List your company

Instruction Induction on BBH Induct

91.3AccuracySTRATEGY-INDUCT
50.729661.262371.79582.3277May 20, 2026

Evaluation results

MethodLinks
STRATEGY-INDUCTBackbone=GPT o3 mini (high), Setting=Zero-shot2026.0591.3
SCoTBackbone=GPT o3 mini (high), Setting=Zero-shot2026.0589.91
STRATEGY-INDUCTBackbone=GPT o3 mini (medium), Setting=Zero-shot2026.0589.74
INDUCTBackbone=GPT o3 mini (high), Setting=Zero-shot2026.0589.74
SCoTBackbone=GPT o3 mini (medium), Setting=Zero-shot2026.0589.68
INDUCTBackbone=GPT o3 mini (medium), Setting=Zero-shot2026.0589.39
INDUCTBackbone=Llama 3.1 405B, Setting=Zero-shot2026.0589.28
STRATEGY-INDUCTBackbone=Llama 3.1 70B, Setting=Zero-shot2026.0588.99
STRATEGY-INDUCTBackbone=Gemini 2.0 Flash Thinking, Setting=Zero-shot2026.0588.99
ZCoTBackbone=GPT o3 mini (high), Setting=Zero-shot2026.0588.87
STRATEGY-INDUCTBackbone=GPT o3 mini (low), Setting=Zero-shot2026.0588.81
ZCoTBackbone=GPT o3 mini (medium), Setting=Zero-shot2026.0588.7
STRATEGY-INDUCTBackbone=Llama 3.1 405B, Setting=Zero-shot2026.0588.52
INDUCTBackbone=Llama 3.3 70B, Setting=Zero-shot2026.0588.52
INDUCTBackbone=GPT o3 mini (low), Setting=Zero-shot2026.0588.46
INDUCTBackbone=GPT-4o, Setting=Zero-shot2026.0587.94
SCoTBackbone=GPT-4o, Setting=Zero-shot2026.0587.83
STRATEGY-INDUCTBackbone=GPT-4o, Setting=Zero-shot2026.0587.65
STRATEGY-INDUCTBackbone=Llama 3.3 70B, Setting=Zero-shot2026.0587.3
ZCoTBackbone=Gemini 2.0 Flash Thinking, Setting=Zero-shot2026.0587.25
INDUCTBackbone=Gemini 2.0 Flash Thinking, Setting=Zero-shot2026.0586.9
STRATEGY-INDUCTBackbone=Gemini 2.0 Pro Exp, Setting=Zero-shot2026.0586.72
SCoTBackbone=Gemini 2.0 Flash Thinking, Setting=Zero-shot2026.0586.52
INDUCTBackbone=Llama 3.1 70B, Setting=Zero-shot2026.0586.03
STRATEGY-INDUCTBackbone=Mistral Large 2, Setting=Zero-shot2026.0585.97
ZCoTBackbone=GPT o3 mini (low), Setting=Zero-shot2026.0585.91
INDUCTBackbone=Mistral Large 2, Setting=Zero-shot2026.0585.57
STRATEGY-INDUCTBackbone=Gemini 2.0 Flash, Setting=Zero-shot2026.0585.45
STRATEGY-INDUCTBackbone=Gemini 1.5 Pro, Setting=Zero-shot2026.0585.39
ZCoTBackbone=Llama 3.1 405B, Setting=Zero-shot2026.0585.04
SCoTBackbone=Gemini 2.0 Pro Exp, Setting=Zero-shot2026.0585.04
SCoTBackbone=GPT o3 mini (low), Setting=Zero-shot2026.0585.04
SCoTBackbone=Llama 3.1 70B, Setting=Zero-shot2026.0584.52
SCoTBackbone=Llama 3.3 70B, Setting=Zero-shot2026.0584.52
ZCoTBackbone=GPT-4o, Setting=Zero-shot2026.0584.12
SCoTBackbone=Llama 3.1 405B, Setting=Zero-shot2026.0583.94
INDUCTBackbone=Gemini 1.5 Pro, Setting=Zero-shot2026.0583.71
ZCoTBackbone=Gemini 2.0 Pro Exp, Setting=Zero-shot2026.0583.62
