Model directory
239 modelsFind every BenchSift model page in one lightweight directory, then open a model to explore its benchmarks, pricing, and capabilities.
Page 4 of 5 · sorted by provider and name
ModelIntelligenceSpeedPrice/1MCompare
Mistral
5- Mistral Small 36.7$0.066.758 tok/s$0.06
- Mistral Small 3.17.1$0.097.130 tok/s$0.09
- Mistral Small 3.27.0$0.117.037 tok/s$0.11
- Mistral Small 411.3$0.2611.3165 tok/s$0.26
- Mixtral 8x7B Instruct5.1$0.515.125 tok/s$0.51
Moonshot AI
6- Kimi K212.7$112.755 tok/s$1
- Kimi K2 090515.3$1.0715.356 tok/s$1.07
- Kimi K2.523.5$1.1423.560 tok/s$1.14
- Kimi K2.627.0$1.7127.053 tok/s$1.71
- Kimi K2.7 Code25.8$1.7125.858 tok/s$1.71
- Kimi K343.6$643.643 tok/s$6
Multiverse Computing
1- Quasar 438B (Max, Based on GLM-5.2)26.7$0.9026.7145 tok/s$0.90
Nous Research
2- Hermes 3 - Llama-3.1 70B6.0$0.706.031 tok/s$0.70
- Hermes 4 - Llama-3.1 405B7.4$1.507.438 tok/s$1.50
NVIDIA
9- Llama 3.1 Nemotron Instruct 70B6.9$1.206.934 tok/s$1.20
- Llama Nemotron Super 49B v1.57.4$0.407.436 tok/s$0.40
- Nemotron 3 Nano Omni 30B A3B Reasoning10.3$0.4510.3237 tok/s$0.45
- Nemotron 3 Super 120B A12B12.8$0.4512.8146 tok/s$0.45
- Nemotron 3 Ultra 550B A55B22.9$1.0722.9155 tok/s$1.07
- Nemotron 3.5 Lightning12.9$0.1012.9302 tok/s$0.10
- NVIDIA Nemotron 3 Nano 30B A3B6.8$0.096.8250 tok/s$0.09
- NVIDIA Nemotron Nano 12B v2 VL5.8$0.305.8206 tok/s$0.30
- NVIDIA Nemotron Nano 9B V26.8$0.096.8170 tok/s$0.09
OpenAI
25- GPT-4 Turbo7.0$157.032 tok/s$15
- GPT-4.112.7$3.5012.7152 tok/s$3.50
- GPT-4.1 mini10.2$0.7010.2147 tok/s$0.70
- GPT-4.1 nano7.8$0.177.8212 tok/s$0.17
- GPT-4o (Aug '24)7.7$4.387.7147 tok/s$4.38
- GPT-4o (May '24)7.3$7.507.3133 tok/s$7.50
- GPT-4o (Nov '24)8.4$4.388.4152 tok/s$4.38
- GPT-4o mini6.7$0.266.7113 tok/s$0.26
- GPT-523.0$3.4423.0102 tok/s$3.44
- GPT-5 Codex (High)24.9$3.4424.9166 tok/s$3.44
- GPT-5 mini16.8$0.6916.8148 tok/s$0.69
- GPT-5 nano13.0$0.1413.0162 tok/s$0.14
- GPT-5.124.7$3.4424.7112 tok/s$3.44
- GPT-5.1 Codex (High)23.7$3.4423.7126 tok/s$3.44
- GPT-5.1 Codex mini (High)20.4$0.6920.4173 tok/s$0.69
- GPT-5.230.4$4.8130.473 tok/s$4.81
- GPT-5.2 Codex (Xhigh)28.5$4.8128.5115 tok/s$4.81
- GPT-5.3 Codex (Xhigh)32.5$4.8132.599 tok/s$4.81
- GPT-5.439.0$5.6339.085 tok/s$5.63
- GPT-5.4 mini24.1$1.6924.1233 tok/s$1.69
- GPT-5.4 nano20.7$0.4620.7166 tok/s$0.46
- GPT-5.538.4$11.2538.482 tok/s$11.25
- GPT-5.5 Instant (June 2026)26.0$11.2526.0151 tok/s$11.25
- GPT-5.6 Luna37.3$0.4537.3115 tok/s$0.45
- GPT-5.6 Sol47.0$847.086 tok/s$8
