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

Gemini 3.5×

Claude 4.6 Sonnet×

Claude 4.7 Opus×

	Gemini 3.5 Google	Claude 4.6 Sonnet Anthropic	Claude 4.7 Opus Anthropic	o3 OpenAI
Vendor	Google	Anthropic	Anthropic	OpenAI
Family	Gemini	Claude	Claude	o-series
Release date	2026-05-20	2026-02-17	2026-04-16	2025-04-16
Context window	2,000,000 tokens	1,000,000 tokens	1,000,000 tokens	200,000 tokens
Parameters	—	—	—	—
Modality	text, vision, audio, video	text, vision	text, vision	text, vision
License	proprietary	proprietary	proprietary	proprietary
Source	proprietary	proprietary	proprietary	proprietary
Description	Google DeepMind's next-gen Gemini — positioned as "frontier intelligence with action". Built for complex agentic workflows. Announced at Google I/O 2026.	Anthropic's mid-tier flagship — released 12 days after Opus 4.6 and matching most of its capabilities at ~40% the API cost ($3/$15 per 1M tokens). 1M-token context.	Anthropic's previous Opus flagship — superseded by Opus 4.8 on May 28, 2026 (42-day cycle).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.	Reasoning-focused model in the o-series.
Links	vendor →		vendor →
Benchmarks
MMLU-Pro	88.9%	85.4%	88.2%	—
GPQA-D	91.2%	85.8%	90.1%	87.7%
HumanEval	—	95.9%	97.4%	—
Aider	—	83.6%	91.2%	—
AIME-25	96.1%	87.4%	93.5%	88.9%
LiveCB	—	73.8%	80.2%	—
MMMU	86.0%	—	79.0%	—