Back to all models
G

Gemini 1.5 Pro

GoogleReleased 2024-02-15
Official Page

Google's most capable model with a massive 2M token context window, enabling processing of entire codebases, books, and videos.

Overall Score
81%
Cost Efficiency
100
Context Window
2.0M

Strengths

  • ✓2M token context window
  • ✓Excellent long-context understanding
  • ✓Multimodal with video
  • ✓Strong knowledge

Weaknesses

  • ✗Slower than Flash
  • ✗Not as strong in coding as GPT-4o
Architecture
Transformer (MoE)
Parameters
Unknown
Input
$1.25/M
Output
$5/M

Benchmark Performance

BenchmarkDescriptionScoreCategoryBar
MMLUMassive Multitask Language Understanding90%knowledge
HumanEvalCode generation accuracy89%coding
MATHMathematical reasoning92%math
GSM8KGrade school math94.4%math
GPQAGraduate-level science Q&A58.5%reasoning
HellaSwagCommon sense reasoning88%reasoning
SWE-benchSoftware engineering problems39.2%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.