Every model. Every benchmark. One table.

Curated catalog with lineage and sourced scores.

106 models · 6 benchmarks

columns
Claude Opus 5100$5$2596
GPT-5.6100$5$3094.6
Claude Mythos 597$10$5094.195.5
Claude Fable 596$10$5095
Claude Opus 4.794$5$2594.287.6
GPT-5.594$5$3093.6
Claude Opus 4.893$5$2593.688.6
Gemini 3.1 Pro91$2$1294.380.6
GPT-5.490$2.5$1592.8
Claude Sonnet 590$3$1585.2
Claude Opus 4.689$5$2591.3199.7980.84
GPT-5.288$1.75$1492.410080
DeepSeek V4-Pro85$0.435$0.8787.590.180.6
GLM-5.284$1.4$4.491.2
Kimi K2.680$0.95$490.580.2
MiniMax M379$0.3$1.280.5
Claude Sonnet 4.679$3$1589.995.679.6
Kimi K2.578$0.6$387.187.696.176.8
Claude Opus 4.577$5$258792.7780.9
Qwen3.5 397B A17B76$0.6$3.687.888.476.4
DeepSeek V4-Flash76$0.14$0.2886.288.179
Gemini 3 Flash75$0.5$390.478
Mistral Large 273self-hostself-host8492
Gemma 4 31B Instruct70self-hostself-host85.284.3
Gemini 3 Pro7091.976.2
GPT-5.169$1.25$1088.19476.3
Gemini 3.1 Flash-Lite68$0.25$1.586.9
GPT-5.1-Codex-Max67$1.25$1077.9
GPT-566$1.25$1094.674.9
GLM-4.766$0.6$2.284.385.795.773.8
GLM-5.165$1.4$4.486.2
GLM-564$1$3.28677.8
Claude 3.5 Sonnet6388.759.492
Mistral Medium 3.563$1.5$7.577.6
MiniMax M2.162$0.3$1.288838374
Llama 3.1 405B61self-hostself-host85.2
Nemotron 3 Ultra 550B A55B61self-hostself-host86.870.7
Claude Sonnet 4.560$3$1577.2
GLM-4.558$0.6$2.29084.679.164.2
Gemma 4 26B A4B Instruct58self-hostself-host82.682.3
DeepSeek V3.2-Exp55self-hostself-host8579.989.367.8
Nemotron 3 Super 120B A12B49self-hostself-host83.7390.2160.47
Nemotron 3 Nano 30B A3B49self-hostself-host78.389.1
Llama 3.1 405B Instruct48self-hostself-host88.651.1
DeepSeek R1-052847self-hostself-host858187.557.6
Gemini 2.5 Pro45$1.25$1086.48859.6
DeepSeek V3.145self-hostself-host80.188.466
Ministral 3 14B Reasoning44$0.2$0.285
GPT-4.144$2$890.266.354.6
GLM-4.7-Flash42self-hostself-host91.659.2
Grok 34179.975.4
MiniMax M240$0.3$1.282787869.4
Olmo 3-Think 32B39self-hostself-host85.472.5
Gemma 4 12B Instruct39self-hostself-host77.278.8
Claude Haiku 4.538$1$57380.773.3
Devstral 238$0.4$272.2
Kimi K237self-hostself-host87.881.175.149.565.8
Llama 4 Maverick Instruct37self-hostself-host80.569.8
Claude Opus 436$15$7579.675.572.5
Qwen3 235B A22B35$0.7$2.871.181.5
DeepSeek R135self-hostself-host71.5
Qwen2.5-Coder 32B Instruct35self-hostself-host79.162.341.892.7
Gemini 1.5 Pro3181.971.9
Devstral Small 231$0.1$0.368
DeepSeek V331self-hostself-host88.575.959.142
Granite 4.1 30B31self-hostself-host80.1664.0945.7688.41
Llama 3.3 70B Instruct31self-hostself-host68.950.588.4
Claude Sonnet 430$3$1575.470.572.7
MiniMax M130self-hostself-host81.17076.956
Gemini 2.5 Flash27$0.3$2.580.875.654
Gemini 2.0 Flash2777.660.1
Llama 3.1 70B Instruct26self-hostself-host83.666.44880.5
Qwen2.5 72B Instruct25self-hostself-host71.14986.6
Mistral Large 324$0.5$1.567.17
Gemma 3 27B Instruct23self-hostself-host76.967.542.487.8
Claude 3.7 Sonnet236863.7
o122$15$6078.340.9
Qwen3 32B21$0.16$0.6468.472.9
DeepSeek R1-Distill-Qwen-32B21self-hostself-host62.1
Llama 4 Scout Instruct19self-hostself-host74.357.2
Magistral Medium18$2$570.864.9
Mixtral 8x22B14$2$677.7545.1
Gemma 2 27B13self-hostself-host75.251.8
Llama 3.1 8B Instruct10self-hostself-host69.448.331.872.6
DeepSeek R1 Distill Llama 8B8self-hostself-host49
Llama 3.1 8B6self-hostself-host66.7
Devstral Small 1.14self-hostself-host53.6
Llama 3.2 3B Instruct0self-hostself-host63.4
DeepSeek V3.2self-hostself-host
DeepSeek V3.2-Specialeself-hostself-host
Gemini 3.5 Flash$1.5$9
Gemini 3.5 Flash-Lite$0.3$2.5
Gemini 3.6 Flash$1.5$7.5
Gemini 3 Deep Think
GLM-4.6$0.6$2.2
GPT-4o$2.5$10
GPT-5.2-Codex$1.75$14
GPT-5.3-Codex$1.75$14
Grok 4
Grok 4.1
Grok 4.1 Fast
Grok 4.5$2$6
Hermes 3 Llama 3.1 8Bself-hostself-host
Kimi K2.7-Code$0.95$4
o3$2$8
o4-mini$1.1$4.4