List your company

Mathematical Reasoning on MATH (Accuracy (mv %), Mean Questions, Mean Tokens)

97.3Accuracy (mv %)Qwen3-14B
75.04480.82286.692.378May 29, 2026

Evaluation results

MethodLinks
Qwen3-14BSetting=Adaptive, Mode=(t)2026.0597.30914
Olmo-3-7B-ThinkSetting=Fixed, Mode=(t)2026.0597.3131,212
Qwen3-14BSetting=Baseline, Mode=(t)2026.0597.1—4,611
Olmo-3-7B-ThinkSetting=Adaptive, Mode=(t)2026.05970.37,668
Qwen3-4BSetting=Baseline, Mode=(t)2026.0596.7—6,897
Qwen3-4BSetting=Adaptive, Mode=(t)2026.0596.70942
Qwen3-1.7BSetting=Baseline, Mode=(t)2026.0592.8—5,074
Qwen3-1.7BSetting=Adaptive, Mode=(t)2026.0592.80.32,939
Olmo-3-7B-ThinkSetting=Baseline, Mode=(t)2026.0591.2—5,026
Qwen3-14BSetting=Adaptive, Mode=(nt)2026.0589.10.2979
Qwen3-14BSetting=Baseline, Mode=(nt)2026.0588.5—840
Qwen3-14BSetting=Fixed, Mode=(nt)2026.0587.83.94,058
Qwen3-4BSetting=Baseline, Mode=(nt)2026.0586.6—698
Qwen3-4BSetting=Fixed, Mode=(nt)2026.058614,885
Qwen3-4BSetting=Adaptive, Mode=(nt)2026.0585.60.21,104
Qwen3-1.7BSetting=Adaptive, Mode=(nt)2026.0576.90.51,260
Qwen3-1.7BSetting=Baseline, Mode=(nt)2026.0576.5—871
Qwen3-1.7BSetting=Fixed, Mode=(nt)2026.0575.92.15,391