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×

DeepSeek-V3.1×

Mistral Large 2×

GPT-5×Clear all

	Qwen3.7-Max Alibaba	DeepSeek-V3.1 DeepSeek	Mistral Large 2 Mistral	GPT-5 OpenAI
Vendor	Alibaba	DeepSeek	Mistral	OpenAI
Family	Qwen	DeepSeek	Mistral	GPT
Release date	2026-05-20	2025-08-21	2024-07-24	2025-08-07
Context window	1,000,000 tokens	128,000 tokens	128,000 tokens	400,000 tokens
Parameters	—	671B	123B	—
Modality	text	text	text	text, vision, audio
License	proprietary	MIT	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.	Large MoE open-weight model. Predecessor to DeepSeek-V4.	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.	OpenAI's flagship general-purpose model. Superseded by GPT-5.5 in April 2026.
Links	vendor →	weights →	vendor →weights →	vendor →
Benchmarks
MMLU-Pro	83.7%	—	—	85.1%
GPQA-D	83.0%	—	—	87.3%
HumanEval	93.9%	—	89.0%	95.2%
Aider	78.4%	—	—	85.4%
AIME-25	90.4%	—	—	91.0%
LiveCB	71.0%	—	—	74.5%
MMMU	—	—	—	74.1%