Key Specifications

SpecificationGemini 1.0 ProGemini 1.0 Ultra
Vendorgooglegoogle
Version1.0-pro1.0-ultra
Release Date2023-12-062023-12-06
Context Window32768 tokens32768 tokens
Input Modalitiestexttext, image
Output Modalitiestexttext
LicenseProprietaryProprietary
SOC2
HIPAA
GDPR
ISO 27001

Benchmark Results

BenchmarkGemini 1.0 ProGemini 1.0 UltraWinner
ARC94.195.7Gemini 1.0 Ultra
BBH79.183.8Gemini 1.0 Ultra
GPQA47.746.9Gemini 1.0 Pro
GSM8K82.485.9Gemini 1.0 Ultra
HUMANEVAL76.481.7Gemini 1.0 Ultra
IFEVAL75.181.6Gemini 1.0 Ultra
MATH58.257.1Gemini 1.0 Pro
MMLU84.580.3Gemini 1.0 Pro
MUSR57.864.3Gemini 1.0 Ultra
WINOGRANDE84.580.4Gemini 1.0 Pro

Pricing Comparison

Tier (per Mtok)Gemini 1.0 ProGemini 1.0 Ultra
Input$0.5$7
Output$1.5$21
Cache Read$0$0
Cache Write$0$0

Gemini 1.0 Pro karşı Gemini 1.0 Ultra

Model Genel Bakışı

Gemini 1.0 Pro and Gemini 1.0 Ultra are both notable options in the AI model market. This page compares their benchmarks, pricing, and compliance.

Temel Özellikler

SatıcıYayın TarihiBağlam PenceresiLisans
Google / Google2023-12-06 / 2023-12-0632K / 32KProprietary / Proprietary

Benchmark Performansı

BenchmarkGemini 1.0 ProGemini 1.0 UltraKazanan
ARC94.195.7B
BBH (BIG-Bench Hard)79.183.8B
GPQA47.746.9A
GSM8K (Grade School Math 8K)82.485.9B
HumanEval76.481.7B
IFEval75.181.6B
MATH58.257.1A
MMLU (Massive Multitask Language Understanding)84.580.3A
MUSR57.864.3B
WinoGrande84.580.4A

Fiyat Karşılaştırması

GirişÇıkışÖnbellek OkumaÖnbellek Yazma
— / —— / —— / —— / —

milyon token başına — A / B

Güçlü Yönler & Zayıf Yönler

Gemini 1.0 Pro

  • ✅ MMLU score 84.5, strong knowledge reasoning.
  • ⚠️ 闭源专有模型,不支持自托管。

Gemini 1.0 Ultra

  • ✅ MMLU score 80.3, strong knowledge reasoning.
  • ✅ HumanEval 81.7, excellent code generation.
  • ✅ GSM8K 85.9, robust math reasoning.
  • ✅ 支持文本、图像、音频多模态输入。
  • ⚠️ 闭源专有模型,不支持自托管。

Editör Görüşü

Gemini 1.0 Pro and Gemini 1.0 Ultra each have their strengths. Choose based on workload (code, long context, vision), referencing the tables above.

SSS

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.

Referanslar

Editor's Take

See Editor's Take section.