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

Qwen3.6-27B×

Gemini 3.5×

DeepSeek-R1×

Claude 4.8 Opus×Clear all

	Qwen3.6-27B Alibaba	Gemini 3.5 Google	DeepSeek-R1 DeepSeek	Claude 4.8 Opus Anthropic
Vendor	Alibaba	Google	DeepSeek	Anthropic
Family	Qwen	Gemini	DeepSeek	Claude
Release date	2026-04-22	2026-05-20	2025-01-20	2026-05-28
Context window	262,144 tokens	2,000,000 tokens	128,000 tokens	1,000,000 tokens
Parameters	27B (dense)	—	671B	—
Modality	text, vision, video	text, vision, audio, video	text	text, vision
License	Apache-2.0	proprietary	MIT	proprietary
Source	open weights	proprietary	open weights	proprietary
Description	Alibaba's first dense open-weight in the 3.6 family. Strong agentic-coding scores (77.2 SWE-bench Verified, matching Claude 4.5 Opus on Terminal-Bench 2.0). Supports 201 languages and multimodal text/image/video input.	Google DeepMind's next-gen Gemini — positioned as "frontier intelligence with action". Built for complex agentic workflows. Announced at Google I/O 2026.	Reasoning-focused open-weight model.	Anthropic's flagship hybrid-reasoning model — Opus 4.8 pushes coding and AI-agent workflows further (agentic coding 69.2% vs 64.3% on 4.7; multidisciplinary reasoning 57.9% vs 54.7%). 1M-token context, $5/$25 per MTok pricing held flat from Opus 4.7. Introduces Dynamic Workflows for Claude Code (research preview). GA on Anthropic API (`claude-opus-4-8`), AWS Bedrock, Google Vertex, Microsoft Foundry, and GitHub Copilot.
Links	weights →	vendor →	weights →	vendor →
Benchmarks
MMLU-Pro	78.9%	88.9%	—	—
GPQA-D	—	91.2%	—	—
HumanEval	91.5%	—	—	—
Aider	70.2%	—	—	—
AIME-25	—	96.1%	79.8%	—
MMMU	70.3%	86.0%	—	—