Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Document and chart understanding on CharXiv RQ
Loading...
82.1
Pass@1
GPT-5.2 High
48.404
57.152
65.9
74.648
May 11, 2025
Jul 19, 2025
Sep 26, 2025
Dec 4, 2025
Feb 11, 2026
Apr 21, 2026
Jun 30, 2026
Pass@1
Updated 23d ago
Evaluation Results
Method
Method
Links
Pass@1
GPT-5.2 High
2026.06
82.1
Gemini-3-Pro High
2026.06
81.4
Seed2.0 Pro
2026.06
80.5
Seed2.0 Lite
2026.06
79.9
Seed1.8
2026.06
71.4
Seed2.0 Mini
2026.06
70.8
Gemini 1.5 Pro
thinking=true, decodin...
2025.05
69.9
Claude 3.7 Sonnet
thinking=true, decodin...
2025.05
68.9
Claude-Opus-4.5
2026.06
65.5
Seed 1.5-VL
thinking=true, decodin...
2025.05
60.2
Seed 1.5-VL
thinking=false, decodi...
2025.05
59.8
OpenAI o1
thinking=true, decodin...
2025.05
55.1
GPT-4o
thinking=false, decodi...
2025.05
52
Qwen 2.5-VL 72B
thinking=false, decodi...
2025.05
49.7
Feedback
Search any
task
Search any
task