List your company

Reasoning on MMLU-ProX Lite

83Target AccuracyGEMINI-3-FLASH
11.44830.02448.667.176Jun 20, 2026

Evaluation results

MethodLinks
GEMINI-3-FLASHConfiguration=LOW2026.0683-0.898.3
GEMINI-3-FLASHConfiguration=Default2026.0682.1-1.498.8
GEMINI-3-FLASHConfiguration=MINIMAL2026.0677.23.293.5
CLAUDEModel Identity=OPUS-4.72026.0676.75.889.3
GEMINI-2.5-FLASHConfiguration=Default2026.0673.4-1.997.5
GPT-OSSParameters=120B2026.0672.36.690.6
GPT-OSSParameters=20B2026.0666.37.788.9
GEMINI-2.5-FLASHThinking Mode=OFF2026.0661.65.988.9
CLAUDEModel Identity=SONNET-4.62026.0659.57.485.4
GEMMA-4Configuration=31B-IT2026.0659.44.884.7
GEMMA-4Configuration=26B-A4B-IT2026.0648.74.878.7
CLAUDEModel Identity=HAIKU-4.52026.0644.60.676.5
QWEN-3Parameters=30B-A3B2026.0643.410.574.8
GEMMA-3Parameters=27B2026.0639.46.477.2
GEMMA-4Configuration=E4B-IT2026.0635.87.174.8
GEMMA-3Parameters=12B2026.0634.9771.6
QWEN-3Parameters=4B2026.0632.78.169.3
GEMMA-4Configuration=E2B-IT2026.0626.15.759.3
GEMMA-3Parameters=4B2026.0624.63.667.5
GEMMA-3Parameters=1B2026.0614.22.758.4