InternVL2_5-78B
InternVL2_5-78B ranks first on MTVQA-Test.
Shanghai AI Lab Released 6 Dec 2024 15
Benchmarks with a score
1
Ranked first, out of five or more models
3
In the top three
Shanghai AI Lab Dec 2024 InternVL2_5-78B
Open weights
No Epoch Capabilities Index score yet
- HumanEval-V 13.4% #10 /24
- MMMU 70.1% #33 /136
- MMBench-EN v1.1 87.3% #5 /178
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 | 87.8% | #3 of 178 | Official leaderboard | |
| Creation-MMBench | -16.43 | #10 of 19 | Official leaderboard |
Coding
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| HumanEval-V | 13.4% | #10 of 24 | Official leaderboard |
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| MMBench | 88.2% | #4 of 155 | Official leaderboard | |
| MMBench-EN v1.1 | 87.3% | #5 of 178 | Official leaderboard | |
| MTVQA-Test | 31.9% | #1 of 18 | Official leaderboard | |
| MMStar | 69.5% | #12 of 173 | Official leaderboard | |
| MMMU | 70.1% | #33 of 136 | Official leaderboard | |
| Video-MME | 74% | #7 of 26 | Official leaderboard | |
| CharXiv | 42.4% | #21 of 77 | Official leaderboard | |
| LVBench | 43.6% | #3 of 9 | Official leaderboard | |
| MMMU-Pro | 48.6% | #26 of 57 | Official leaderboard | |
| VisuLogic | 27.3% | #8 of 17 | Official leaderboard | |
| MATH-Vision (MathVision) | 32.2% | #70 of 105 | Official leaderboard |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| OpenVLM Leaderboard | 68.3 | #42 of 173 | Official leaderboard |