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

Gemini 2.5 Flash×

Mistral Large 2×

Gemini Omni×

DeepSeek-V3.1×Clear all

	Gemini 2.5 Flash Google	Mistral Large 2 Mistral	Gemini Omni Google	DeepSeek-V3.1 DeepSeek
Vendor	Google	Mistral	Google	DeepSeek
Family	Gemini	Mistral	Gemini	DeepSeek
Release date	2025-06-17	2024-07-24	2026-05-20	2025-08-21
Context window	1,000,000 tokens	128,000 tokens	1,000,000 tokens	128,000 tokens
Parameters	—	123B	—	671B
Modality	text, vision, audio	text	text, vision, audio, video	text
License	proprietary	Mistral Research License	proprietary	MIT
Source	proprietary	open weights	proprietary	open weights
Description	Google's cost-and-latency-optimized Gemini 2.5 variant. Generally available June 2025 — designed for high-throughput agentic workflows with sub-second first-token latency.	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.	Multimodal Gemini variant introduced at Google I/O 2026 — unified text, image, audio, and video processing in a single model.	Large MoE open-weight model. Predecessor to DeepSeek-V4.
Links		vendor →weights →	vendor →	weights →
Benchmarks
HumanEval	—	89.0%	—	—
MMMU	—	—	82.5%	—