List your company
ResearchFormerly WizWand

General Reasoning on BIG-bench

81.6Accuracy (General)POES
40.93651.49362.0572.607Apr 13, 2026
Updated 6mo ago

Evaluation results

MethodLinks
POESOptimizer=OPRO, Model=Llama-3.1-8B-Instruct2026.0481.6———
IPOMPOptimizer=OPRO, Model=Llama-3.1-8B-Instruct2026.0475.8———
RandomOptimizer=OPRO, Model=Llama-3.1-8B-Instruct2026.0474.8———
PredictionOptimizer=OPRO, Model=Llama-3.1-8B-Instruct2026.0474.6———
SESSOptimizer=OPRO, Model=Llama-3.1-8B-Instruct2026.0471.9———
POESOptimizer=EvoPrompt-DE, Model=Llama-3.1-8B-Instruct2026.0471.3———
AnchorOptimizer=OPRO, Model=Llama-3.1-8B-Instruct2026.0470.9———
POESOptimizer=EvoPrompt-DE, Model=Qwen-2.5-7B-Instruct2026.0463.3———
POESOptimizer=EvoPrompt-GA, Model=Llama-3.1-8B-Instruct2026.0461.2———
POESOptimizer=OPRO, Model=Qwen-2.5-7B-Instruct2026.0459.3———
POESOptimizer=EvoPrompt-GA, Model=Qwen-2.5-7B-Instruct2026.0456.6———
IPOMPOptimizer=EvoPrompt-DE, Model=Qwen-2.5-7B-Instruct2026.0455.8———
PredictionOptimizer=EvoPrompt-GA, Model=Llama-3.1-8B-Instruct2026.0455———
AnchorOptimizer=EvoPrompt-DE, Model=Qwen-2.5-7B-Instruct2026.0454.6———
SESSOptimizer=EvoPrompt-GA, Model=Llama-3.1-8B-Instruct2026.0453.8———
AnchorOptimizer=EvoPrompt-GA, Model=Llama-3.1-8B-Instruct2026.0453.3———
AnchorOptimizer=EvoPrompt-DE, Model=Llama-3.1-8B-Instruct2026.0452.1———
IPOMPOptimizer=OPRO, Model=Qwen-2.5-7B-Instruct2026.0452———
SESSOptimizer=EvoPrompt-DE, Model=Llama-3.1-8B-Instruct2026.0451.7———
RandomOptimizer=EvoPrompt-GA, Model=Llama-3.1-8B-Instruct2026.0451.2———
PredictionOptimizer=EvoPrompt-DE, Model=Llama-3.1-8B-Instruct2026.0451.2———
IPOMPOptimizer=EvoPrompt-GA, Model=Llama-3.1-8B-Instruct2026.0450.8———
RandomOptimizer=EvoPrompt-DE, Model=Llama-3.1-8B-Instruct2026.0450.1———
PredictionOptimizer=EvoPrompt-GA, Model=Qwen-2.5-7B-Instruct2026.0449.6———
IPOMPOptimizer=EvoPrompt-DE, Model=Llama-3.1-8B-Instruct2026.0449.6———
RandomOptimizer=EvoPrompt-GA, Model=Qwen-2.5-7B-Instruct2026.0449.5———
SESSOptimizer=EvoPrompt-DE, Model=Qwen-2.5-7B-Instruct2026.0448.6———
RandomOptimizer=OPRO, Model=Qwen-2.5-7B-Instruct2026.0448.2———
PredictionOptimizer=OPRO, Model=Qwen-2.5-7B-Instruct2026.0446.7———
IPOMPOptimizer=EvoPrompt-GA, Model=Qwen-2.5-7B-Instruct2026.0446.7———
SESSOptimizer=OPRO, Model=Qwen-2.5-7B-Instruct2026.0446.5———
AnchorOptimizer=OPRO, Model=Qwen-2.5-7B-Instruct2026.0446.5———
SESSOptimizer=EvoPrompt-GA, Model=Qwen-2.5-7B-Instruct2026.0446.4———
RandomOptimizer=EvoPrompt-DE, Model=Qwen-2.5-7B-Instruct2026.0446.4———
PredictionOptimizer=EvoPrompt-DE, Model=Qwen-2.5-7B-Instruct2026.0444.6———
