Back to all models
G

Gemini 2.0 Flash

GoogleReleased 2024-12-11
Official Page

Google's fastest and most capable model with native multimodality, extreme context window, and built-in function calling for agents.

Overall Score
80%
Cost Efficiency
100
Context Window
1.0M

Strengths

  • ✓Extremely fast and cheap
  • ✓1M token context window
  • ✓Native multimodal
  • ✓Strong agent capabilities

Weaknesses

  • ✗Not as smart as top-tier models
  • ✗Smaller context benefit in practice
Architecture
Transformer (MoE)
Parameters
Unknown
Input
$0.1/M
Output
$0.4/M

Benchmark Performance

BenchmarkDescriptionScoreCategoryBar
MMLUMassive Multitask Language Understanding86.5%knowledge
HumanEvalCode generation accuracy89.7%coding
MATHMathematical reasoning90%math
GSM8KGrade school math92%math
GPQAGraduate-level science Q&A58%reasoning
HellaSwagCommon sense reasoning87.8%reasoning
SWE-benchSoftware engineering problems41.1%coding
ARC-CAI2 Reasoning Challenge96%reasoning
AI
ModelBench

The open benchmark platform for comparing the latest AI models and their capabilities.

Platform

  • Compare Models
  • All Models
  • Methodology

AI Labs

  • OpenAI
  • Anthropic
  • Google DeepMind
  • Meta AI

Resources

  • Documentation
  • Benchmark Guide
  • API Reference
Benchmarks are sourced from official model cards and independent evaluations. Data is for informational purposes only.
© 2026 ModelBench. Built for the AI community.