Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Document and chart understanding on CharXiv DQ
Loading...
98.4
Pass@1
Kimi K2.5 + ETCHR
59.712
69.756
79.8
89.844
May 11, 2025
Jul 12, 2025
Sep 13, 2025
Nov 15, 2025
Jan 16, 2026
Mar 20, 2026
May 22, 2026
Pass@1
Updated 9d ago
Evaluation Results
Method
Method
Links
Pass@1
Kimi K2.5 + ETCHR
Temperature=0
2026.05
98.4
Kimi K2.5
Temperature=0
2026.05
98.3
Gemini-3.1-Flash-Lite + ETCHR
Temperature=0
2026.05
94.6
Gemini 1.5 Pro
thinking=true, decodin...
2025.05
94.4
Gemini-3.1-Flash-Lite
Temperature=0
2026.05
93.8
Seed 1.5-VL
thinking=true, decodin...
2025.05
92.6
Seed 1.5-VL
thinking=false, decodi...
2025.05
92.6
Claude 3.7 Sonnet
thinking=true, decodin...
2025.05
92
OpenAI o1
thinking=true, decodin...
2025.05
88.9
Qwen 2.5-VL 72B
thinking=false, decodi...
2025.05
87.4
Qwen3-VL-8B + ETCHR
Temperature=0
2026.05
86.8
GPT-4o
thinking=false, decodi...
2025.05
86.5
Qwen3-VL-8B
Temperature=0
2026.05
85
DeepEyesV2
Temperature=0, Max too...
2026.05
78.6
Thyme
Temperature=0, Max too...
2026.05
66.1
Bagel-Zebra-CoT
Temperature=0, Max ima...
2026.05
62.8
ThinkMorph-7B
Temperature=0, Max ima...
2026.05
61.2
Feedback
Search any
task
Search any
task