LLaVA-v1.6-34B
LLaVA-v1.6-34B places in the top three on 2 benchmarks.
16
Benchmarks with a score
0
Ranked first, out of five or more models
2
In the top three
University of Wisconsin-Madison Jan 2024 LLaVA-v1.6-34B
Open weights Mid-size
No Epoch Capabilities Index score yet
- VisualPuzzles 29.8% #22 /29
- OlympicArena 18.2% #18 /25
- OlympiadBench 3.65% #6 /7
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 | 77.1% | #64 of 178 | Official leaderboard |
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| OlympicArena | 18.2% | #18 of 25 | Official leaderboard | |
| OlympiadBench | 3.65% | #6 of 7 | Official leaderboard |
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| BLINK | 45% | #3 of 11 | Official leaderboard | |
| MMBench | 81.1% | #45 of 155 | Official leaderboard | |
| MathVerse | 23.8% | #3 of 9 | Official leaderboard | |
| MMBench-EN v1.1 | 78.5% | #67 of 178 | Official leaderboard | |
| CCBench (MMBench Chinese Culture) | 49.2% | #66 of 152 | Official leaderboard | |
| MMStar | 51.6% | #98 of 173 | Official leaderboard | |
| MMMU | 48.1% | #92 of 136 | Official leaderboard | |
| MathVista | 46.5% | #30 of 43 | Official leaderboard | |
| VisualPuzzles | 29.8% | #22 of 29 | Official leaderboard | |
| CharXiv | 22.5% | #64 of 77 | Official leaderboard | |
| MMMU-Pro | 23.8% | #49 of 57 | Official leaderboard | |
| MTVQA-Test | 11.1% | #16 of 18 | Official leaderboard |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| OpenVLM Leaderboard | 55.1 | #107 of 173 | Official leaderboard |