LLaVA-v1.6-34B
LLaVA-v1.6-34B places in the top three on 4 benchmarks.
University of Wisconsin-Madison Released January 31st, 2024 Family LLaVA-NeXT The lab's model card Compare with others 27
Benchmarks with a score
0
Ranked first, out of five or more models
4
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
- MM-Vet 50.7% #88 /164
- SEED-Bench-2-Plus 65.9% #50 /136
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% | #5 of 6 | Official leaderboard |
Coding
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| ChartMimic | 20.1 | #12 of 14 | Official leaderboard |
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| WildVision Arena | 1,059 | #2 of 10 | Official leaderboard | |
| MuirBench | 33.3% | #2 of 8 | Official leaderboard | |
| MMT-Bench | 60.8% | #4 of 15 | Official leaderboard | |
| BLINK | 45% | #3 of 11 | Official leaderboard | |
| WildVision | 51.9 | #4 of 14 | Official leaderboard | |
| MMBench | 81.1% | #45 of 155 | Official leaderboard | |
| MathVerse | 23.8% | #3 of 9 | Official leaderboard | |
| SEED-Bench-2-Plus | 65.9% | #50 of 136 | Official leaderboard | |
| MMBench-EN v1.1 | 78.5% | #67 of 178 | Official leaderboard | |
| MME | 1631.5 | #7 of 17 | Official leaderboard | |
| CCBench (MMBench Chinese Culture) | 49.2% | #66 of 152 | Official leaderboard | |
| TemporalBench | 19% | #5 of 10 | Official leaderboard | |
| MM-Vet | 50.7% | #88 of 164 | 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 | |
| CharXiv (DQ) | 51% | #48 of 67 | Official leaderboard | |
| DynaMath | 27.1% | #8 of 11 | 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 |