// ranked · November 2026
Best LLM for Reasoning
Ranked by LiveBench’s reasoning category: logic puzzles, deduction and spatial reasoning tasks written after most training cutoffs.
Gemini 4 Argon leads on LiveBench reasoning at 95.1, ahead of GPT-6 Astra (92.7) and GPT-6.1 Sol (92.6).
Gemini 4 Argon vs GPT-6 Astra, head to headTop 10
| # | Model | Reasoning score | Blended / 1M | Context | Capabilities |
|---|---|---|---|---|---|
| 1 | Gemini 4 Argon google/gemini-4-argon | 95.1 | $4.00 | 1.0M | reasoningtoolsvision |
| 2 | GPT-6 Astra openai/gpt-6-astra | 92.7 | $20.00 | 1.1M | reasoningtoolsvision |
| 3 | GPT-6.1 Sol openai/gpt-6.1-sol | 92.6 | $4.00 | 1.1M | reasoningtoolsvision |
| 4 | Claude Opus 5.5 anthropic/claude-opus-5.5 | 92.2 | $8.00 | 1M | reasoningtoolsvision |
| 5 | Claude Fable 5.1 anthropic/claude-fable-5.1 | 91.7 | $20.00 | 1M | reasoningtoolsvision |
| 6 | Claude Sonnet 5.5 anthropic/claude-sonnet-5.5 | 91.6 | $4.00 | 1M | reasoningtoolsvision |
| 7 | SpaceXAI: Grok 4.6 x-ai/grok-4.6 | 91.2 | $3.00 | 500K | reasoningtoolsvision |
| 8 | Kimi K3.1 Pro moonshotai/kimi-k3.1-pro | 91.1 | $4.00 | 1.0M | reasoningtoolsvision |
| 9 | Kimi K3 moonshotai/kimi-k3 | 90.7 | $4.14 | 1.0M | reasoningtoolsvision |
| 10 | Muse Wonder meta/muse-wonder | 90.6 | $8.00 | 1.0M | reasoningtoolsvision |
18 more models qualify — see the full leaderboard.
FAQ
What is the best LLM for Reasoning in November 2026?
Gemini 4 Argon leads on LiveBench reasoning at 95.1, ahead of GPT-6 Astra (92.7) and GPT-6.1 Sol (92.6).
What is the best under $1.00 / 1m for reasoning?
DeepSeek V4.1 Flash 1017. Highest score at a blended list price of $1.00 per 1M tokens or less — 89.1 at $0.262.
How is this ranking produced?
Ranked by LiveBench’s reasoning category: logic puzzles, deduction and spatial reasoning tasks written after most training cutoffs.
Other rankings
How this ranking is produced
- One metric, stated above — nothing here is weighted or scored by us. Scores come from LiveBench release 2026-10-25; models without a published run don't appear in score-based rankings.
- Price, context and capabilities — live from OpenRouter, refreshed every 15 minutes.
- Ties — scores less than a point apart are called a tie; effort settings alone move a LiveBench score by more than that.
A public benchmark is someone else's workload. Before committing, see LLM & agent evaluation.