Best LLMs for Long-Context Reasoning — Qwen
The best Qwen model for reasoning over long inputs is Qwen3.6 Max Preview, scoring 69.7% on long-context reasoning — a different question from how large a window it accepts. Qwen3.6 Plus (69.7%) and Qwen3.7 Max (69.0%) round out the top three.
- 1
qwen3.6-max-previewReasoningToolsJSON40.0 intel · $1.03/M · 262K ctx69.7%LCR - 2qwen3.6-plusReasoningToolsJSON+139.6 intel · $0.325/M · 55 t/s69.7%LCR
- 3qwen3.7-maxReasoningToolsJSON46.0 intel · $1.48/M · 207 t/s69.0%LCR
- 4qwen3.6-27bReasoningToolsJSON+137.1 intel · $0.289/M · 60 t/s68.7%LCR
- 5qwen3.5-27bReasoningToolsJSON+133.8 intel · $0.195/M · 262K ctx67.3%LCR
- 6qwen3.5-122b-a10bReasoningToolsJSON+132.3 intel · $0.260/M · 127 t/s66.7%LCR
- 7qwen3-max-thinkingReasoningToolsJSON31.7 intel · $0.780/M · 262K ctx66.0%LCR
- 8qwen3.5-397b-a17bReasoningToolsJSON+133.7 intel · $0.390/M · 69 t/s65.7%LCR
- 9qwen3.7-plusReasoningToolsJSON+139.0 intel · $0.320/M · 54 t/s65.0%LCR
- 10qwen3.6-35b-a3bReasoningToolsJSON+131.6 intel · $0.140/M · 158 t/s63.7%LCR
- 11qwen3.5-35b-a3bReasoningToolsJSON+129.3 intel · $0.140/M · 262K ctx62.7%LCR
- 12qwen3.5-9bReasoningToolsJSON+121.4 intel · $0.100/M · 74 t/s59.0%LCR
- 13qwen3-next-80b-a3b-instructToolsJSON13.7 intel · $0.090/M · 205 t/s51.3%LCR
- 14qwen3-maxToolsJSON24.0 intel · $0.780/M · 262K ctx46.7%LCR
- 15qwen3-coder-nextToolsJSON21.1 intel · $0.120/M · 72 t/s40.0%LCR
- 16qwen3-vl-235b-a22b-instructToolsJSONVision14.3 intel · $0.210/M · 262K ctx31.7%LCR
- 17qwen3-vl-32b-instructToolsJSONVision11.1 intel · $0.104/M · 38 t/s31.3%LCR
- 18qwen3-coder-30b-a3b-instructToolsJSON13.6 intel · $0.070/M · 262K ctx29.0%LCR
- 19qwen3-vl-30b-a3b-instructToolsJSONVision10.0 intel · $0.150/M · 34 t/s23.7%LCR
- 20qwen-2.5-72b-instructToolsJSON9.6 intel · $0.360/M · 24 t/s20.3%LCR
- 21qwen3-vl-8b-instructToolsJSONVision8.4 intel · $0.117/M · 42 t/s15.3%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 Qwen model reasons best over long inputs?
The best Qwen model for reasoning over long inputs is Qwen3.6 Max Preview, scoring 69.7% on long-context reasoning — a different question from how large a window it accepts. Qwen3.6 Plus (69.7%) and Qwen3.7 Max (69.0%) round out the top three.
What's a good alternative to Qwen3.6 Max Preview?
Qwen3.6 Plus (69.7%) is the closest alternative on this metric, followed by Qwen3.7 Max (69.0%). See the full ranking above for the tradeoffs.
How many Qwen models are there?
modelgrep tracks 49 Qwen models with live benchmarks, speed, latency and per-provider pricing, led on intelligence by Qwen3.7 Max. 21 of them qualify for this ranking.