ZCoTBackbone=Llama 3.3 70B, Setting=Zero-shot2026.0583.59
STRATEGY-INDUCTBackbone=GPT-4o mini, Setting=Zero-shot2026.0582.32
ZCoTBackbone=Llama 3.1 70B, Setting=Zero-shot2026.0582.09
ZCoTBackbone=Mistral Large 2, Setting=Zero-shot2026.0582.03
SCoTBackbone=Gemini 1.5 Pro, Setting=Zero-shot2026.0582.03
SCoTBackbone=Mistral Large 2, Setting=Zero-shot2026.0581.86
STRATEGY-INDUCTBackbone=Gemini 1.5 Flash, Setting=Zero-shot2026.0581.8
STRATEGY-INDUCTBackbone=Gemini 2.0 Flash Lite, Setting=Zero-shot2026.0581.8
ZCoTBackbone=Gemini 1.5 Pro, Setting=Zero-shot2026.0580.87
STRATEGY-INDUCTBackbone=Mistral Small 3, Setting=Zero-shot2026.0580.41
INDUCTBackbone=Gemini 2.0 Pro Exp, Setting=Zero-shot2026.0580.23
SCoTBackbone=GPT-4o mini, Setting=Zero-shot2026.0580.06
SCoTBackbone=Gemini 2.0 Flash, Setting=Zero-shot2026.0579.62
ZCoTBackbone=GPT-4o mini, Setting=Zero-shot2026.0579.54
INDUCTBackbone=Gemini 2.0 Flash, Setting=Zero-shot2026.0579.3
INDUCTBackbone=GPT-4o mini, Setting=Zero-shot2026.0578.78
ZCoTBackbone=Gemini 1.5 Flash, Setting=Zero-shot2026.0578.72
ZCoTBackbone=Gemini 2.0 Flash, Setting=Zero-shot2026.0578.33
SCoTBackbone=Gemini 2.0 Flash Lite, Setting=Zero-shot2026.0578.23
SCoTBackbone=Gemini 1.5 Flash, Setting=Zero-shot2026.0577.86
INDUCTBackbone=Gemini 1.5 Flash, Setting=Zero-shot2026.0577.68
INDUCTBackbone=Mistral Small 3, Setting=Zero-shot2026.0576.64
ZCoTBackbone=Gemini 2.0 Flash Lite, Setting=Zero-shot2026.0576.64
SCoTBackbone=Mistral Small 3, Setting=Zero-shot2026.0576.52
INDUCTBackbone=Gemini 2.0 Flash Lite, Setting=Zero-shot2026.0576.52
ZCoTBackbone=Mistral Small 3, Setting=Zero-shot2026.0575.07
STRATEGY-INDUCTBackbone=Mistral Small 2, Setting=Zero-shot2026.0570.32
ZCoTBackbone=Mistral Small 2, Setting=Zero-shot2026.0570.14
SCoTBackbone=Mistral Small 2, Setting=Zero-shot2026.0569.91
SCoTBackbone=Gemini 1.5 Flash 8B, Setting=Zero-shot2026.0569.8
INDUCTBackbone=Mistral Small 2, Setting=Zero-shot2026.0569.57
STRATEGY-INDUCTBackbone=Gemini 1.5 Flash 8B, Setting=Zero-shot2026.0569.33
ZCoTBackbone=Gemini 1.5 Flash 8B, Setting=Zero-shot2026.0567.42
INDUCTBackbone=Gemini 1.5 Flash 8B, Setting=Zero-shot2026.0567.07
STRATEGY-INDUCTBackbone=Llama 3.1 8B, Setting=Zero-shot2026.0565.33
ZCoTBackbone=Llama 3.1 8B, Setting=Zero-shot2026.0562.03
INDUCTBackbone=Llama 3.1 8B, Setting=Zero-shot2026.0559.48
ZCoTBackbone=Mistral Nemo 12B, Setting=Zero-shot2026.0556.46
SCoTBackbone=Llama 3.1 8B, Setting=Zero-shot2026.0556.29
STRATEGY-INDUCTBackbone=Mistral Nemo 12B, Setting=Zero-shot2026.0555.71
SCoTBackbone=Mistral Nemo 12B, Setting=Zero-shot2026.0553.97
INDUCTBackbone=Mistral Nemo 12B, Setting=Zero-shot2026.0552.29