Best LLMs for Summarization
9 models · ranked by real Summarization usage
Key facts · week of 2026-08-10
The top 3 models (Xiaomi: MiMo-V2.5, OpenAI: gpt-oss-120b, Google: Gemini 3 Flash Preview (batch)) account for 37.7% of all usage.
§This week's biggest riser is StepFun: Step 3.7 Flash, up from #7 to #4.
§The cheapest model in the usage top 10 is OpenAI: gpt-oss-120b at $0.03 per 1M input tokens (usage rank #2).
§The largest context window in the top 10 is Xiaomi: MiMo-V2.5 at 1.1M tokens.
§
Cite as: AI Tier List, LLM Usage Rankings (2026-08-10), www.aitierlist.xyz/en/models/summarization — data: OpenRouter
Which model should you pick?
- When quality comes first
- DeepSeek: DeepSeek V4 Flash 0731
- Artificial Analysis intelligence index score 51.8 — highest in this ranking
- The proven default
- Xiaomi: MiMo-V2.5
- 19.8% usage share — #1 in real usage
- When cost matters
- NVIDIA: Nemotron 3 Ultra (free)
- Cheapest in the top 15 — Free/1M input
- For long docs & codebases
- OpenAI: GPT-5.6 Luna (batch)
- 1.1M token context window
- To bet on the trending choice
- StepFun: Step 3.7 Flash
- Up 3 spots (#7 → #4)
Full ranking · 9 models
| Rank | Model | Share |
|---|---|---|
1 | Xiaomi: MiMo-V2.5 | |
2 | OpenAI: gpt-oss-120b | |
3 | Google: Gemini 3 Flash Preview (batch) | |
4 | StepFun: Step 3.7 Flash | |
5 | DeepSeek: DeepSeek V4 Flash 0423 | |
6 | Tencent: Hy3 | |
7 | NVIDIA: Nemotron 3 Ultra (free) | |
8 | OpenAI: GPT-5.6 Luna (batch) | |
9 | DeepSeek: DeepSeek V4 Flash 0731 |
Model Comparisons
- Xiaomi: MiMo-V2.5 vs OpenAI: gpt-oss-120b
- Xiaomi: MiMo-V2.5 vs Google: Gemini 3 Flash Preview (batch)
- Xiaomi: MiMo-V2.5 vs StepFun: Step 3.7 Flash
- OpenAI: gpt-oss-120b vs Google: Gemini 3 Flash Preview (batch)
- OpenAI: gpt-oss-120b vs StepFun: Step 3.7 Flash
- Google: Gemini 3 Flash Preview (batch) vs StepFun: Step 3.7 Flash
- Full LLM API pricing →
Related AI Tool Tier Lists
Get notified when Summarization rankings move
This ranking refreshes every week. We email you when it moves — once a week, no spam.
FAQ
What is the most-used LLM for Summarization?
Xiaomi: MiMo-V2.5 by xiaomi ranks first for Summarization by real token usage. It accounts for roughly 19.8% of tokens in this segment. OpenAI: gpt-oss-120b, Google: Gemini 3 Flash Preview (batch), StepFun: Step 3.7 Flash follow.
How are these rankings calculated?
Models are ranked by tokens actually consumed through OpenRouter, not by benchmark scores. This page counts only usage tagged as Summarization tasks. It refreshes weekly and currently tracks 9 models.
Which is the cheapest LLM for Summarization?
Among the paid models in this ranking, OpenAI: gpt-oss-120b is cheapest at $0.03 per 1M input tokens. 1 models in the list are free to use.
Is Xiaomi: MiMo-V2.5 still the most-used LLM for Summarization right now?
Yes. As of the week of 2026-08-10, Xiaomi: MiMo-V2.5 is #1 by real usage. It was #1 last week too. The ranking refreshes weekly, so this page changes as soon as it does.
Which model has the longest context window?
Xiaomi: MiMo-V2.5 has the longest context window in this ranking at 1.1M tokens.
Token usage and share data aggregated by OpenRouter, refreshed weekly. Prices are USD per 1M tokens. Benchmark scores come from Artificial Analysis; models it hasn't measured show —.