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×

o3×

Gemini 3.5×

Mistral Large 2×Clear all

	Qwen3.6-27B Alibaba	o3 OpenAI	Gemini 3.5 Google	Mistral Large 2 Mistral
Vendor	Alibaba	OpenAI	Google	Mistral
Family	Qwen	o-series	Gemini	Mistral
Release date	2026-04-22	2025-04-16	2026-05-20	2024-07-24
Context window	262,144 tokens	200,000 tokens	2,000,000 tokens	128,000 tokens
Parameters	27B (dense)	—	—	123B
Modality	text, vision, video	text, vision	text, vision, audio, video	text
License	Apache-2.0	proprietary	proprietary	Mistral Research License
Source	open weights	proprietary	proprietary	open weights
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.	Reasoning-focused model in the o-series.	Google DeepMind's next-gen Gemini — positioned as "frontier intelligence with action". Built for complex agentic workflows. Announced at Google I/O 2026.	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	78.9%	—	88.9%	—
GPQA-D	—	87.7%	91.2%	—
HumanEval	91.5%	—	—	89.0%
Aider	70.2%	—	—	—
AIME-25	—	88.9%	96.1%	—
MMMU	70.3%	—	86.0%	—