List your company

Reasoning on BBEH mini

14.8Pass@1SUPERNOVA
2.9446.0229.112.178Apr 9, 2026

Evaluation results

MethodLinks
SUPERNOVAModel Size=4B2026.0414.831.7
SUPERNOVAModel Size=1.7B2026.0412.425.7
Qwen3Model Size=4B2026.041223.7
Qwen3Model Size=8B2026.0411.921.7
General-ReasonerModel Size=4B2026.0411.530
SUPERNOVAModel Size=0.6B2026.049.824.6
Qwen3Model Size=1.7B2026.047.618
Qwen3.5Model Size=2B2026.047.522.4
Qwen3Model Size=0.8B2026.046.622.2
Olmo-3-ThinkModel Size=7B2026.046.413
Qwen3Model Size=0.6B2026.045.715.4
OpenReasoning-NemotronModel Size=7B2026.043.58.5
Openthinker3Model Size=7B2026.043.47.6