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×

o3×

DeepSeek-V4-Flash×

Mistral Large 2×Clear all

	Qwen3.7-Max Alibaba	o3 OpenAI	DeepSeek-V4-Flash DeepSeek	Mistral Large 2 Mistral
Vendor	Alibaba	OpenAI	DeepSeek	Mistral
Family	Qwen	o-series	DeepSeek	Mistral
Release date	2026-05-20	2025-04-16	2026-04-22	2024-07-24
Context window	1,000,000 tokens	200,000 tokens	1,000,000 tokens	128,000 tokens
Parameters	—	—	284B (13B active)	123B
Modality	text	text, vision	text	text
License	proprietary	proprietary	MIT	Mistral Research License
Source	proprietary	proprietary	open weights	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.	Reasoning-focused model in the o-series.	Smaller, faster sibling to DeepSeek-V4-Pro. Same 1M context window with a much lighter 284B / 13B-active MoE.	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 →	vendor →weights →
Benchmarks
MMLU-Pro	83.7%	—	—	—
GPQA-D	83.0%	87.7%	—	—
HumanEval	93.9%	—	—	89.0%
Aider	78.4%	—	—	—
AIME-25	90.4%	88.9%	—	—
LiveCB	71.0%	—	—	—