Model results directory
Browse published models and tested efforts. An overall score requires all axes at one configuration; models with partial results remain in this directory.
46 models · 107 configurations
claude-fable-5-13 tested configurations · Best overall 87.25claude-haiku-5-51 tested configurations · Best overall 65.65claude-opus-4-83 tested configurations · Best overall 76.80claude-opus-53 tested configurations · Best overall 81.70claude-opus-5-52 tested configurations · Best overall 89.15claude-sonnet-5-51 tested configurations · Best overall 82.30
deepseek-v4-flash2 tested configurations · Best overall 60.50deepseek-v4-flash-vision-exp2 tested configurations · Best overall 59.95deepseek-v4-pro2 tested configurations · Best overall 65.15deepseek-v4.1-flash2 tested configurations · Best overall 67.85deepseek-v4.1-flash-10173 tested configurations · Best overall 74.30
dotBot1 tested configurations · Best overall 81.95
doubao-seed-2-1-pro1 tested configurations · Best overall 61.55
Gemini 3.7 Flash High1 tested configurations · Best overall 51.95Gemini 3.8 Flash High1 tested configurations · Best overall 59.80Gemini 4 Argon1 tested configurations · Best overall 79.35
glm-5.32 tested configurations · Best overall 70.40glm-5.3-flash2 tested configurations · Best overall 56.80gpt-5.6-luna5 tested configurations · Best overall 52.35gpt-5.6-sol5 tested configurations · Best overall 74.15gpt-5.6-terra5 tested configurations · Best overall 65.90gpt-6-astra5 tested configurations · Best overall 88.80gpt-6-luna6 tested configurations · Best overall 62.00gpt-6-sol5 tested configurations · Best overall 78.90gpt-6.1-sol5 tested configurations · Best overall 86.60gpt-6.1-terra5 tested configurations · Best overall 80.05
grok-4.62 tested configurations · Best overall 76.85grok-4.72 tested configurations · Best overall 78.55grok-botBot1 tested configurations · Best overall 76.35
hy4-preview1 tested configurations · Best overall 66.70
k2.82 tested configurations · Best overall 63.55k31 tested configurations · Best overall 71.60k3.1-pro2 tested configurations · Best overall 79.60
mimo-v2.6-flash1 tested configurations · Best overall 56.10mimo-v2.6-pro1 tested configurations · Best overall 69.25
MiniMax-M31 tested configurations · Best overall 52.95MiniMax-M3.1-Flash3 tested configurations · Best overall 73.60MiniMax-M3.1-Flash-Preview5 tested configurations · Best overall 68.45
muse-spark-1.31 tested configurations · Best overall 72.60muse-wonder4 tested configurations · Best overall 81.55
Nemotron-3-Ultra1 tested configurations · Best overall 44.05
Qwen 3.8 27b1 tested configurations · Best overall 53.00Qwen 3.8 Flash1 tested configurations · Best overall 65.15Qwen 3.8 Max1 tested configurations · Best overall 55.50
space-bunny1 tested configurations · Best overall 68.80
step-51 tested configurations · Best overall 65.20No models match your search. Try a model name or provider.