InternVL3-9B
InternVL3-9B.
15
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Shanghai AI Lab Apr 2025 InternVL3-9B
Open weights Small
No Epoch Capabilities Index score yet
- HiPhO 15.6% #33 /36
- Video SimpleQA 23.1% #17 /27
- MM-Vet 78.4% #6 /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 | 82.4% | #31 of 178 | Official leaderboard | |
| Video SimpleQA | 23.1% | #17 of 27 | Official leaderboard |
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| HiPhO | 15.6% | #33 of 36 | Official leaderboard |
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| MM-Vet | 78.4% | #6 of 164 | Official leaderboard | |
| CCBench (MMBench Chinese Culture) | 78% | #12 of 152 | Official leaderboard | |
| MMStar | 67.4% | #24 of 173 | Official leaderboard | |
| MMBench | 83.9% | #23 of 155 | Official leaderboard | |
| MMBench-EN v1.1 | 81.9% | #38 of 178 | Official leaderboard | |
| VSI-Bench-Debiased | 41.5% | #1 of 4 | Official leaderboard | |
| CharXiv | 38% | #25 of 77 | Official leaderboard | |
| CharXiv (DQ) | 72.5% | #23 of 67 | Official leaderboard | |
| MMMU | 57.7% | #66 of 136 | Official leaderboard | |
| MMSI-Bench | 26.7% | #20 of 28 | Official leaderboard | |
| MATH-Vision (MathVision) | 27.6% | #77 of 105 | Official leaderboard |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| OpenVLM Leaderboard | 72.6 | #22 of 173 | Official leaderboard |