InternLM-XComposer2.5-7B
InternLM-XComposer2.5-7B ranks first on MME-RealWorld.
Shanghai AI Lab Released July 3rd, 2024 Family InternLM-XComposer The lab's model card Compare with others 12
Benchmarks with a score
1
Ranked first, out of five or more models
1
In the top three
Shanghai AI Lab Jul 2024 InternLM-XComposer2.5-7B
Open weights Small
No Epoch Capabilities Index score yet
- MM-Vet 49.3% #91 /164
- SEED-Bench-2-Plus 66.5% #43 /136
- VCR (Visual Caption Restoration) 25.1% #18 /42
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 | 78.8% | #58 of 178 | Official leaderboard |
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| OlympicArena | 12.7% | #23 of 25 | Official leaderboard |
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| MME-RealWorld | 50% | #1 of 11 | Official leaderboard | |
| MMBench | 82% | #40 of 155 | Official leaderboard | |
| MMBench-EN v1.1 | 80.1% | #52 of 178 | Official leaderboard | |
| SEED-Bench-2-Plus | 66.5% | #43 of 136 | Official leaderboard | |
| MMStar | 59.9% | #60 of 173 | Official leaderboard | |
| CCBench (MMBench Chinese Culture) | 49.6% | #65 of 152 | Official leaderboard | |
| VCR (Visual Caption Restoration) | 25.1% | #18 of 42 | Official leaderboard | |
| TempCompass | 62.1% | #7 of 13 | Official leaderboard | |
| MM-Vet | 49.3% | #91 of 164 | Official leaderboard |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| OpenVLM Leaderboard | 61.1 | #77 of 173 | Official leaderboard |