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

Claude 4.6 Sonnet×

Qwen3.7-Max×

Grok 4×

GPT-5.5×Clear all

	Claude 4.6 Sonnet Anthropic	Qwen3.7-Max Alibaba	Grok 4 xAI	GPT-5.5 OpenAI
Vendor	Anthropic	Alibaba	xAI	OpenAI
Family	Claude	Qwen	Grok	GPT
Release date	2026-02-17	2026-05-20	2025-07-09	2026-04-23
Context window	1,000,000 tokens	1,000,000 tokens	256,000 tokens	400,000 tokens
Parameters	—	—	—	—
Modality	text, vision	text	text	text, vision, audio
License	proprietary	proprietary	proprietary	proprietary
Source	proprietary	proprietary	proprietary	proprietary
Description	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.	Alibaba's flagship agent model — 1M-token context, extended-thinking mode, 56.6 on the Artificial Analysis Intelligence Index v4.0 (5th overall, #1 Chinese). 50.8% on Terminal-Bench Hard. Designed for long-horizon agent workloads (hundreds-to-thousands of steps). Closed-weight, $2.50/$7.50 per 1M tokens.	—	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.
Links		vendor →	vendor →	vendor →
Benchmarks
MMLU-Pro	85.4%	83.7%	82.8%	87.6%
GPQA-D	85.8%	83.0%	87.5%	89.4%
HumanEval	95.9%	93.9%	—	96.8%
Aider	83.6%	78.4%	72.5%	89.7%
AIME-25	87.4%	90.4%	86.1%	94.2%
LiveCB	73.8%	71.0%	65.3%	78.9%
MMMU	—	—	—	78.4%