Key Specifications

SpecificationGPT-4oGPT-4o (2024-08-06)
Vendoropenaiopenai
Version4o4o-2024-08-06
Release Date2024-05-132024-08-06
Context Window128000 tokens128000 tokens
Input Modalitiestext, image, audiotext, image, audio
Output Modalitiestext, audiotext, audio
LicenseProprietaryProprietary
SOC2
HIPAA
GDPR
ISO 27001

Benchmark Results

BenchmarkGPT-4oGPT-4o (2024-08-06)Winner
ARC95.9GPT-4o (2024-08-06)
BBH83.184.9GPT-4o (2024-08-06)
GPQA62GPT-4o (2024-08-06)
GSM8K95.893.3GPT-4o
HUMANEVAL90.285.1GPT-4o
IFEVAL85.5GPT-4o (2024-08-06)
MATH76.668.2GPT-4o
MMLU88.787.6GPT-4o
MUSR62.9GPT-4o (2024-08-06)
WINOGRANDE87.7GPT-4o (2024-08-06)

Pricing Comparison

Tier (per Mtok)GPT-4oGPT-4o (2024-08-06)
Input$2.5$2.5
Output$10$10
Cache Read$1.25$0
Cache Write$2.5$0

GPT-4o contra GPT-4o (2024-08-06)

Descripción del modelo

GPT-4o and GPT-4o (2024-08-06) are both notable options in the AI model market. This page compares their benchmarks, pricing, and compliance.

Especificaciones clave

ProveedorFecha de lanzamientoVentana de contextoLicencia
Openai / Openai2024-05-13 / 2024-08-06128K / 128KProprietary / Proprietary

Rendimiento en benchmarks

BenchmarkGPT-4oGPT-4o (2024-08-06)Ganador
ARC95.9B
BBH (BIG-Bench Hard)83.184.9B
GPQA62.0B
GSM8K (Grade School Math 8K)95.893.3A
HumanEval90.285.1A
IFEval85.5B
MATH76.668.2A
MMLU (Massive Multitask Language Understanding)88.787.6A
MUSR62.9B
WinoGrande87.7B

Comparación de precios

EntradaSalidaLectura cachéEscritura caché
— / —— / —— / —— / —

por millón de tokens — A / B

Fortalezas & Debilidades

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。

GPT-4o (2024-08-06)

  • ✅ MMLU score 87.6, strong knowledge reasoning.
  • ✅ HumanEval 85.1, excellent code generation.
  • ✅ GSM8K 93.3, 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。

Opinión del editor

GPT-4o and GPT-4o (2024-08-06) each have their strengths. Choose based on workload (code, long context, vision), referencing the tables above.

Preguntas frecuentes

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.

Referencias

Editor's Take

See Editor's Take section.