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

o3×

Qwen3.7-Max×

Claude 4.7 Opus×

Llama 4 Maverick×Clear all

	o3 OpenAI	Qwen3.7-Max Alibaba	Claude 4.7 Opus Anthropic	Llama 4 Maverick Meta
Vendor	OpenAI	Alibaba	Anthropic	Meta
Family	o-series	Qwen	Claude	Llama
Release date	2025-04-16	2026-05-20	2026-04-16	2025-04-05
Context window	200,000 tokens	1,000,000 tokens	1,000,000 tokens	1,000,000 tokens
Parameters	—	—	—	400B
Modality	text, vision	text	text, vision	text, vision
License	proprietary	proprietary	proprietary	Llama 4 Community License
Source	proprietary	proprietary	proprietary	open weights
Description	Reasoning-focused model in the o-series.	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	Anthropic's previous Opus flagship — superseded by Opus 4.8 on May 28, 2026 (42-day cycle).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.	Mixture-of-experts open-weight model from Meta.
Links		vendor →	vendor →	weights →
Benchmarks
MMLU-Pro	—	83.7%	88.2%	80.5%
GPQA-D	87.7%	83.0%	90.1%	—
HumanEval	—	93.9%	97.4%	—
Aider	—	78.4%	91.2%	—
AIME-25	88.9%	90.4%	93.5%	—
LiveCB	—	71.0%	80.2%	—
MMMU	—	—	79.0%	68.5%