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×

Qwen3.6-27B×

Mistral Large 2×

	Claude 4.6 Sonnet Anthropic	Qwen3.6-27B Alibaba	Mistral Large 2 Mistral	o3 OpenAI
Vendor	Anthropic	Alibaba	Mistral	OpenAI
Family	Claude	Qwen	Mistral	o-series
Release date	2026-02-17	2026-04-22	2024-07-24	2025-04-16
Context window	1,000,000 tokens	262,144 tokens	128,000 tokens	200,000 tokens
Parameters	—	27B (dense)	123B	—
Modality	text, vision	text, vision, video	text	text, vision
License	proprietary	Apache-2.0	Mistral Research License	proprietary
Source	proprietary	open weights	open weights	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 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.	Large text-only Mistral model with a 128K context window and 123B parameters, tuned for strong instruction following and long-context reasoning. Mistral's flagship open-weights release in the Large 2 line.	Reasoning-focused model in the o-series.
Links		weights →	vendor →weights →
Benchmarks
MMLU-Pro	85.4%	78.9%	—	—
GPQA-D	85.8%	—	—	87.7%
HumanEval	95.9%	91.5%	89.0%	—
Aider	83.6%	70.2%	—	—
AIME-25	87.4%	—	—	88.9%
LiveCB	73.8%	—	—	—
MMMU	—	70.3%	—	—