Key Specifications

SpecificationGPT-4oGemini 1.5 Pro
Vendoropenaigoogle
Version4o1.5-pro
Release Date2024-05-132024-02-15
Context Window128000 tokens2e+06 tokens
Input Modalitiestext, image, audiotext, image, audio, video
Output Modalitiestext, audiotext
LicenseProprietaryProprietary
SOC2
HIPAA
GDPR
ISO 27001

Benchmark Results

BenchmarkGPT-4oGemini 1.5 ProWinner
BBH83.184Gemini 1.5 Pro
GSM8K95.891.7GPT-4o
HUMANEVAL90.271.9GPT-4o
MATH76.658.5GPT-4o
MMLU88.785.9GPT-4o

Pricing Comparison

Tier (per Mtok)GPT-4oGemini 1.5 Pro
Input$2.5$1.25
Output$10$5
Cache Read$1.25$0.3125
Cache Write$2.5$1.25

GPT-4o contra Gemini 1.5 Pro

Visão geral do modelo

GPT-4o and Gemini 1.5 Pro are both notable options in the AI model market. This page compares their benchmarks, pricing, and compliance.

Especificações principais

FornecedorData de lançamentoJanela de contextoLicença
Openai / Google2024-05-13 / 2024-02-15128K / 2000KProprietary / Proprietary

Desempenho em benchmarks

BenchmarkGPT-4oGemini 1.5 ProVencedor
BBH (BIG-Bench Hard)83.184.0B
GSM8K (Grade School Math 8K)95.891.7A
HumanEval90.271.9A
MATH76.658.5A
MMLU (Massive Multitask Language Understanding)88.785.9A

Comparação de preços

EntradaSaídaLeitura de cacheEscrita de cache
— / —— / —— / —— / —

por milhão de tokens — A / B

Pontos fortes & Pontos fracos

GPT-4o

  • ✅ MMLU score 88.7, strong knowledge reasoning.
  • ✅ HumanEval 90.2, excellent code generation.
  • ✅ GSM8K 95.8, 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。

Gemini 1.5 Pro

  • ✅ MMLU score 85.9, strong knowledge reasoning.
  • ✅ GSM8K 91.7, robust math reasoning.
  • ✅ 支持文本、图像、音频多模态输入。
  • ✅ 上下文窗口 2000K,支持长文本。
  • ⚠️ 闭源专有模型,不支持自托管。

Opinião do editor

GPT-4o and Gemini 1.5 Pro each have their strengths. Choose based on workload (code, long context, vision), referencing the tables above.

Perguntas frequentes

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.

Referências

Editor's Take

See Editor's Take section.