Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Search on HLE text
Loading...
54.2
Score
Seed2.0 Pro
6.984
19.242
31.5
43.758
Feb 15, 2026
Mar 9, 2026
Apr 1, 2026
Apr 23, 2026
May 16, 2026
Jun 7, 2026
Jun 30, 2026
Score
Updated 23d ago
Evaluation Results
Method
Method
Links
Score
Seed2.0 Pro
2026.06
54.2
Gemini-3-pro High
2026.06
46.9
Gemini-3-Pro
Params=-, Evaluation T...
2026.02
45.8
GPT-5.2 High
2026.06
45.5
Claude-Opus-4.5
2026.06
43.2
GPT-5
Params=-
2026.02
41.7
Seed1.8
Params=-
2026.02
40.9
Claude-Sonnet-4.5
2026.06
32
REDSearcher-MM-RL
Params=30B
2026.02
25.3
REDSearcher-MM-SFT
Params=30B
2026.02
24.4
Qwen3-VL Thinking
Params=235B
2026.02
14.5
Qwen3-VL Thinking
Params=30B
2026.02
8.8
Feedback
Search any
task
Search any
task