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 235B×

Gemini Omni×

DeepSeek-V3.1×

Mistral Large 2×Clear all

	Qwen3 235B Alibaba	Gemini Omni Google	DeepSeek-V3.1 DeepSeek	Mistral Large 2 Mistral
Vendor	Alibaba	Google	DeepSeek	Mistral
Family	Qwen	Gemini	DeepSeek	Mistral
Release date	2025-04-29	2026-05-20	2025-08-21	2024-07-24
Context window	128,000 tokens	1,000,000 tokens	128,000 tokens	128,000 tokens
Parameters	235B	—	671B	123B
Modality	text	text, vision, audio, video	text	text
License	Apache-2.0	proprietary	MIT	Mistral Research License
Source	open weights	proprietary	open weights	open weights
Description	Predecessor to the Qwen3.6 family.	Multimodal Gemini variant introduced at Google I/O 2026 — unified text, image, audio, and video processing in a single model.	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.
Links	weights →	vendor →	weights →	vendor →weights →
Benchmarks
HumanEval	—	—	—	89.0%
MMMU	—	82.5%	—	—