InternVL3-78B
InternVL3-78B ranks first on 2 of the 38 benchmarks with five or more models scored.
38
Benchmarks with a score
2
Ranked first, out of five or more models
13
In the top three
Shanghai AI Lab Apr 2025 InternVL3-78B
Open weights Flagship
No Epoch Capabilities Index score yet
- HiPhO 37.2% #25 /36
- Video SimpleQA 33.8% #8 /27
- OCR-Reasoning 19.9% #11 /15
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 | 87.9% | #2 of 178 | Official leaderboard | |
| Video SimpleQA | 33.8% | #8 of 27 | Official leaderboard |
Math and science
Coding
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| SArena | 0.85 | #4 of 17 | Official leaderboard |
Agents and tools
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| SnakeBench | 19 | #141 of 188 | Official leaderboard | |
| ScienceBoard | 5.46% | #13 of 15 | Official leaderboard |
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| MMBench | 88.8% | #1 of 155 | Official leaderboard | |
| MMStar | 73.4% | #3 of 173 | Official leaderboard | |
| MM-Vet | 80.7% | #3 of 164 | Official leaderboard | |
| CCBench (MMBench Chinese Culture) | 83.5% | #3 of 152 | Official leaderboard | |
| MMBench-EN v1.1 | 87.5% | #4 of 178 | Official leaderboard | |
| SEED-Bench-2-Plus | 71.7% | #7 of 136 | Official leaderboard | |
| EmbodiedBench EB-Navigation | 53.7% | #1 of 17 | Official leaderboard | |
| A-Bench | 78.9% | #9 of 116 | Official leaderboard | |
| EmbodiedBench EB-Habitat | 55% | #2 of 17 | Official leaderboard | |
| CharXiv (DQ) | 85.1% | #9 of 67 | Official leaderboard | |
| SpaCE-10 | 52.5% | #5 of 36 | Official leaderboard | |
| EmbodiedBench EB-ALFRED | 39% | #3 of 17 | Official leaderboard | |
| EmbodiedBench EB-Manipulation | 26.3% | #3 of 17 | Official leaderboard | |
| MMBench-Video | 1.81 | #5 of 28 | Official leaderboard | |
| CharXiv | 46% | #14 of 77 | Official leaderboard | |
| Ego3D-Bench | 7.40 | #2 of 11 | Official leaderboard | |
| MMMU | 72.2% | #28 of 136 | Official leaderboard | |
| We-Math | 46.1% | #5 of 21 | Official leaderboard | |
| CSVQA | 37.4% | #4 of 12 | Official leaderboard | |
| VisuLogic | 27.7% | #7 of 17 | Official leaderboard | |
| SpatialViz-Bench | 31.7% | #6 of 14 | Official leaderboard | |
| VideoReasonBench | 5.80% | #6 of 14 | Official leaderboard | |
| EMMA | 34.8% | #3 of 7 | Official leaderboard | |
| CrossVid | 25.8% | #6 of 13 | Official leaderboard | |
| MMSI-Bench | 28.5% | #14 of 28 | Official leaderboard | |
| MM-HELIX | 18.6% | #9 of 17 | Official leaderboard | |
| MATH-Vision (MathVision) | 43.1% | #58 of 105 | Official leaderboard | |
| OCR-Reasoning | 19.9% | #11 of 15 | Official leaderboard | |
| MME-Reasoning | 32.1% | #9 of 11 | Official leaderboard | |
| OmniDocBench v1.5 | 80.3 | #11 of 11 | Official leaderboard |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| OpenVLM Leaderboard | 79.1 | #3 of 173 | Official leaderboard |