List your company
ResearchFormerly WizWand

General Reasoning on LiveBench

53.47AccuracyPerSyn
7.741219.613131.48543.3569Oct 7, 2025Nov 16, 2025Dec 26, 2025Feb 4, 2026Mar 16, 2026Apr 25, 2026Jun 4, 2026
Updated 4mo ago

Evaluation results

MethodLinks
PerSynStudent Model=Qwen2.5-14B2025.1053.47
CARStudent Model=Qwen2.5-14B2025.1052.06
ARM + MPFoundation Model=GPT-4o2025.1051.9
Family-StrongStudent Model=Qwen2.5-14B2025.1050.59
ARM + MPFoundation Model=LLaMA-3.3-70B2025.1050
PerSynStudent Model=Qwen2.5-7B2025.1049.08
MixStudent Model=Qwen2.5-14B2025.1048.85
LLM-DebateFoundation Model=GPT-4o2025.1047.5
ARMFoundation Model=GPT-4o2025.1047.5
CARStudent Model=Qwen2.5-7B2025.1047.33
Self-RefineFoundation Model=LLaMA-3.3-70B2025.1046.9
StrongStudent Model=Qwen2.5-14B2025.1046.34
CoTFoundation Model=GPT-4o2025.1046.2
LLM-DebateFoundation Model=LLaMA-3.3-70B2025.1046.2
ADASFoundation Model=LLaMA-3.3-70B, Evaluation Setup=1000-sample2025.1046.2
ARMFoundation Model=LLaMA-3.3-70B2025.1046.2
Family-StrongStudent Model=Qwen2.5-7B2025.1046.15
ARM + MPFoundation Model=GPT-4.1-nano2025.1045.6
AFlowFoundation Model=GPT-4o, Evaluation Setup=1000-sample2025.1045
CoT-SCFoundation Model=LLaMA-3.3-70B2025.1045
MixStudent Model=Qwen2.5-7B2025.1044.26
StrongStudent Model=Qwen2.5-7B2025.1043.02
CoT-SCFoundation Model=GPT-4o2025.1042.5
ADASFoundation Model=GPT-4o, Evaluation Setup=1000-sample2025.1041.9
AFlowFoundation Model=GPT-4o, Evaluation Setup=test set2025.1041.9
ARMFoundation Model=GPT-4.1-nano2025.1039.4
ADASFoundation Model=GPT-4o, Evaluation Setup=test set2025.1038.8
CoTFoundation Model=LLaMA-3.3-70B2025.1038.1
AFlowFoundation Model=LLaMA-3.3-70B, Evaluation Setup=test set2025.1038.1
PerSynStudent Model=Gemma-2-9B2025.1037.84
Self-RefineFoundation Model=GPT-4o2025.1037.5
ADASFoundation Model=LLaMA-3.3-70B, Evaluation Setup=test set2025.1037.5
PerSynStudent Model=Llama-3.1-8B2025.1037.13
CoT-SCFoundation Model=GPT-4.1-nano2025.1036.9
CARStudent Model=Gemma-2-9B2025.1036.63
Family-StrongStudent Model=Gemma-2-9B2025.1036.09
CARStudent Model=Llama-3.1-8B2025.1035.86
MixStudent Model=Llama-3.1-8B2025.1035.42
MixStudent Model=Gemma-2-9B2025.1034.63
LLM-DebateFoundation Model=GPT-4.1-nano2025.1033.8
StrongStudent Model=Gemma-2-9B2025.1033.49
Family-StrongStudent Model=Llama-3.1-8B2025.1033.25
CoTFoundation Model=GPT-4.1-nano2025.1033.1
StrongStudent Model=Llama-3.1-8B2025.1032.87
ADASFoundation Model=GPT-4.1-nano, Evaluation Setup=test set2025.1031.2
AFlowFoundation Model=GPT-4.1-nano, Evaluation Setup=test set2025.1030.6
AFlowFoundation Model=GPT-4.1-nano, Evaluation Setup=1000-sample2025.1030.6
ADASFoundation Model=GPT-4.1-nano, Evaluation Setup=1000-sample2025.1029.4
SDAR-8BScale=8B, Tokens=55B, FLOPs=2640, Decoding Strategy=greedy static decoding, Block Size=42026.0628.6
Self-RefineFoundation Model=GPT-4.1-nano2025.1028.1
OPDLM-4BScale=4B, Tokens=0.076B, FLOPs=2.4, Decoding Strategy=greedy static decoding, Block Size=42026.0627.8
OPDLM-8BScale=8B, Tokens=0.066B, FLOPs=4.2, Decoding Strategy=greedy static decoding, Block Size=42026.0625.8
SDAR-4BScale=4B, Tokens=55B, FLOPs=1320, Decoding Strategy=greedy static decoding, Block Size=42026.0625.3
AFlowFoundation Model=LLaMA-3.3-70B, Evaluation Setup=1000-sample2025.1015.6
Fast-dLLM-v2-7BScale=8B, Tokens=1B, FLOPs=42, Decoding Strategy=greedy static decoding, Block Size=42026.069.5