
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| PHYSICS | 15.3% | #11 of 20 | Official leaderboard | |
| PHYSICS-Verified | 16.4% | #16 of 19 | Official leaderboard |
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| MMBench-EN v1.1 | 85.3% | #16 of 178 | Official leaderboard | |
| All-Angles Bench | 55.6% | #2 of 18 | Official leaderboard | |
| MMStar | 68.5% | #20 of 173 | Official leaderboard | |
| MM-Vet | 67.2% | #29 of 164 | Official leaderboard | |
| CharXiv (DQ) | 79.6% | #14 of 67 | Official leaderboard | |
| CharXiv | 42.4% | #20 of 77 | Official leaderboard | |
| CoreCognition | 59.5% | #37 of 119 | Official leaderboard | |
| EmbodiedBench EB-Habitat | 38.3% | #6 of 17 | Official leaderboard | |
| MMMU | 63.9% | #49 of 136 | Official leaderboard | |
| SpaCE-10 | 45.1% | #14 of 36 | Official leaderboard | |
| MMVU | 50.5% | #12 of 28 | Official leaderboard | |
| OST-Bench | 50.8% | #3 of 6 | Official leaderboard | |
| MMMU-Pro | 46% | #29 of 57 | Official leaderboard | |
| EmbodiedBench EB-Manipulation | 15.8% | #9 of 17 | Official leaderboard | |
| EmoBench-M | 54.4% | #8 of 15 | Official leaderboard | |
| EmbodiedBench EB-Navigation | 30.3% | #10 of 17 | Official leaderboard | |
| EmbodiedBench EB-ALFRED | 23.3% | #11 of 17 | Official leaderboard | |
| MATH-Vision (MathVision) | 31.8% | #72 of 105 | Official leaderboard | |
| VisuLogic | 25.5% | #15 of 17 | Official leaderboard |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| OpenVLM Leaderboard | 73.3 | #18 of 173 | Official leaderboard |