List your company

Single-turn Reasoning on AIME24, AIME25, and GPQA

92.2AIME 2024 AccuracySKillOS
72.54477.64782.7587.853May 7, 2026

Evaluation results

MethodLinks
SKillOSExecutor=Gemini-2.5-pro, Curator=Qwen3-8B2026.0592.286.786.888.6
SKillOS-geminiExecutor=Gemini-2.5-pro, Curator=Gemini-2.5-pro2026.059085.680.785.4
SKillOS-baseExecutor=Gemini-2.5-pro, Curator=Qwen3-8B2026.0587.883.382.884.6
SKillOSExecutor=Qwen3-32B, Curator=Qwen3-8B2026.0585.681.172.479.7
No MemoryExecutor=Gemini-2.5-pro, Curator=None2026.0585.68079.981.8
ReasoningBankExecutor=Gemini-2.5-pro, Curator=Gemini-2.5-pro2026.0585.684.480.483.5
MemPExecutor=Gemini-2.5-pro, Curator=Gemini-2.5-pro2026.0583.376.781.880.6
MemPExecutor=Qwen3-32B, Curator=Qwen3-32B2026.0582.276.766.575.1
No MemoryExecutor=Qwen3-32B, Curator=None2026.0581.472.268.474
ReasoningBankExecutor=Qwen3-32B, Curator=Qwen3-32B2026.0581.175.666.974.9
SKillOSExecutor=Qwen3-8B, Curator=Qwen3-8B2026.058076.764.673.8
SKillOS-baseExecutor=Qwen3-32B, Curator=Qwen3-8B2026.058075.667.774.7
SKillOS-geminiExecutor=Qwen3-32B, Curator=Gemini-2.5-pro2026.0577.874.466.273.2
No MemoryExecutor=Qwen3-8B, Curator=None2026.057671.161.869.6
MemPExecutor=Qwen3-8B, Curator=Qwen3-8B2026.0575.671.160.669.1
SKillOS-baseExecutor=Qwen3-8B, Curator=Qwen3-8B2026.0575.671.959.368.9
ReasoningBankExecutor=Qwen3-8B, Curator=Qwen3-8B2026.0575.473.260.369.6
SKillOS-geminiExecutor=Qwen3-8B, Curator=Gemini-2.5-pro2026.0573.371.357.667.4