List your company

Mathematical Reasoning on AIME 24 (Acc, Tok, CR)

78.2AccuracyVanilla
21.10435.92750.7565.573Apr 19, 2026

Evaluation results

MethodLinks
VanillaBackbone=Gemini2.5-Flash2026.0478.28,476100
NoThinkBackbone=Gemini2.5-Flash2026.0476.38,21496.9
TRACEBackbone=Gemini2.5-Flash2026.0474.96,89781.4
DynasorBackbone=Gemini2.5-Flash2026.0474.76,97682.3
VanillaBackbone=Qwen3-8B2026.0470.314,477100
TALEBackbone=Gemini2.5-Flash2026.0469.17,36186.8
TRACEBackbone=Qwen3-8B2026.0468.810,53272.8
TALEBackbone=Qwen3-8B2026.0468.110,16670.2
DynasorBackbone=Qwen3-8B2026.0466.712,63887.3
DEERBackbone=Gemini2.5-Flash2026.0466.76,32674.6
DEERBackbone=Qwen3-8B2026.0466.39,64566.6
VanillaBackbone=Qwen3-4B2026.0464.714,318100
DynasorBackbone=Qwen3-4B2026.0462.312,75589.1
TRACEBackbone=Qwen3-4B2026.0461.59,20464.3
TALEBackbone=Qwen3-4B2026.0457.39,37365.5
DEERBackbone=Qwen3-4B2026.0452.78,72060.9
VanillaBackbone=R1-Distilled-Llama-8B2026.0443.312,648100
DynasorBackbone=R1-Distilled-Llama-8B2026.0442.210,91286.3
TRACEBackbone=R1-Distilled-Llama-8B2026.0441.99,85877.9
NoThinkBackbone=R1-Distilled-Llama-8B2026.0441.312,803101
NoThinkBackbone=Qwen3-8B2026.0439.73,81226.3
DEERBackbone=R1-Distilled-Llama-8B2026.0434.59,07071.7
TALEBackbone=R1-Distilled-Llama-8B2026.0432.18,72469
NoThinkBackbone=Qwen3-4B2026.0423.35,45938.1