InternVL3.5-8B
InternVL3.5-8B.
Shanghai AI Lab Released August 25th, 2025 Family InternVL3.5 The lab's model card Compare with others 19
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Shanghai AI Lab Aug 2025 InternVL3.5-8B
Open weights Small
No Epoch Capabilities Index score yet
- MathCanvas-Bench 16.7% #10 /16
- CC-OCR-Bench-V2 48.3% #14 /15
- VideoEval-Pro 24.4% #7 /10
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.
Agents and tools
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| GameHorizon | 55.8 | #35 of 37 | Official leaderboard |
Professional work
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| MMEnterprise-Bench | 36.6% | #8 of 9 | Official leaderboard | |
| RadLE 2.0 | 241.0 | #11 of 12 | Official leaderboard | |
| LMBuild | 22.7% | #17 of 18 | Official leaderboard |
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Math-VR | 40.8% | #12 of 26 | Official leaderboard | |
| MATH-Vision (MathVision) | 52% | #50 of 105 | Official leaderboard | |
| Video-Oasis | 33.6% | #2 of 4 | Official leaderboard | |
| ERQA | 36.3% | #9 of 17 | Official leaderboard | |
| MathCanvas-Bench | 16.7% | #10 of 16 | Official leaderboard | |
| SpaCE-10 | 39.5% | #24 of 36 | Official leaderboard | |
| VideoEval-Pro | 24.4% | #7 of 10 | Official leaderboard | |
| OVO-S-Bench | 44.6% | #11 of 15 | Official leaderboard | |
| VideoMME v2 (with subtitles) | 16.4% | #23 of 31 | Official leaderboard | |
| ExtractBench | 64.6% | #21 of 27 | Official leaderboard | |
| MeasureBench Real-world | 9.70% | #17 of 19 | Official leaderboard | |
| MeasureBench Synthetic | 7.70% | #17 of 19 | Official leaderboard | |
| CC-OCR-Bench-V2 | 48.3% | #14 of 15 | Official leaderboard | |
| GSM8K-V | 10.8% | #24 of 24 | Official leaderboard | |
| MDPBench | 42.7 | #12 of 12 | Official leaderboard |