List your company

STEM Knowledge on GPQA Diamond

90.7Avg@16Gemini-3-Flash
72.577.22581.9586.675Dec 30, 2025Jan 29, 2026Feb 28, 2026Mar 31, 2026Apr 30, 2026May 30, 2026Jun 30, 2026

Evaluation results

MethodLinks
Gemini-3-FlashTier=High2026.0690.7
Seed2.0 Lite2026.0685.1
GPT-5-miniTier=High2026.0682.1
Seed2.0 Mini2026.0679
LongCat-Flash Exp-ChatEvaluation Mode=Chat2025.1275.6
DeepSeek V3.2Evaluation Mode=Chat2025.1275.3
GLM 4.6Evaluation Mode=Chat2025.1274.8
LongCat-Flash ChatEvaluation Mode=Chat2025.1273.2