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-V4-Pro×

o3×

Gemini 3.5×Clear all

	Qwen3.7-Max Alibaba	DeepSeek-V4-Pro DeepSeek	o3 OpenAI	Gemini 3.5 Google
Vendor	Alibaba	DeepSeek	OpenAI	Google
Family	Qwen	DeepSeek	o-series	Gemini
Release date	2026-05-20	2026-04-22	2025-04-16	2026-05-20
Context window	1,000,000 tokens	1,000,000 tokens	200,000 tokens	2,000,000 tokens
Parameters	—	1.6T (49B active)	—	—
Modality	text	text	text, vision	text, vision, audio, video
License	proprietary	MIT	proprietary	proprietary
Source	proprietary	open weights	proprietary	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.	DeepSeek's flagship open-weight MoE. 1.6T parameters with 49B activated, 1M-token context, and a hybrid attention scheme (CSA + HCA) that delivers long-context inference at ~27% of V3.2's FLOPs.	Reasoning-focused model in the o-series.	Google DeepMind's next-gen Gemini — positioned as "frontier intelligence with action". Built for complex agentic workflows. Announced at Google I/O 2026.
Links	vendor →	weights →		vendor →
Benchmarks
MMLU-Pro	83.7%	84.2%	—	88.9%
GPQA-D	83.0%	82.4%	87.7%	91.2%
HumanEval	93.9%	95.1%	—	—
Aider	78.4%	80.1%	—	—
AIME-25	90.4%	88.6%	88.9%	96.1%
LiveCB	71.0%	72.4%	—	—
MMMU	—	—	—	86.0%