Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
LLM Evaluation on Arena-Hard v2.0
Loading...
65.8
Quality
SEE
45.624
50.862
56.1
61.338
Jun 3, 2026
Quality
Calibration
Updated 1mo ago
Evaluation Results
Method
Method
Links
Quality
Calibration
SEE
Judge=Gemini 3.1 Flash...
2026.06
65.8
61.2
Adapted RLCR
Judge=Gemini 3.1 Flash...
2026.06
63.8
55.6
Qwen 3-4B
Judge=Gemini 3.1 Flash...
2026.06
63.1
52.2
SEE
Judge=Claude Sonnet 4.6
2026.06
48.3
55.1
Adapted RLCR
Judge=Claude Sonnet 4.6
2026.06
47
49.7
Qwen 3-4B
Judge=Claude Sonnet 4.6
2026.06
46.4
44.3
Feedback
Search any
task
Search any
task