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

Claude 4.7 Opus×

Mistral Large 2×

Qwen3 235B×

DeepSeek-V4-Flash×Clear all

	Claude 4.7 Opus Anthropic	Mistral Large 2 Mistral	Qwen3 235B Alibaba	DeepSeek-V4-Flash DeepSeek
Vendor	Anthropic	Mistral	Alibaba	DeepSeek
Family	Claude	Mistral	Qwen	DeepSeek
Release date	2026-04-16	2024-07-24	2025-04-29	2026-04-22
Context window	1,000,000 tokens	128,000 tokens	128,000 tokens	1,000,000 tokens
Parameters	—	123B	235B	284B (13B active)
Modality	text, vision	text	text	text
License	proprietary	Mistral Research License	Apache-2.0	MIT
Source	proprietary	open weights	open weights	open weights
Description	Anthropic's previous Opus flagship — superseded by Opus 4.8 on May 28, 2026 (42-day cycle). Optimized for complex reasoning and coding. Improved software engineering, long-running coding tasks, and higher-resolution vision over Claude 4.6.	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.	Predecessor to the Qwen3.6 family.	Smaller, faster sibling to DeepSeek-V4-Pro. Same 1M context window with a much lighter 284B / 13B-active MoE.
Links	vendor →	vendor →weights →	weights →	weights →
Benchmarks
MMLU-Pro	88.2%	—	—	—
GPQA-D	90.1%	—	—	—
HumanEval	97.4%	89.0%	—	—
Aider	91.2%	—	—	—
AIME-25	93.5%	—	—	—
LiveCB	80.2%	—	—	—
MMMU	79.0%	—	—	—