List your company

Domain-level accuracy estimation on STEM benchmarks (GSM8K, OlympiadBench, MATH, SciBench, etc.) (held-out)

100External ScorePHI-3.5-MINI
75.0481.528894.48Jan 13, 2026

Evaluation results

MethodLinks
PHI-3.5-MINIParameters=3B2026.01100959594909088908990
MISTRALParameters=7B2026.0196799695926861665568
MIXTRALParameters=8x7B2026.0196899896966647627373
QWEN2Parameters=7B2026.0195949698959596959895
LLAMA-3Parameters=8B2026.01959295955565906510065
GEMMAParameters=2B2026.0194928989878789879887
GEMMAParameters=7B2026.0192859088818493849583
GPT-NEOXParameters=20B2026.0190899498825837507050
QWEN2Parameters=72B2026.0176759379757589759575