Best LLMs for Long-Context Reasoning — Anthropic
The best Anthropic model for reasoning over long inputs is Claude Sonnet 5, scoring 70.7% on long-context reasoning — a different question from how large a window it accepts. Claude Opus 4.7 (70.3%) and Claude Opus 5 (70.0%) round out the top three.
- 1
claude-sonnet-5ReasoningToolsJSON+153.4 intel · $2.00/M · 95 t/s70.7%LCR - 2claude-opus-4.7ReasoningToolsJSON+153.5 intel · $5.00/M · 1M ctx70.3%LCR
- 3claude-opus-5ReasoningToolsJSON+160.7 intel · $5.00/M · 60 t/s70.0%LCR
- 4claude-fable-5ReasoningToolsJSON+159.9 intel · $10.00/M · 71 t/s70.0%LCR
- 5claude-opus-4.8ReasoningToolsJSON+155.7 intel · $5.00/M · 1M ctx67.7%LCR
- 6claude-opus-4.5ReasoningToolsJSON+134.7 intel · $5.00/M · 51 t/s65.3%LCR
- 7claude-opus-4.6ReasoningToolsJSON+137.8 intel · $5.00/M · 40 t/s58.3%LCR
- 8claude-sonnet-4.6ReasoningToolsJSON+135.9 intel · $3.00/M · 1M ctx57.7%LCR
- 9claude-sonnet-4.5ReasoningToolsJSON+129.3 intel · $3.00/M · 1M ctx51.3%LCR
- 10claude-sonnet-4ReasoningToolsVision25.5 intel · $3.00/M · 1M ctx44.3%LCR
- 11claude-haiku-4.5ReasoningToolsJSON+123.7 intel · $1.00/M · 91 t/s43.7%LCR
- 12claude-opus-4ReasoningToolsVision25.5 intel · $15.00/M · 200K ctx36.0%LCR
- 13claude-3-haikuToolsVision3.9 intel · $0.250/M · 89 t/s21.0%LCR
How this is ranked
AI models ranked by LCR — reasoning accuracy over long inputs, not just the size of the window they accept. A large context window is a capacity claim; this is the measurement of whether the model can still reason over information buried deep inside it. Pair it with the longest-context ranking, which sorts on raw window size.
Frequently asked
Which Anthropic model reasons best over long inputs?
The best Anthropic model for reasoning over long inputs is Claude Sonnet 5, scoring 70.7% on long-context reasoning — a different question from how large a window it accepts. Claude Opus 4.7 (70.3%) and Claude Opus 5 (70.0%) round out the top three.
What's a good alternative to Claude Sonnet 5?
Claude Opus 4.7 (70.3%) is the closest alternative on this metric, followed by Claude Opus 5 (70.0%). See the full ranking above for the tradeoffs.
How many Anthropic models are there?
modelgrep tracks 17 Anthropic models with live benchmarks, speed, latency and per-provider pricing, led on intelligence by Claude Opus 5. 13 of them qualify for this ranking.