Compare models
Pick up to 4models. Specs render side-by-side. Share the URL — it's stateless.
Comparing agents instead? Switch to agent compare →
 Qwen3 235BAlibaba |  Gemini 3 Pro |  Mistral Large 2Mistral |  Llama 4 MaverickMeta | |
|---|---|---|---|---|
| Vendor | Alibaba | Mistral | Meta | |
| Family | Qwen | Gemini | Mistral | Llama |
| Release date | 2025-04-29 | 2026-04-22 | 2024-07-24 | 2025-04-05 |
| Context window | 128,000 tokens | 2,000,000 tokens | 128,000 tokens | 1,000,000 tokens |
| Parameters | 235B | — | 123B | 400B |
| Modality | text | text, vision, audio, video | text | text, vision |
| License | Apache-2.0 | proprietary | Mistral Research License | Llama 4 Community License |
| Source | open weights | proprietary | open weights | open weights |
| Description | Predecessor to the Qwen3.6 family. | Google DeepMind's flagship multimodal model. Best-in-class for multimodal understanding and agentic / vibe coding workflows. A "Deep Think" reasoning mode is available to AI Ultra subscribers. | 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. | Mixture-of-experts open-weight model from Meta. |
| Links | ||||
| Benchmarks | ||||
| MMLU-Pro | — | 87.1% | — | 80.5% |
| GPQA-D | — | 88.6% | — | — |
| HumanEval | — | 96.5% | 89.0% | — |
| Aider | — | 84.8% | — | — |
| AIME-25 | — | 92.8% | — | — |
| LiveCB | — | 76.1% | — | — |
| MMMU | — | 84.3% | — | 68.5% |
Add a model
Claude 4.8 OpusmaxQwen3.7-MaxmaxGemini 3.5maxGemini Omnimax
GPT-5.5maxQwen3.6-27Bmax
DeepSeek-V4-FlashmaxDeepSeek-V4-PromaxGemini 3 Pro✓Claude 4.7 OpusmaxClaude 4.6 SonnetmaxClaude 4.5 HaikumaxDeepSeek-V3.1maxGPT-5max
Grok 4maxGemini 2.5 FlashmaxQwen3 235B✓o3maxGPT-4.1maxLlama 4 ScoutmaxLlama 4 Maverick✓Gemini 2.5 PromaxDeepSeek-R1maxMistral Large 2✓Max 4 models. Remove one to add another.