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

GPT-5×

Gemini 3 Pro×

Qwen3.7-Max×

Qwen3 235B×Clear all

	GPT-5 OpenAI	Gemini 3 Pro Google	Qwen3.7-Max Alibaba	Qwen3 235B Alibaba
Vendor	OpenAI	Google	Alibaba	Alibaba
Family	GPT	Gemini	Qwen	Qwen
Release date	2025-08-07	2026-04-22	2026-05-20	2025-04-29
Context window	400,000 tokens	2,000,000 tokens	1,000,000 tokens	128,000 tokens
Parameters	—	—	—	235B
Modality	text, vision, audio	text, vision, audio, video	text	text
License	proprietary	proprietary	proprietary	Apache-2.0
Source	proprietary	proprietary	proprietary	open weights
Description	OpenAI's flagship general-purpose model. Superseded by GPT-5.5 in April 2026.	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.	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.	Predecessor to the Qwen3.6 family.
Links	vendor →	vendor →	vendor →	weights →
Benchmarks
MMLU-Pro	85.1%	87.1%	83.7%	—
GPQA-D	87.3%	88.6%	83.0%	—
HumanEval	95.2%	96.5%	93.9%	—
Aider	85.4%	84.8%	78.4%	—
AIME-25	91.0%	92.8%	90.4%	—
LiveCB	74.5%	76.1%	71.0%	—
MMMU	74.1%	84.3%	—	—