Compare models
Pick up to 4models. Specs render side-by-side. Share the URL — it's stateless.
Comparing agents instead? Switch to agent compare →
OpenAI | OpenAI | OpenAI | ||
|---|---|---|---|---|
| Vendor | OpenAI | OpenAI | OpenAI | |
| Family | Gemini | GPT | o-series | GPT |
| Release date | 2026-04-22 | 2026-06-26 | 2025-04-16 | 2025-08-07 |
| Context window | 2,000,000 tokens | — | 200,000 tokens | 400,000 tokens |
| Parameters | — | — | — | — |
| Modality | text, vision, audio, video | text, vision, audio | text, vision | text, vision, audio |
| License | proprietary | proprietary | proprietary | proprietary |
| Source | proprietary | proprietary | proprietary | proprietary |
| Description | 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. | Flagship of OpenAI's GPT-5.6 three-model suite (Sol / Terra / Luna), released as a limited preview. Strong gains in coding, cybersecurity, biology, and long-horizon agentic work. Pricing: $5 / $30 per million input/output tokens. | Reasoning-focused model in the o-series. | Higher-reasoning variant of GPT-5, used for harder scientific and research tasks (e.g., immunology breakthroughs at NIH). Same 400K context as GPT-5; trades latency for depth. |
| Links | ||||
| Benchmarks | ||||
| MMLU-Pro | 87.1% | — | — | — |
| GPQA-D | 88.6% | — | 87.7% | — |
| HumanEval | 96.5% | — | — | — |
| Aider | 84.8% | — | — | — |
| AIME-25 | 92.8% | — | 88.9% | — |
| LiveCB | 76.1% | — | — | — |
| MMMU | 84.3% | — | — | — |
Add a model
Max 4 models. Remove one to add another.