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

Qwen3.7-Max×

Llama 4 Maverick×

Mistral Large 2×

	Qwen3.7-Max Alibaba	Llama 4 Maverick Meta	Mistral Large 2 Mistral	o3 OpenAI
Vendor	Alibaba	Meta	Mistral	OpenAI
Family	Qwen	Llama	Mistral	o-series
Release date	2026-05-20	2025-04-05	2024-07-24	2025-04-16
Context window	1,000,000 tokens	1,000,000 tokens	128,000 tokens	200,000 tokens
Parameters	—	400B	123B	—
Modality	text	text, vision	text	text, vision
License	proprietary	Llama 4 Community License	Mistral Research License	proprietary
Source	proprietary	open weights	open weights	proprietary
Description	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.	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.	Reasoning-focused model in the o-series.
Links	vendor →	weights →	vendor →weights →
Benchmarks
MMLU-Pro	83.7%	80.5%	—	—
GPQA-D	83.0%	—	—	87.7%
HumanEval	93.9%	—	89.0%	—
Aider	78.4%	—	—	—
AIME-25	90.4%	—	—	88.9%
LiveCB	71.0%	—	—	—
MMMU	—	68.5%	—	—