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

Qwen3.6-27B×

GPT-5.6 Sol×

o3×

DeepSeek-V4-Flash×Clear all

	Qwen3.6-27B Alibaba	GPT-5.6 Sol OpenAI	o3 OpenAI	DeepSeek-V4-Flash DeepSeek
Vendor	Alibaba	OpenAI	OpenAI	DeepSeek
Family	Qwen	GPT	o-series	DeepSeek
Release date	2026-04-22	2026-06-26	2025-04-16	2026-04-22
Context window	262,144 tokens	—	200,000 tokens	1,000,000 tokens
Parameters	27B (dense)	—	—	284B (13B active)
Modality	text, vision, video	text, vision, audio	text, vision	text
License	Apache-2.0	proprietary	proprietary	MIT
Source	open weights	proprietary	proprietary	open weights
Description	Alibaba's first dense open-weight in the 3.6 family. Strong agentic-coding scores (77.2 SWE-bench Verified, matching Claude 4.5 Opus on Terminal-Bench 2.0). Supports 201 languages and multimodal text/image/video input.	Flagship of OpenAI's GPT-5.6 three-model suite (Sol / Terra / Luna), released as a limited preview. Strong gains in coding, cybersecurity, biology, and long-horizon agentic work. Pricing: $5 / $30 per million input/output 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.
Links	weights →	vendor →		weights →
Benchmarks
MMLU-Pro	78.9%	—	—	—
GPQA-D	—	—	87.7%	—
HumanEval	91.5%	—	—	—
Aider	70.2%	—	—	—
AIME-25	—	—	88.9%	—
MMMU	70.3%	—	—	—