Compare AI models
| Specifications | ||
Context windowHow much information the model can work with in one request, measured in tokens — pieces of words or other data. This includes your question, attachments, conversation and reply. Limits can vary by model variant and provider. | 400k | 32k |
| These models have no shared benchmark scores. | ||
LiveCodeBenchCompetitive coding — Coding problems published so recently the AI can't have seen them in training — a contamination-free test of raw programming skill. Higher is better. | — | 38.7% |
| Overview | ||
| Company | OpenAI | Qwen |
| Release date | Nov 13 2025 | Jan 28 2025 |
| Access | Closed | Closed |
| Model details | View model | View model |
Other comparisons
GPT-5.1-Codex-MinivsClaude Fable 5.2Qwen2.5-MaxvsClaude Fable 5.2GPT-5.1-Codex-MinivsGemini 4 CarbonQwen2.5-MaxvsGemini 4 CarbonGPT-5.1-Codex-MinivsMuse EmberQwen2.5-MaxvsMuse EmberGPT-5.1-Codex-MinivsGrok 4.7Qwen2.5-MaxvsGrok 4.7GPT-5.1-Codex-MinivsDeepSeek-V4.1-Flash-1017Qwen2.5-MaxvsDeepSeek-V4.1-Flash-1017GPT-5.1-Codex-MinivsMistral Large 4Qwen2.5-MaxvsMistral Large 4Frequently asked questions
GPT-5.1-Codex-Mini and Qwen2.5-Max don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Qwen2.5-Max shipped 289 days before GPT-5.1-Codex-Mini, so benchmark comparisons should account for the intervening progress.
Context windows are 400k (GPT-5.1-Codex-Mini) vs 32k (Qwen2.5-Max).
Direct benchmark comparisons are unavailable — GPT-5.1-Codex-Mini and Qwen2.5-Max don't publish scores on any of the same benchmarks.