Compare models
Pick up to 4models. Specs render side-by-side. Share the URL — it's stateless.
Comparing agents instead? Switch to agent compare →
 Mistral Large 2Mistral |  Gemini 2.5 Pro |  Qwen3 235BAlibaba |  GPT-5.5OpenAI | |
|---|---|---|---|---|
| Vendor | Mistral | Alibaba | OpenAI | |
| Family | Mistral | Gemini | Qwen | GPT |
| Release date | 2024-07-24 | 2025-03-25 | 2025-04-29 | 2026-04-23 |
| Context window | 128,000 tokens | 2,000,000 tokens | 128,000 tokens | 400,000 tokens |
| Parameters | 123B | — | 235B | — |
| Modality | text | text, vision, audio, video | text | text, vision, audio |
| License | Mistral Research License | proprietary | Apache-2.0 | proprietary |
| Source | open weights | proprietary | open weights | proprietary |
| Description | Large text-only Mistral model with a 128K context window and 123B parameters, tuned for strong instruction following and long-context reasoning. Mistral's flagship open-weights release in the Large 2 line. | Predecessor to Gemini 3 Pro. | Predecessor to the Qwen3.6 family. | OpenAI's smartest and most intuitive model — successor to GPT-5, with major coding, research, and document workflow gains. GPT-5.5 Pro variant also available for heavier reasoning. |
| Links | ||||
| Benchmarks | ||||
| MMLU-Pro | — | 84.1% | — | 87.6% |
| GPQA-D | — | 84.0% | — | 89.4% |
| HumanEval | 89.0% | — | — | 96.8% |
| Aider | — | — | — | 89.7% |
| AIME-25 | — | — | — | 94.2% |
| LiveCB | — | — | — | 78.9% |
| MMMU | — | 72.4% | — | 78.4% |
Add a model
Claude 4.8 OpusmaxQwen3.7-MaxmaxGemini 3.5maxGemini OmnimaxGPT-5.5✓Qwen3.6-27Bmax
DeepSeek-V4-FlashmaxDeepSeek-V4-PromaxGemini 3 PromaxClaude 4.7 OpusmaxClaude 4.6 SonnetmaxClaude 4.5 HaikumaxDeepSeek-V3.1maxGPT-5max
Grok 4maxGemini 2.5 FlashmaxQwen3 235B✓o3maxGPT-4.1max
Llama 4 ScoutmaxLlama 4 MaverickmaxGemini 2.5 Pro✓DeepSeek-R1maxMistral Large 2✓Max 4 models. Remove one to add another.