Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
General Knowledge on MMLU-Pro (pass@1)
Loading...
66.46
pass@1
Qwen3-8B
28.5728
38.4089
48.245
58.0811
Jan 8, 2026
pass@1
Updated 4d ago
Evaluation Results
Method
Method
Links
pass@1
Qwen3-8B
Backbone=Qwen3-8B
2026.01
66.46
RelayLLM (Difficulty-Aware)
Student Model Backbone...
2026.01
59.03
RelayLLM (Simple)
Student Model Backbone...
2026.01
58.76
CITER
Student Model Backbone...
2026.01
53.38
GRPO
Student Model Backbone...
2026.01
49.76
Base Model
Student Model Backbone...
2026.01
46.9
RelayLLM (Difficulty-Aware)
Student Model Backbone...
2026.01
35.87
RelayLLM (Simple)
Student Model Backbone...
2026.01
35.61
CITER
Student Model Backbone...
2026.01
33.12
GRPO
Student Model Backbone...
2026.01
32.15
Base Model
Student Model Backbone...
2026.01
30.03
Feedback
Search any
task
Search any
task