Compare models

Pick up to 4models. Specs render side-by-side. Share the URL — it's stateless.

Comparing agents instead? Switch to agent compare →

Selected

GPT-5.5×

Claude 4.7 Opus×

Gemini 3.5×

Qwen3 235B×Clear all

	GPT-5.5 OpenAI	Claude 4.7 Opus Anthropic	Gemini 3.5 Google	Qwen3 235B Alibaba
Vendor	OpenAI	Anthropic	Google	Alibaba
Family	GPT	Claude	Gemini	Qwen
Release date	2026-04-23	2026-04-16	2026-05-20	2025-04-29
Context window	400,000 tokens	1,000,000 tokens	2,000,000 tokens	128,000 tokens
Parameters	—	—	—	235B
Modality	text, vision, audio	text, vision	text, vision, audio, video	text
License	proprietary	proprietary	proprietary	Apache-2.0
Source	proprietary	proprietary	proprietary	open weights
Description	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.	Anthropic's previous Opus flagship — superseded by Opus 4.8 on May 28, 2026 (42-day cycle). Optimized for complex reasoning and coding. Improved software engineering, long-running coding tasks, and higher-resolution vision over Claude 4.6.	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.
Links	vendor →	vendor →	vendor →	weights →
Benchmarks
MMLU-Pro	87.6%	88.2%	88.9%	—
GPQA-D	89.4%	90.1%	91.2%	—
HumanEval	96.8%	97.4%	—	—
Aider	89.7%	91.2%	—	—
AIME-25	94.2%	93.5%	96.1%	—
LiveCB	78.9%	80.2%	—	—
MMMU	78.4%	79.0%	86.0%	—