Compare models
Pick up to 4models. Specs render side-by-side. Share the URL — it's stateless.
Comparing agents instead? Switch to agent compare →
 o3OpenAI |  Gemini 3.5 |  Qwen3 235BAlibaba |  Mistral Large 2Mistral | |
|---|---|---|---|---|
| Vendor | OpenAI | Alibaba | Mistral | |
| Family | o-series | Gemini | Qwen | Mistral |
| Release date | 2025-04-16 | 2026-05-20 | 2025-04-29 | 2024-07-24 |
| Context window | 200,000 tokens | 2,000,000 tokens | 128,000 tokens | 128,000 tokens |
| Parameters | — | — | 235B | 123B |
| Modality | text, vision | text, vision, audio, video | text | text |
| License | proprietary | proprietary | Apache-2.0 | Mistral Research License |
| Source | proprietary | proprietary | open weights | open weights |
| Description | Reasoning-focused model in the o-series. | Google DeepMind's next-gen Gemini — positioned as "frontier intelligence with action". Built for complex agentic workflows. Announced at Google I/O 2026. | Predecessor to the Qwen3.6 family. | 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. |
| Links | ||||
| Benchmarks | ||||
| MMLU-Pro | — | 88.9% | — | — |
| GPQA-D | 87.7% | 91.2% | — | — |
| HumanEval | — | — | — | 89.0% |
| AIME-25 | 88.9% | 96.1% | — | — |
| MMMU | — | 86.0% | — | — |
Add a model
Claude 4.8 OpusmaxQwen3.7-MaxmaxGemini 3.5✓Gemini OmnimaxGPT-5.5maxQwen3.6-27Bmax
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✓o3✓GPT-4.1max
Llama 4 ScoutmaxLlama 4 MaverickmaxGemini 2.5 PromaxDeepSeek-R1maxMistral Large 2✓Max 4 models. Remove one to add another.