Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
English Knowledge on MMLU-Redux
Loading...
90.15
Accuracy (English Knowledge)
Teacher-30B
19.066
37.5205
55.975
74.4295
Apr 30, 2026
May 9, 2026
May 18, 2026
May 28, 2026
Jun 6, 2026
Jun 15, 2026
Jun 25, 2026
Accuracy (English Knowledge)
Updated 29d ago
Evaluation Results
Method
Method
Links
Accuracy (English Knowledge)
Teacher-30B
Inference Mode=thinking
2026.06
90.15
Teacher-8B
Inference Mode=thinking
2026.06
85.86
OPD-T30B
Inference Mode=thinking
2026.06
84.89
OPD-T8B
Inference Mode=thinking
2026.06
84.83
Qwen3.5-9B
Shots=5
2026.04
83.43
Llama-3.3-70B-Instruct
Shots=5
2026.04
81.73
Qwen3-14B
Shots=5
2026.04
80.47
XekRung-8B
Shots=5
2026.04
78.77
Qwen3-8B
Shots=5
2026.04
77.53
RL
Inference Mode=thinking
2026.06
74.82
Base (SFT ckpt)
Inference Mode=thinking
2026.06
69.75
SecGPT-14B
Shots=5
2026.04
69.5
Llama-Primus-Reasoning-8B
Shots=5
2026.04
21.8
Feedback
Search any
task
Search any
task