// ranked · November 2026
Best Vision LLM
Models that accept image input, ranked by LiveBench overall score. LiveBench doesn’t score vision separately, so this ranks general capability among models that can see.
Claude Fable 5.1 (85.7) and GPT-6 Astra (85.6) are effectively tied on LiveBench overall — less than a point apart, which effort settings alone can move. Claude Opus 5.5 follows at 85.1.
Claude Fable 5.1 vs GPT-6 Astra, head to headTop 10
| # | Model | Overall score | Blended / 1M | Context | Capabilities |
|---|---|---|---|---|---|
| 1 | Claude Fable 5.1 anthropic/claude-fable-5.1 | 85.7 | $20.00 | 1M | reasoningtoolsvision |
| 2 | GPT-6 Astra openai/gpt-6-astra | 85.6 | $20.00 | 1.1M | reasoningtoolsvision |
| 3 | Claude Opus 5.5 anthropic/claude-opus-5.5 | 85.1 | $8.00 | 1M | reasoningtoolsvision |
| 4 | GPT-6.1 Sol openai/gpt-6.1-sol | 84.1 | $4.00 | 1.1M | reasoningtoolsvision |
| 5 | Claude Sonnet 5.5 anthropic/claude-sonnet-5.5 | 80.0 | $4.00 | 1M | reasoningtoolsvision |
| 6 | Gemini 4 Argon google/gemini-4-argon | 79.3 | $4.00 | 1.0M | reasoningtoolsvision |
| 7 | GPT-6.1 Terra openai/gpt-6.1-terra | 77.8 | $2.00 | 1.1M | reasoningtoolsvision |
| 8 | Muse Wonder meta/muse-wonder | 74.2 | $8.00 | 1.0M | reasoningtoolsvision |
| 9 | DeepSeek V4.1 Flash 1017 deepseek/deepseek-v4.1-flash-1017 | 72.9 | $0.262 | 1.0M | reasoningtoolsvision |
| 10 | Kimi K3.1 Pro moonshotai/kimi-k3.1-pro | 71.3 | $4.00 | 1.0M | reasoningtoolsvision |
18 more models qualify — see the full leaderboard.
FAQ
What is the best vision LLM in November 2026?
Claude Fable 5.1 (85.7) and GPT-6 Astra (85.6) are effectively tied on LiveBench overall — less than a point apart, which effort settings alone can move. Claude Opus 5.5 follows at 85.1.
How is this ranking produced?
Models that accept image input, ranked by LiveBench overall score. LiveBench doesn’t score vision separately, so this ranks general capability among models that can see.
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.