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 4.8 Opus×

o3×

Qwen3.6-27B×

GPT-5×Clear all

	Claude 4.8 Opus Anthropic	o3 OpenAI	Qwen3.6-27B Alibaba	GPT-5 OpenAI
Vendor	Anthropic	OpenAI	Alibaba	OpenAI
Family	Claude	o-series	Qwen	GPT
Release date	2026-05-28	2025-04-16	2026-04-22	2025-08-07
Context window	1,000,000 tokens	200,000 tokens	262,144 tokens	400,000 tokens
Parameters	—	—	27B (dense)	—
Modality	text, vision	text, vision	text, vision, video	text, vision, audio
License	proprietary	proprietary	Apache-2.0	proprietary
Source	proprietary	proprietary	open weights	proprietary
Description	Anthropic's flagship hybrid-reasoning model — Opus 4.8 pushes coding and AI-agent workflows further (agentic coding 69.2% vs 64.3% on 4.7; multidisciplinary reasoning 57.9% vs 54.7%). 1M-token context, $5/$25 per MTok pricing held flat from Opus 4.7. Introduces Dynamic Workflows for Claude Code (research preview). GA on Anthropic API (`claude-opus-4-8`), AWS Bedrock, Google Vertex, Microsoft Foundry, and GitHub Copilot.	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.	OpenAI's flagship general-purpose model. Superseded by GPT-5.5 in April 2026.
Links	vendor →		weights →	vendor →
Benchmarks
MMLU-Pro	—	—	78.9%	85.1%
GPQA-D	—	87.7%	—	87.3%
HumanEval	—	—	91.5%	95.2%
Aider	—	—	70.2%	85.4%
AIME-25	—	88.9%	—	91.0%
LiveCB	—	—	—	74.5%
MMMU	—	—	70.3%	74.1%