Large Language Models
docAnalyzer keeps pace with releases from Alibaba, Anthropic, Google, Meta, Minimax, Moonshot AI, OpenAI, Xiaomi, and xAI, adding new models within days so you can pick the right fit for every workflow. We surface 20 models across 9 creators, each benchmarked for quality, speed, and responsiveness.
Refreshed 2026-11-07
59.1 top quality · Claude Opus 5.5
382 tok/s top speed · Gemini 3.5 Flash Lite
820 ms top responsiveness · MiniMax M3
| Model | |||
|---|---|---|---|
 Claude Opus 5.5 Anthropic | 59.1 | 95 tok/s | 647.78 s |
 GPT-6 Astra OpenAI | 56.9 | 46 tok/s | 362.51 s |
| GPT-6.1 Sol OpenAI | 54.6 | 58 tok/s | 309.89 s |
| Claude Sonnet 5.5 Anthropic | 54.5 | 135 tok/s | 389.26 s |
 Gemini 4 Argon Google | 50.4 | 88 tok/s | 50.79 s |
| Claude Fable 5.1 Anthropic | 50.0 | 61 tok/s | 97.89 s |
 Muse Wonder Meta | 43.6 | 134 tok/s | 26.01 s |
| Muse Spark 1.3 Meta | 36.6 | 136 tok/s | 34.78 s |
| Claude Haiku 5.5 Anthropic | 36.5 | 233 tok/s | 278.19 s |
 Grok 4.7 xAI | 35.5 | 64 tok/s | 36.63 s |
 Qwen3.8 Max Alibaba | 33.7 | 38 tok/s | 3.18 s |
| Gemini 3.8 Flash Google | 30.8 | 119 tok/s | 27.56 s |
 MiMo V2.6 Pro Xiaomi | 29.9 | 39 tok/s | 3.17 s |
| GPT-6 Luna OpenAI | 27.9 | 121 tok/s | 118.79 s |
| MiMo V2.6 Flash Xiaomi | 26.7 | 35 tok/s | 3.62 s |
| GPT-5.6 Luna OpenAI | 23.8 | 125 tok/s | 106.26 s |
| Qwen 3.8 27B Alibaba | 20.1 | 38 tok/s | 4.03 s |
 MiniMax M3 Minimax | 18.9 | 114 tok/s | 820 ms |
 Kimi K3 Moonshot AI | 17.4 | 49 tok/s | 3.82 s |
| Gemini 3.5 Flash Lite Google | 11.7 | 382 tok/s | 7.20 s |
* Latency uses a logarithmic scale: shorter time means a longer bar.