Key Specifications

SpecificationGemini 1.5 ProGemini 1.5 Flash
Vendorgooglegoogle
Version1.5-pro1.5-flash
Release Date2024-02-152024-05-14
Context Window2e+06 tokens1e+06 tokens
Input Modalitiestext, image, audio, videotext, image, audio, video
Output Modalitiestexttext
LicenseProprietaryProprietary
SOC2
HIPAA
GDPR
ISO 27001

Benchmark Results

BenchmarkGemini 1.5 ProGemini 1.5 FlashWinner
ARC93.4Gemini 1.5 Flash
BBH8471.7Gemini 1.5 Pro
GPQA38.5Gemini 1.5 Flash
GSM8K91.775.2Gemini 1.5 Pro
HUMANEVAL71.967.5Gemini 1.5 Pro
IFEVAL68Gemini 1.5 Flash
MATH58.553.2Gemini 1.5 Pro
MMLU85.976Gemini 1.5 Pro
MUSR46.1Gemini 1.5 Flash
WINOGRANDE78.9Gemini 1.5 Flash

Pricing Comparison

Tier (per Mtok)Gemini 1.5 ProGemini 1.5 Flash
Input$1.25$0.075
Output$5$0.3
Cache Read$0.3125$0
Cache Write$1.25$0

Gemini 1.5 Pro vs Gemini 1.5 Flash

Model Overview

Gemini 1.5 Pro and Gemini 1.5 Flash are both notable options in the AI model market. This page compares their benchmarks, pricing, and compliance.

Key Specifications

VendorRelease DateContext WindowLicense
Google / Google2024-02-15 / 2024-05-142000K / 1000KProprietary / Proprietary

Benchmark Performance

BenchmarkGemini 1.5 ProGemini 1.5 FlashWinner
ARC93.4B
BBH (BIG-Bench Hard)84.071.7A
GPQA38.5B
GSM8K (Grade School Math 8K)91.775.2A
HumanEval71.967.5A
IFEval68.0B
MATH58.553.2A
MMLU (Massive Multitask Language Understanding)85.976.0A
MUSR46.1B
WinoGrande78.9B

Pricing Comparison

InputOutputCache ReadCache Write
— / —— / —— / —— / —

per million tokens — A / B

Strengths & Weaknesses

Gemini 1.5 Pro

  • ✅ MMLU score 85.9, strong knowledge reasoning.
  • ✅ GSM8K 91.7, robust math reasoning.
  • ✅ Input Modalities: text, image, audio.
  • ✅ Context window 2000K.
  • ⚠️ Proprietary, not self-hostable.

Gemini 1.5 Flash

  • ✅ Input Modalities: text, image, audio.
  • ✅ Context window 1000K.
  • ⚠️ Proprietary, not self-hostable.

Editor’s Take

Gemini 1.5 Pro and Gemini 1.5 Flash each have their strengths. Choose based on workload (code, long context, vision), referencing the tables above.

FAQ

Which model is better for coding tasks?

Refer to the HumanEval benchmark table; the model with a higher score is better suited for coding tasks.

Which model is cheaper?

Refer to the pricing comparison table above; the model with lower input/output prices is more cost-effective.

Which has a longer context window?

Refer to the key specifications table; the model with a larger context window is better for long documents.

References

Editor's Take

See Editor's Take section.