InternVL2-8B
InternVL2-8B places in the top three on 2 benchmarks.
35
Benchmarks with a score
0
Ranked first, out of five or more models
2
In the top three
Shanghai AI Lab Jul 2024 InternVL2-8B
Open weights Small
No Epoch Capabilities Index score yet
- MM-IFEval 41.9% #7 /9
- VLADBench 48.6% #6 /7
- MM-Vet 54.3% #73 /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 | 79.3% | #54 of 178 | Official leaderboard | |
| MM-IFEval | 41.9% | #7 of 9 | Official leaderboard |
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| OlympicArena | 18.5% | #17 of 25 | Official leaderboard |
Coding
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| ChartMimic | 36.6 | #5 of 14 | Official leaderboard |
Agents and tools
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| UI-Vision Element Grounding | 0.09% | #5 of 5 | Official leaderboard |
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| CCBench (MMBench Chinese Culture) | 77.1% | #14 of 152 | Official leaderboard | |
| VSI-Bench | 37.5% | #2 of 9 | Official leaderboard | |
| VL-RewardBench | 45.2% | #2 of 8 | Official leaderboard | |
| MMBench | 82% | #41 of 155 | Official leaderboard | |
| SEED-Bench-2-Plus | 67.3% | #38 of 136 | Official leaderboard | |
| MMStar | 61.5% | #51 of 173 | Official leaderboard | |
| OmniBench | 50.8% | #5 of 16 | Official leaderboard | |
| MMBench-EN v1.1 | 79.5% | #57 of 178 | Official leaderboard | |
| DriveBench Behavior | 54.6 | #1 of 3 | Official leaderboard | |
| DriveBench Prediction | 48.9 | #1 of 3 | Official leaderboard | |
| VCR (Visual Caption Restoration) | 28.6% | #15 of 42 | Official leaderboard | |
| TempCompass | 66% | #5 of 13 | Official leaderboard | |
| A-Bench | 72.9% | #51 of 116 | Official leaderboard | |
| MM-Vet | 54.3% | #73 of 164 | Official leaderboard | |
| CoreCognition | 56.2% | #54 of 119 | Official leaderboard | |
| We-Math | 26.6% | #11 of 21 | Official leaderboard | |
| OVBench | 48.7% | #4 of 7 | Official leaderboard | |
| MMMU | 51.2% | #80 of 136 | Official leaderboard | |
| MEGA-Bench | 27.7% | #13 of 22 | Official leaderboard | |
| DynaMath | 39.7% | #7 of 11 | Official leaderboard | |
| DriveBench Perception | 33.6 | #2 of 3 | Official leaderboard | |
| DriveBench Planning | 55.3 | #2 of 3 | Official leaderboard | |
| Video-MMMU | 37.4% | #18 of 24 | Official leaderboard | |
| MMMU-Pro | 29% | #43 of 57 | Official leaderboard | |
| MMBench-Video | 1.26 | #22 of 28 | Official leaderboard | |
| TOMATO | 21.7% | #18 of 22 | Official leaderboard | |
| MMVU | 36.3% | #24 of 28 | Official leaderboard | |
| VLADBench | 48.6% | #6 of 7 | Official leaderboard |
Safety and security
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Video-SafetyBench | 2.10 | #8 of 15 | Official leaderboard |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| OpenVLM Leaderboard | 64.1 | #63 of 173 | Official leaderboard |