List your company

Language Understanding on MMLU SAGE-generated (test)

94.12Overall Accuracy (OA)GPT-4o
44.30457.23770.1783.103May 12, 2026

Evaluation results

MethodLinks
GPT-4oFamily=GPT2026.0594.1267.3328.4664.76
Gemma-3-27BFamily=Gemma-3, Parameters=27B2026.0575.2149.2225.9939.92
Gemma-3-12BFamily=Gemma-3, Parameters=12B2026.0574.7949.5825.2140.16
Llama-3.1-70BFamily=Llama, Parameters=70B2026.0570.1748.821.3737.21
Llama-3.1-8BFamily=Llama, Parameters=8B2026.0566.8147.7219.0934.93
Gemma-3-4BFamily=Gemma-3, Parameters=4B2026.0565.5547.7817.7734.57
Llama-3.2-3BFamily=Llama, Parameters=3B2026.0562.1847.1215.0732.53
Qwen3.5-35B-A3BFamily=Qwen3.5, Parameters=35B-A3B2026.0558.447.1211.2830.49
Qwen3.5-9BFamily=Qwen3.5, Parameters=9B2026.0556.7246.889.8429.95
Qwen3.5-4BFamily=Qwen3.5, Parameters=4B2026.0553.3646.526.8427.79
Llama-3.2-1BFamily=Llama, Parameters=1B2026.0552.145.56.627.91
Qwen3.5-2BFamily=Qwen3.5, Parameters=2B2026.0546.2245.860.3624.37