Large Language Models
docAnalyzer keeps pace with releases from Alibaba, Anthropic, DeepSeek, Google, Minimax, Moonshot AI, OpenAI, Xiaomi, and xAI, adding new models within days so you can pick the right fit for every workflow. We surface 22 models across 9 creators, each benchmarked for quality, speed, and responsiveness.
Refreshed 2026-09-20
52.7 top quality · GPT-6 Astra
351 tok/s top speed · Gemini 3.5 Flash Lite
0 ms top responsiveness · GPT-5 nano
| Model | |||
|---|---|---|---|
 GPT-6 Astra OpenAI | 52.7 | 60 tok/s | 206.39 s |
 Claude Opus 5 Anthropic | 50.8 | 52 tok/s | 29.83 s |
| GPT-5.6 Sol OpenAI | 47.0 | 65 tok/s | 64.46 s |
 Qwen3.8 Max Alibaba | 45.4 | 39 tok/s | 1.72 s |
 Grok 4.6 xAI | 44.3 | 58 tok/s | 35.83 s |
 Kimi K3 Moonshot AI | 43.6 | 40 tok/s | 2.81 s |
| GPT-5.6 Terra OpenAI | 42.1 | 91 tok/s | 115.76 s |
 Gemini 3.8 Flash Google | 40.9 | 312 tok/s | 12.22 s |
 DeepSeek V4.1 Flash DeepSeek | 39.5 | 225 tok/s | 810 ms |
| Claude Sonnet 5 Anthropic | 38.2 | 78 tok/s | 116.56 s |
| GPT-5.6 Luna OpenAI | 37.3 | 155 tok/s | 81.86 s |
| Qwen 3.8 27B Alibaba | 33.7 | 44 tok/s | 1.25 s |
| Gemini 3.1 Pro Preview Google | 29.7 | 125 tok/s | 24.64 s |
| Qwen3.7 Max Alibaba | 29.5 | 0 tok/s | 0 ms |
 MiniMax M3 Minimax | 29.2 | 110 tok/s | 980 ms |
 MiMo V2.5 Pro Xiaomi | 26.0 | 50 tok/s | 3.48 s |
| Qwen3.7 Plus Alibaba | 25.2 | 67 tok/s | 1.61 s |
| MiMo V2.5 Xiaomi | 25.2 | 32 tok/s | 2.24 s |
| Grok 4.3 xAI | 24.9 | 0 tok/s | 0 ms |
| Gemini 3.5 Flash Lite Google | 22.2 | 351 tok/s | 6.71 s |
| Claude Haiku 4.5 Anthropic | 16.9 | 114 tok/s | 13.49 s |
| GPT-5 nano OpenAI | 13.0 | 0 tok/s | 0 ms |
* Latency uses a logarithmic scale: shorter time means a longer bar.