Best Anthropic Reasoning Models
The best Anthropic 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.
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
- 4claude-opus-4.8ReasoningToolsJSON+155.7 intel · $5.00/M · 1M ctx55.7Intelligence
- 5claude-opus-4.8:batchReasoningToolsJSON+155.7 intel · $2.50/M · 1M ctx55.7Intelligence
- 6claude-opus-4.7ReasoningToolsJSON+153.5 intel · $5.00/M · 1M ctx53.5Intelligence
- 7claude-opus-4.7:batchReasoningToolsJSON+153.5 intel · $2.50/M · 1M ctx53.5Intelligence
- 8claude-sonnet-5ReasoningToolsJSON+153.4 intel · $2.00/M · 1M ctx53.4Intelligence
- 9claude-sonnet-5:batchReasoningToolsJSON+153.4 intel · $1.00/M · 1M ctx53.4Intelligence
- 10claude-opus-4.6ReasoningToolsJSON+137.8 intel · $5.00/M · 1M ctx37.8Intelligence
- 11claude-opus-4.6:batchReasoningToolsJSON+137.8 intel · $2.50/M · 1M ctx37.8Intelligence
- 12claude-sonnet-4.6ReasoningToolsJSON+135.9 intel · $3.00/M · 1M ctx35.9Intelligence
- 13claude-opus-4.5ReasoningToolsJSON+134.7 intel · $5.00/M · 200K ctx34.7Intelligence
- 14claude-opus-4.5:batchReasoningToolsJSON+134.7 intel · $2.50/M · 200K ctx34.7Intelligence
- 15claude-sonnet-4.5ReasoningToolsJSON+129.3 intel · $3.00/M · 1M ctx29.3Intelligence
- 16claude-sonnet-4.5:batchReasoningToolsJSON+129.3 intel · $1.50/M · 1M ctx29.3Intelligence
- 17claude-opus-4.1ReasoningToolsJSON+128.2 intel · $15.00/M · 200K ctx28.2Intelligence
- 18claude-opus-4.1:batchReasoningToolsJSON+128.2 intel · $7.50/M · 200K ctx28.2Intelligence
- 19claude-opus-4ReasoningToolsVision25.5 intel · $15.00/M · 200K ctx25.5Intelligence
- 20claude-sonnet-4ReasoningToolsVision25.5 intel · $3.00/M · 1M ctx25.5Intelligence
- 21claude-haiku-4.5ReasoningToolsJSON+123.7 intel · $1.00/M · 200K ctx23.7Intelligence
- 22claude-haiku-4.5:batchReasoningToolsJSON+123.7 intel · $0.500/M · 200K ctx23.7Intelligence
- 23claude-opus-5-fastReasoningToolsJSON+1$10.00/M · 1M ctx—Intelligence
- 24claude-opus-4.8-fastReasoningToolsJSON+1$10.00/M · 1M ctx—Intelligence
- 25claude-opus-4.7-fastReasoningToolsJSON+1$30.00/M · 1M ctx—Intelligence
Frequently asked
What is the best Anthropic model for reasoning?
The best Anthropic 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.
How many Anthropic models are there?
modelgrep tracks 26 Anthropic models with live benchmarks, speed, latency and per-provider pricing, led on intelligence by Claude Opus 5. 25 of them qualify for this ranking.