Complex Reasoning on LLaVA Bench (val)
2.1875Perplexity
MARS
Updated 1mo ago
Evaluation Results
| Method | Links | |
|---|---|---|
2026.02 | 2.1875 | |
2026.02 | 2.1875 | |
2026.02 | 2.2317 | |
2026.02 | 2.2317 | |
2026.02 | 2.2693 | |
2026.02 | 2.295 | |
2026.02 | 2.3181 | |
2026.02 | 2.4346 | |
2026.02 | 2.442 | |
2026.02 | 2.4888 | |
2026.02 | 2.5189 | |
2026.02 | 2.7188 | |
2026.02 | 2.7188 | |
2026.02 | 2.7209 | |
2026.02 | 2.7331 | |
2026.02 | 2.7336 | |
2026.02 | 2.7336 | |
2026.02 | 2.7582 | |
2026.02 | 2.771 | |
2026.02 | 2.8472 | |
2026.02 | 2.8801 | |
2026.02 | 2.8973 | |
2026.02 | 3.3616 | |
2026.02 | 3.3879 | |
2026.02 | 3.5011 | |
2026.02 | 3.5032 | |
2026.02 | 3.5032 | |
2026.02 | 3.5825 | |
2026.02 | 3.5908 | |
2026.02 | 3.5912 | |
2026.02 | 3.5917 | |
2026.02 | 3.5925 | |
2026.02 | 3.6098 | |
2026.02 | 3.6156 | |
2026.02 | 3.6156 | |
2026.02 | 3.6378 | |
2026.02 | 3.6394 | |
2026.02 | 3.6528 | |
2026.02 | 3.6676 | |
2026.02 | 3.6679 | |
2026.02 | 3.7415 | |
2026.02 | 3.7811 | |
2026.02 | 3.8716 | |
2026.02 | 4.1557 |