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×

Mistral Large 2×

Gemini 3 Pro×

Llama 4 Maverick×Clear all

	Qwen3.7-Max Alibaba	Mistral Large 2 Mistral	Gemini 3 Pro Google	Llama 4 Maverick Meta
Vendor	Alibaba	Mistral	Google	Meta
Family	Qwen	Mistral	Gemini	Llama
Release date	2026-05-20	2024-07-24	2026-04-22	2025-04-05
Context window	1,000,000 tokens	128,000 tokens	2,000,000 tokens	1,000,000 tokens
Parameters	—	123B	—	400B
Modality	text	text	text, vision, audio, video	text, vision
License	proprietary	Mistral Research License	proprietary	Llama 4 Community License
Source	proprietary	open weights	proprietary	open weights
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.	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.	Google DeepMind's flagship multimodal model. Best-in-class for multimodal understanding and agentic / vibe coding workflows. A "Deep Think" reasoning mode is available to AI Ultra subscribers.	Mixture-of-experts open-weight model from Meta.
Links	vendor →	vendor →weights →	vendor →	weights →
Benchmarks
MMLU-Pro	83.7%	—	87.1%	80.5%
GPQA-D	83.0%	—	88.6%	—
HumanEval	93.9%	89.0%	96.5%	—
Aider	78.4%	—	84.8%	—
AIME-25	90.4%	—	92.8%	—
LiveCB	71.0%	—	76.1%	—
MMMU	—	—	84.3%	68.5%