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

Grok 4×

Qwen3.6-27B×

Llama 4 Maverick×

Mistral Large 2×Clear all

	Grok 4 xAI	Qwen3.6-27B Alibaba	Llama 4 Maverick Meta	Mistral Large 2 Mistral
Vendor	xAI	Alibaba	Meta	Mistral
Family	Grok	Qwen	Llama	Mistral
Release date	2025-07-09	2026-04-22	2025-04-05	2024-07-24
Context window	256,000 tokens	262,144 tokens	1,000,000 tokens	128,000 tokens
Parameters	—	27B (dense)	400B	123B
Modality	text	text, vision, video	text, vision	text
License	proprietary	Apache-2.0	Llama 4 Community License	Mistral Research License
Source	proprietary	open weights	open weights	open weights
Description	—	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.	Mixture-of-experts open-weight model from Meta.	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.
Links	vendor →	weights →	weights →	vendor →weights →
Benchmarks
MMLU-Pro	82.8%	78.9%	80.5%	—
GPQA-D	87.5%	—	—	—
HumanEval	—	91.5%	—	89.0%
Aider	72.5%	70.2%	—	—
AIME-25	86.1%	—	—	—
LiveCB	65.3%	—	—	—
MMMU	—	70.3%	68.5%	—