Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Open-ended instruction following on WildBench v2
Loading...
58.1
Win Rate
SEE
49.676
51.863
54.05
56.237
Jun 3, 2026
Win Rate
Quality
Calibration
Updated 1mo ago
Evaluation Results
Method
Method
Links
Win Rate
Quality
Calibration
SEE
2026.06
58.1
56.7
60.9
Adapted RLCR
2026.06
53.7
56.1
54.1
Qwen3-4B
2026.06
50
56
50.4
Feedback
Search any
task
Search any
task