AnchorOptimizer=EvoPrompt-GA, Model=Qwen-2.5-7B-Instruct2026.0442.5———
Prompt basedBackbone=Gemma-2-9B-it, Configuration=w/o reflection2025.05—61.275.614.4
Prompt basedBackbone=Gemma-2-9B-it, Configuration=w/ reflection2025.05—61.274.413.2
Prompt basedBackbone=Gemma-2-27B-it, Configuration=w/o reflection2025.05—63.4728.6
Prompt basedBackbone=Gemma-2-27B-it, Configuration=w/ reflection2025.05—63.475.211.8
Prompt basedBackbone=Meta-Llama-3-8B-Instruct, Variant=w/o reflection2025.05—38.2——
Prompt basedBackbone=Meta-Llama-3-8B-Instruct, Variant=w/ reflection2025.05—38.252.414.2
Prompt basedBackbone=Meta-Llama-3-70B-Instruct, Variant=w/o reflection2025.05—48——
Prompt basedBackbone=Meta-Llama-3-70B-Instruct, Variant=w/ reflection (variant 1)2025.05—486719
Prompt basedBackbone=Meta-Llama-3-70B-Instruct, Variant=w/ reflection (variant 2)2025.05—4864.416.4
Prompt basedBackbone=Mistral-7B-Instruct-v0.2, Variant=w/o reflection2025.05—36.6——
Prompt basedBackbone=Mistral-7B-Instruct-v0.2, Variant=w/ reflection2025.05—36.643.87.2
Prompt basedBackbone=Mistral-22B-Small-Instruct, Variant=w/o reflection2025.05—54.4——
Prompt basedBackbone=Mistral-22B-Small-Instruct, Variant=w/ reflection (variant 1)2025.05—54.467.212.8
Prompt basedBackbone=Mistral-22B-Small-Instruct, Variant=w/ reflection (variant 2)2025.05—54.46813.6
ReflectEvoBackbone=Gemma-2-9B-it, Configuration=one-stage w/ D+2025.05—61.278.417.2
ReflectEvoBackbone=Gemma-2-9B-it, Configuration=two-stage w/ D+2025.05—61.2675.8
ReflectEvoBackbone=Gemma-2-9B-it, Configuration=w/ D-2025.05—61.274.813.6
ReflectEvoBackbone=Gemma-2-9B-it, Configuration=w/ Dpref2025.05—61.27513.8
ReflectEvoBackbone=Meta-Llama-3-8B-Instruct, Variant=one-stage w/ D+2025.05—38.271.233
ReflectEvoBackbone=Meta-Llama-3-8B-Instruct, Variant=two-stage w/ D+2025.05—38.245.47.2
ReflectEvoBackbone=Meta-Llama-3-8B-Instruct, Variant=w/ D+/-2025.05—38.26324.8
ReflectEvoBackbone=Meta-Llama-3-8B-Instruct, Variant=w/ Dpref2025.05—38.259.621.4
ReflectEvoBackbone=Mistral-7B-Instruct-v0.2, Variant=one-stage w/ D+2025.05—36.651.615
ReflectEvoBackbone=Mistral-7B-Instruct-v0.2, Variant=two-stage w/ D+2025.05—36.671.134.5
ReflectEvoBackbone=Mistral-7B-Instruct-v0.2, Variant=w/ D+/-2025.05—36.650.213.6
ReflectEvoBackbone=Mistral-7B-Instruct-v0.2, Variant=w/ Dpref2025.05—36.648.411.8
SFT basedBackbone=Gemma-2-9B-it, Configuration=w/ SFT qa pairs2025.05—74.6——
SFT basedBackbone=Meta-Llama-3-8B-Instruct, Variant=w/ SFT qa pairs2025.05—61.6——
SFT basedBackbone=Mistral-7B-Instruct-v0.2, Variant=w/ SFT qa pairs2025.05—37.8——