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 3 Pro×

Claude 4.6 Sonnet×

Mistral Large 2×Clear all

	Qwen3 235B Alibaba	Gemini 3 Pro Google	Claude 4.6 Sonnet Anthropic	Mistral Large 2 Mistral
Vendor	Alibaba	Google	Anthropic	Mistral
Family	Qwen	Gemini	Claude	Mistral
Release date	2025-04-29	2026-04-22	2026-02-17	2024-07-24
Context window	128,000 tokens	2,000,000 tokens	1,000,000 tokens	128,000 tokens
Parameters	235B	—	—	123B
Modality	text	text, vision, audio, video	text, vision	text
License	Apache-2.0	proprietary	proprietary	Mistral Research License
Source	open weights	proprietary	proprietary	open weights
Description	Predecessor to the Qwen3.6 family.	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.	Anthropic's mid-tier flagship — released 12 days after Opus 4.6 and matching most of its capabilities at ~40% the API cost ($3/$15 per 1M tokens). 1M-token context.	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 →		vendor →weights →
Benchmarks
MMLU-Pro	—	87.1%	85.4%	—
GPQA-D	—	88.6%	85.8%	—
HumanEval	—	96.5%	95.9%	89.0%
Aider	—	84.8%	83.6%	—
AIME-25	—	92.8%	87.4%	—
LiveCB	—	76.1%	73.8%	—
MMMU	—	84.3%	—	—