Updated daily at 05:00 UTC
Models
AI models
1521 current models, newest first. Each links to its benchmark results, with who ran them.
Best by specialty
Independent and third-party results only · method category-2026-09-29.1
All current models
Best for
- Knowledge & reasoning
- Scientific reasoning
- Mathematics
- Coding & software engineering
- Agentic tool use
- Computer & browser use
- Professional knowledge work
- Long context
- Vision & multimodal understanding
- OCR & documents
- Law
- Medicine & health
- Finance
- Multilingual
- Factuality & hallucination
- Instruction following
- Writing
- Speech & audio
- Human preference
Kind· Language
Maker· Google DeepMind
Context
Input price
Weights· Open weights
Reasoning
- FunctionGemma 270MGoogle DeepMind · 18 Dec 2025 · 32.8K context—in / 1M
- T5Gemma 2 (270M-270M, 1B-1B, 4B-4B)Google DeepMind · 18 Dec 2025 · — context—in / 1M
- VaultGemma 1BGoogle DeepMind · 13 Sep 2025 · — context—in / 1M
- T5Gemma (all sizes)Google DeepMind · 9 Jul 2025 · — context—in / 1M
- TxGemma 27BGoogle DeepMind · 25 Mar 2025 · — context—in / 1M
- TxGemma 2BGoogle DeepMind · 25 Mar 2025 · — context—in / 1M
- TxGemma 9BGoogle DeepMind · 25 Mar 2025 · — context—in / 1M
- ShieldGemma 2 4BGoogle DeepMind · 10 Mar 2025 · — context—in / 1M
- Gemma-APS 2BGoogle DeepMind · 15 Oct 2024 · — context—in / 1M
- Gemma-APS 7BGoogle DeepMind · 15 Oct 2024 · — context—in / 1M
- DataGemma RAG 27BGoogle DeepMind · 12 Sep 2024 · — context—in / 1M
- DataGemma RIG 27BGoogle DeepMind · 12 Sep 2024 · — context—in / 1M
- ShieldGemma 27BGoogle DeepMind · 31 Jul 2024 · — context—in / 1M
- ShieldGemma 2BGoogle DeepMind · 31 Jul 2024 · — context—in / 1M
- ShieldGemma 9BGoogle DeepMind · 31 Jul 2024 · — context—in / 1M
- RecurrentGemma 9BGoogle DeepMind · 11 Jun 2024 · — context—in / 1M
- RecurrentGemma 2BGoogle DeepMind · 9 Apr 2024 · — context—in / 1M