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×

Qwen3.6-27B×

GPT-5.6 Sol×

Claude 4.7 Opus×Clear all

	o3 OpenAI	Qwen3.6-27B Alibaba	GPT-5.6 Sol OpenAI	Claude 4.7 Opus Anthropic
Vendor	OpenAI	Alibaba	OpenAI	Anthropic
Family	o-series	Qwen	GPT	Claude
Release date	2025-04-16	2026-04-22	2026-06-26	2026-04-16
Context window	200,000 tokens	262,144 tokens	—	1,000,000 tokens
Parameters	—	27B (dense)	—	—
Modality	text, vision	text, vision, video	text, vision, audio	text, vision
License	proprietary	Apache-2.0	proprietary	proprietary
Source	proprietary	open weights	proprietary	proprietary
Description	Reasoning-focused model in the o-series.	Alibaba's first dense open-weight in the 3.6 family. Strong agentic-coding scores (77.2 SWE-bench Verified, matching Claude 4.5 Opus on Terminal-Bench 2.0). Supports 201 languages and multimodal text/image/video input.	Flagship of OpenAI's GPT-5.6 three-model suite (Sol / Terra / Luna), released as a limited preview. Strong gains in coding, cybersecurity, biology, and long-horizon agentic work. Pricing: $5 / $30 per million input/output 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	Anthropic's previous Opus flagship — superseded by Opus 4.8 on May 28, 2026 (42-day cycle).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		weights →	vendor →	vendor →
Benchmarks
MMLU-Pro	—	78.9%	—	88.2%
GPQA-D	87.7%	—	—	90.1%
HumanEval	—	91.5%	—	97.4%
Aider	—	70.2%	—	91.2%
AIME-25	88.9%	—	—	93.5%
LiveCB	—	—	—	80.2%
MMMU	—	70.3%	—	79.0%