InternVL3-38B
InternVL3-38B places in the top three on 4 benchmarks.
29
Benchmarks with a score
0
Ranked first, out of five or more models
4
In the top three
Shanghai AI Lab Apr 2025 InternVL3-38B
Open weights Mid-size
No Epoch Capabilities Index score yet
- HiPhO 25.8% #32 /36
- Video SimpleQA 31.5% #9 /27
- CrossVid 23.5% #10 /13
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 | 86.6% | #6 of 178 | Official leaderboard | |
| Video SimpleQA | 31.5% | #9 of 27 | Official leaderboard |
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| HiPhO | 25.8% | #32 of 36 | Official leaderboard |
Coding
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| SArena | 0.83 | #8 of 17 | Official leaderboard |
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| MM-Vet | 81.1% | #2 of 164 | Official leaderboard | |
| MMStar | 72.6% | #5 of 173 | Official leaderboard | |
| MMBench | 87.7% | #5 of 155 | Official leaderboard | |
| MMBench-EN v1.1 | 87% | #6 of 178 | Official leaderboard | |
| SEED-Bench-2-Plus | 71.8% | #5 of 136 | Official leaderboard | |
| CCBench (MMBench Chinese Culture) | 80.6% | #7 of 152 | Official leaderboard | |
| SpaCE-10 | 53.1% | #3 of 36 | Official leaderboard | |
| EmbodiedBench EB-Navigation | 50.7% | #2 of 17 | Official leaderboard | |
| ERQA | 41.7% | #2 of 17 | Official leaderboard | |
| CharXiv (DQ) | 87.2% | #8 of 67 | Official leaderboard | |
| A-Bench | 77.1% | #15 of 116 | Official leaderboard | |
| CharXiv | 46.4% | #13 of 77 | Official leaderboard | |
| MMBench-Video | 1.80 | #6 of 28 | Official leaderboard | |
| EmbodiedBench EB-ALFRED | 38% | #4 of 17 | Official leaderboard | |
| EmbodiedBench EB-Habitat | 43.3% | #4 of 17 | Official leaderboard | |
| EmbodiedBench EB-Manipulation | 22.6% | #4 of 17 | Official leaderboard | |
| MMMU | 70.1% | #34 of 136 | Official leaderboard | |
| VisuLogic | 27.1% | #9 of 17 | Official leaderboard | |
| SpatialViz-Bench | 31% | #9 of 14 | Official leaderboard | |
| MM-HELIX | 16.7% | #11 of 17 | Official leaderboard | |
| MATH-Vision (MathVision) | 34.5% | #68 of 105 | Official leaderboard | |
| Ego3D-Bench | 8.50 | #8 of 11 | Official leaderboard | |
| CrossVid | 23.5% | #10 of 13 | Official leaderboard | |
| MME-Reasoning | 28.4% | #10 of 11 | Official leaderboard |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| OpenVLM Leaderboard | 77.8 | #5 of 173 | Official leaderboard |