The Model Index
The gap your audience does not see

Open vs closed

Open-weight models anyone can download and run trail the closed frontier by months, not years.

74open models above GPT-4 level
$0.036/Mcheapest open above GPT-4: gpt-oss-20b

How far behind open models aremonths, at each new open record

Each point is a new best open model, placed when its weights were published. Its height is how long before that a closed model had already reached the same score; zero means no closed model had that score yet. Points before the first measured closed model are left out. Hover for both models.

Strongest open model from each lab12 labs · measured models

Run it yourself →
ModelLabRegionIndex scoreWeights outCheapest $/MDownload
Kimi K3MoonshotChina
172
Jul 2026$3.02Weights ↗
GLM-5.3ZhipuChina
167
Aug 2026$0.26Weights ↗
DeepSeek-V4-ProDeepSeekChina
167
Aug 2026$1.98–
Inkling-SmallThinking MachinesUnited States
154
Jul 2026$0.64Weights ↗
Qwen3.8-27BAlibabaChina
152
Aug 2026$0.58Weights ↗
MiniMax-M2.5MiniMaxChina
146
Feb 2026$0.44Weights ↗
Nemotron 3 UltraNVIDIAUnited States
145
Jun 2026$0.93Weights ↗
Gemma 4GoogleUnited States
138
Apr 2026$0.15Weights ↗
Mistral Medium 3.5MistralEurope
134
Apr 2026$3.0–
gpt-oss-120bOpenAIUnited States
131
Aug 2025$0.065Weights ↗
Llama 4 MaverickMetaUnited States
115
Apr 2025$0.30Weights ↗
Phi-4MicrosoftUnited States
112
Dec 2024$0.088Weights ↗

Weights out is when the weights were published, which can trail the announcement. Cheapest price is the lowest API provider on OpenRouter, blended 3:1 input to output.