Beta
Home/Comparer/Qwen3.6 Plus vs GPT-5.1-Codex

Qwen3.6 Plus vs GPT-5.1-Codex

Côte à côte. Chaque métrique. Chaque benchmark.

Alibaba Qwen
70.9
score moyen
6/8
benchmarks
OpenAI
68.6
score moyen
2/8
benchmarks
TypeQwen3.6 PlusGPT-5.1-Codex
ProviderAlibaba Qwen logoAlibaba QwenOpenAI logoOpenAI
score moyen70.968.6
Prix d'entrée$0.33$1.25
Prix de sortie$1.95$10.00
Fenêtre de contexte1.0M tokens (~500 books)400K tokens (~200 books)
Sorti le2026-04-022025-11-13
Code source ouvertOpen SourceProprietary

8 benchmarks · Qwen3.6 Plus: 6, GPT-5.1-Codex: 2

BenchmarkCatégorieQwen3.6 PlusGPT-5.1-Codex
LiveBench — Agentic Codingcoding55.053.3
LiveBench — Codingcoding78.271.8
LiveBench — Data Analysisreasoning69.960.8
LiveBench — Iflanguage58.363.4
LiveBench — Languagelanguage75.069.5
LiveBench — Mathematicsmath83.779.6
LiveBench — Overallknowledge70.868.6
LiveBench — Reasoningreasoning75.882.0