Best Reasoning LLMs
The best LLM for reasoning is Claude Opus 5 — 60.7 intelligence with extended step-by-step thinking. Claude Fable 5 (59.9) and Claude Fable 5 (batch) (59.9) round out the top three.
Large language models with extended reasoning / thinking, ranked by intelligence. The smartest AI models for complex multi-step reasoning, math and analysis.
- 1
claude-opus-5ReasoningToolsJSON+160.7 intel · $5.00/M · 1M ctx60.7Intelligence - 2claude-fable-5ReasoningToolsJSON+159.9 intel · $10.00/M · 1M ctx59.9Intelligence
- 3claude-fable-5:batchReasoningToolsJSON+159.9 intel · $5.00/M · 1M ctx59.9Intelligence
- 4
gpt-5.6-solReasoningToolsJSON+158.9 intel · $5.00/M · 1.1M ctx58.9Intelligence - 5
kimi-k3ReasoningToolsJSON+157.1 intel · $3.00/M · 1.0M ctx57.1Intelligence - 6claude-opus-4.8ReasoningToolsJSON+155.7 intel · $5.00/M · 1M ctx55.7Intelligence
- 7claude-opus-4.8:batchReasoningToolsJSON+155.7 intel · $2.50/M · 1M ctx55.7Intelligence
- 8gpt-5.6-terraReasoningToolsJSON+155.0 intel · $1.00/M · 1.1M ctx55.0Intelligence
- 9gpt-5.5ReasoningToolsJSON+154.8 intel · $5.00/M · 1.1M ctx54.8Intelligence
- 10gpt-5.5:batchReasoningToolsJSON+154.8 intel · $2.50/M · 1.1M ctx54.8Intelligence
- 11
grok-4.5ReasoningToolsJSON+153.8 intel · $2.00/M · 500K ctx53.8Intelligence - 12claude-opus-4.7ReasoningToolsJSON+153.5 intel · $5.00/M · 1M ctx53.5Intelligence
- 13claude-opus-4.7:batchReasoningToolsJSON+153.5 intel · $2.50/M · 1M ctx53.5Intelligence
- 14claude-sonnet-5ReasoningToolsJSON+153.4 intel · $2.00/M · 1M ctx53.4Intelligence
- 15claude-sonnet-5:batchReasoningToolsJSON+153.4 intel · $1.00/M · 1M ctx53.4Intelligence
- 16gpt-5.4ReasoningToolsJSON+151.4 intel · $2.50/M · 1.1M ctx51.4Intelligence
- 17gpt-5.4:batchReasoningToolsJSON+151.4 intel · $1.25/M · 1.1M ctx51.4Intelligence
- 18gpt-5.6-lunaReasoningToolsJSON+151.2 intel · $0.100/M · 1.1M ctx51.2Intelligence
- 19
glm-5.2ReasoningToolsJSON51.1 intel · $0.966/M · 1.0M ctx51.1Intelligence - 20Mmuse-spark-1.1ReasoningToolsJSON+250.6 intel · $1.25/M · 1.0M ctx50.6Intelligence
- 21
gemini-3.5-flashReasoningToolsJSON+250.2 intel · $1.50/M · 1.0M ctx50.2Intelligence - 22gemini-3.5-flash:batchReasoningToolsJSON+250.2 intel · $0.750/M · 1.0M ctx50.2Intelligence
- 23gemini-3.6-flashReasoningToolsJSON+250.1 intel · $1.50/M · 1.0M ctx50.1Intelligence
- 24gemini-3.6-flash:batchReasoningToolsJSON+250.1 intel · $0.750/M · 1.0M ctx50.1Intelligence
- 25gemini-3.1-pro-previewReasoningToolsJSON+246.5 intel · $2.00/M · 1.0M ctx46.5Intelligence
Frequently asked
What is the best LLM for reasoning?
The best LLM for reasoning is Claude Opus 5 — 60.7 intelligence with extended step-by-step thinking. Claude Fable 5 (59.9) and Claude Fable 5 (batch) (59.9) round out the top three.
What is the best AI for reasoning?
The best AI model for reasoning is Claude Opus 5 — 60.7 intelligence with extended step-by-step thinking. Claude Fable 5 (59.9) and Claude Fable 5 (batch) (59.9) round out the top three.
What's a good alternative to Claude Opus 5?
Claude Fable 5 (59.9) is the closest alternative on this metric, followed by Claude Fable 5 (batch) (59.9). See the full ranking above for the tradeoffs.