Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Thinking-with-images on HRBench 8K
Loading...
0.935
Accuracy
S1-VL-32B-RL
0.7114
0.76945
0.8275
0.88555
Jun 23, 2026
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
S1-VL-32B-RL
2026.06
0.935
S1-VL-32B-SFT
2026.06
0.851
S1-Omni-Image
2026.06
0.85
Qwen3-VL-235B-A22B-Thinking
2026.06
0.804
Qwen3-VL-32B-Thinking
2026.06
0.77
GPT-5
2026.06
0.7375
Thyme-VL
2026.06
0.72
Feedback
Search any
task
Search any
task