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

DeepSeek-V3.1×

o3×

Mistral Large 2×

Claude 4.7 Opus×Clear all

	DeepSeek-V3.1 DeepSeek	o3 OpenAI	Mistral Large 2 Mistral	Claude 4.7 Opus Anthropic
Vendor	DeepSeek	OpenAI	Mistral	Anthropic
Family	DeepSeek	o-series	Mistral	Claude
Release date	2025-08-21	2025-04-16	2024-07-24	2026-04-16
Context window	128,000 tokens	200,000 tokens	128,000 tokens	1,000,000 tokens
Parameters	671B	—	123B	—
Modality	text	text, vision	text	text, vision
License	MIT	proprietary	Mistral Research License	proprietary
Source	open weights	proprietary	open weights	proprietary
Description	Large MoE open-weight model. Predecessor to DeepSeek-V4.	Reasoning-focused model in the o-series.	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.	Anthropic's previous Opus flagship — superseded by Opus 4.8 on May 28, 2026 (42-day cycle).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.
Links	weights →		vendor →weights →	vendor →
Benchmarks
MMLU-Pro	—	—	—	88.2%
GPQA-D	—	87.7%	—	90.1%
HumanEval	—	—	89.0%	97.4%
Aider	—	—	—	91.2%
AIME-25	—	88.9%	—	93.5%
LiveCB	—	—	—	80.2%
MMMU	—	—	—	79.0%