Best LLMs for Long-Context Reasoning — OpenAI
The best OpenAI model for reasoning over long inputs is GPT-5.2-Codex, scoring 75.7% on long-context reasoning — a different question from how large a window it accepts. GPT-5 (75.6%) and GPT-5.1 (75.0%) round out the top three.
- 1
gpt-5.2-codexReasoningToolsJSON+140.1 intel · $1.75/M · 400K ctx75.7%LCR - 2gpt-5ReasoningToolsJSON+134.7 intel · $1.25/M · 400K ctx75.6%LCR
- 3gpt-5.1ReasoningToolsJSON+136.9 intel · $1.25/M · 400K ctx75.0%LCR
- 4gpt-5.5ReasoningToolsJSON+154.8 intel · $5.00/M · 72 t/s74.3%LCR
- 5gpt-5.6-lunaReasoningToolsJSON+151.2 intel · $0.100/M · 86 t/s74.0%LCR
- 6gpt-5.6-terraReasoningToolsJSON+155.0 intel · $1.00/M · 60 t/s74.0%LCR
- 7gpt-5.4ReasoningToolsJSON+151.4 intel · $2.50/M · 72 t/s74.0%LCR
- 8gpt-5.3-codexReasoningToolsJSON+144.3 intel · $1.75/M · 55 t/s74.0%LCR
- 9gpt-5.6-solReasoningToolsJSON+158.9 intel · $5.00/M · 49 t/s73.7%LCR
- 10gpt-5.2ReasoningToolsJSON+142.2 intel · $1.75/M · 400K ctx72.7%LCR
- 11gpt-5.4-miniReasoningToolsJSON+140.0 intel · $0.750/M · 132 t/s69.3%LCR
- 12o3ReasoningToolsJSON+130.4 intel · $2.00/M · 44 t/s69.3%LCR
- 13gpt-5-miniReasoningToolsJSON+125.3 intel · $0.250/M · 400K ctx68.0%LCR
- 14gpt-5.1-codexReasoningToolsJSON+134.7 intel · $1.25/M · 400K ctx67.3%LCR
- 15gpt-5.4-nanoReasoningToolsJSON+138.2 intel · $0.200/M · 45 t/s66.0%LCR
- 16gpt-5.1-codex-miniReasoningToolsJSON+130.6 intel · $0.250/M · 400K ctx62.7%LCR
- 17gpt-4.1ToolsJSONVision19.4 intel · $2.00/M · 62 t/s61.0%LCR
- 18o1ReasoningToolsJSON+123.4 intel · $15.00/M · 48 t/s59.3%LCR
- 19o4-mini-highReasoningToolsJSON+125.6 intel · $1.10/M · 95 t/s55.0%LCR
- 20o4-miniReasoningToolsJSON+125.6 intel · $1.10/M · 81 t/s55.0%LCR
- 21gpt-oss-120bReasoningToolsJSON23.8 intel · $0.037/M · 199 t/s50.7%LCR
- 22gpt-4.1-miniToolsJSONVision14.8 intel · $0.400/M · 43 t/s42.3%LCR
- 23gpt-5-nanoReasoningToolsJSON+119.9 intel · $0.050/M · 400K ctx41.7%LCR
- 24o3-mini-highReasoningToolsJSON15.6 intel · $1.10/M · 115 t/s39.3%LCR
- 25gpt-4o-2024-08-06ToolsJSONVision9.6 intel · $2.50/M · 28 t/s35.0%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 OpenAI model reasons best over long inputs?
The best OpenAI model for reasoning over long inputs is GPT-5.2-Codex, scoring 75.7% on long-context reasoning — a different question from how large a window it accepts. GPT-5 (75.6%) and GPT-5.1 (75.0%) round out the top three.
What's a good alternative to GPT-5.2-Codex?
GPT-5 (75.6%) is the closest alternative on this metric, followed by GPT-5.1 (75.0%). See the full ranking above for the tradeoffs.
How many OpenAI models are there?
modelgrep tracks 60 OpenAI models with live benchmarks, speed, latency and per-provider pricing, led on intelligence by GPT-5.6 Sol. 25 of them qualify for this ranking.