TAAFT
Free mode
100% free
Freemium
Free Trial
Deals
Companies
Google DeepMind
Models
Gemma 2

Gemma 2

By Google DeepMind
Model family: Gemma
Text Gen 7
Released: June 27, 2024
💻Coding

About Google DeepMind

Company Size: 6000
Location: London, England, GB
Website: deepmind.com
View Company Profile

Benchmark scores

How Gemma 2 ranks on tracked AI benchmarks. Click any benchmark to see its full leaderboard.

DROP
Reasoning
52.0%
HumanEval
Coding
17.7%
MBPP
Coding
29.6%
GSM8K
Math
23.9%
MATH
Math
15.0%
MATH
Math
15.0%
ARC Challenge
Knowledge
554.0%
MMLU
Knowledge
51.3%
TriviaQA
Knowledge
59.4%
Compare across all benchmarks →

Other models from this family

View all models from this family

Tools using Gemma 2

Related Models

  • Gen 7
    BGE Reranker large
    BGE Reranker large is BAAI’s larger first-generation cross-encoder reranker for English and Chinese. Instead of producing embeddings, it scores a query-document pair directly, making it suitable for reranking top-k retrieval results with higher accuracy after a first-pass embedder search.
    🔍Information retrieval📂Content categorization
    Text
    Released 2y ago
  • Gen 3
    GPT 4.1
    GPT-4.1 is OpenAI’s flagship reasoning model in the GPT-4.1 family. It combines advanced reasoning, long-context support, multimodal input (text + images), and reliable JSON outputs, making it well suited for complex coding, math, analysis, and enterprise copilots.
    Text
    Released 1y ago
  • Gen 7
    1 Bit Bonsai 4B
    1-bit Bonsai 4B is PrismML’s mid-size ultra-efficient model designed for fast local inference. It uses just 0.57GB of memory and is positioned as a strong balance of speed, accuracy, and energy efficiency, with PrismML reporting throughput of 132 tokens per second on an M4 Pro for workloads that need both responsiveness and capable language performance.
    🧠AI inference🤖Ai deployment management💰Ai cost management
    NewText
    Released 2mo ago
Last updated: June 2, 2026
0 AIs selected
Clear selection
#
Name
Task