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×

DeepSeek-V4-Pro×

Gemini 3.5×

Claude 4.7 Opus×Clear all

	Qwen3 235B Alibaba	DeepSeek-V4-Pro DeepSeek	Gemini 3.5 Google	Claude 4.7 Opus Anthropic
Vendor	Alibaba	DeepSeek	Google	Anthropic
Family	Qwen	DeepSeek	Gemini	Claude
Release date	2025-04-29	2026-04-22	2026-05-20	2026-04-16
Context window	128,000 tokens	1,000,000 tokens	2,000,000 tokens	1,000,000 tokens
Parameters	235B	1.6T (49B active)	—	—
Modality	text	text	text, vision, audio, video	text, vision
License	Apache-2.0	MIT	proprietary	proprietary
Source	open weights	open weights	proprietary	proprietary
Description	Predecessor to the Qwen3.6 family.	DeepSeek's flagship open-weight MoE. 1.6T parameters with 49B activated, 1M-token context, and a hybrid attention scheme (CSA + HCA) that delivers long-context inference at ~27% of V3.2's FLOPs.	Google DeepMind's next-gen Gemini — positioned as "frontier intelligence with action". Built for complex agentic workflows. Announced at Google I/O 2026.	Anthropic's previous Opus flagship — superseded by Opus 4.8 on May 28, 2026 (42-day cycle).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 →	weights →	vendor →	vendor →
Benchmarks
MMLU-Pro	—	84.2%	88.9%	88.2%
GPQA-D	—	82.4%	91.2%	90.1%
HumanEval	—	95.1%	—	97.4%
Aider	—	80.1%	—	91.2%
AIME-25	—	88.6%	96.1%	93.5%
LiveCB	—	72.4%	—	80.2%
MMMU	—	—	86.0%	79.0%