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×

Qwen3.7-Max×

Grok 4×

Claude 4.7 Opus×Clear all

	GPT-5 OpenAI	Qwen3.7-Max Alibaba	Grok 4 xAI	Claude 4.7 Opus Anthropic
Vendor	OpenAI	Alibaba	xAI	Anthropic
Family	GPT	Qwen	Grok	Claude
Release date	2025-08-07	2026-05-20	2025-07-09	2026-04-16
Context window	400,000 tokens	1,000,000 tokens	256,000 tokens	1,000,000 tokens
Parameters	—	—	—	—
Modality	text, vision, audio	text	text	text, vision
License	proprietary	proprietary	proprietary	proprietary
Source	proprietary	proprietary	proprietary	proprietary
Description	OpenAI's flagship general-purpose model. Superseded by GPT-5.5 in April 2026.	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.	—	Anthropic's previous Opus flagship — superseded by Opus 4.8 on May 28, 2026 (42-day cycle).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.
Links	vendor →	vendor →	vendor →	vendor →
Benchmarks
MMLU-Pro	85.1%	83.7%	82.8%	88.2%
GPQA-D	87.3%	83.0%	87.5%	90.1%
HumanEval	95.2%	93.9%	—	97.4%
Aider	85.4%	78.4%	72.5%	91.2%
AIME-25	91.0%	90.4%	86.1%	93.5%
LiveCB	74.5%	71.0%	65.3%	80.2%
MMMU	74.1%	—	—	79.0%