o1 Preview: Complete Benchmark Performance Guide

openai o1-preview 2024-09-12 Proprietary

In-depth analysis of o1 Preview performance on MMLU, HumanEval, GSM8K, MATH, BBH benchmarks, including pricing and use cases.

Key Specifications

Vendoropenai
Versiono1-preview
Release Date2024-09-12
Context Window128000 tokens
Input Modalitiestext
Output Modalitiestext
LicenseProprietary
Documentationhttps://platform.openai.com/docs/models

Benchmark Performance

Benchmark Score Unit Evaluated At Notes Source
MMLU 85.3 % 2024-09-12 5-shot view
HUMANEVAL 90.1 pass@1 2024-09-12 — view
GSM8K 92.5 % 2024-09-12 0-shot CoT view
MATH 71.5 % 2024-09-12 0-shot CoT view
BBH 84.5 % 2024-09-12 3-shot CoT view
GPQA 57.7 % 2024-09-12 0-shot view
IFEVAL 84.4 % 2024-09-12 prompt_strict view
ARC 96 % 2024-09-12 challenge view
MUSR 64.1 % 2024-09-12 0-shot view
WINOGRANDE 85.2 % 2024-09-12 0-shot view

Pricing

Tier Price Currency
Input$15 / MtokUSD
Output$60 / MtokUSD
Cache Read$0 / MtokUSD
Cache Write$0 / MtokUSD

Source: https://openai.com/api/pricing/ · as of 2024-09-12

Compliance

  • Data Residency: US
  • SOC2: ✓
  • HIPAA: ✓
  • GDPR: ✓
  • ISO 27001: ✓

o1 Preview

Model Overview

OpenAI o1 预览版推理模型, 128K 上下文, 通过链式思维推理在数学/编码/科学任务上达到博士级表现。

Core Specifications

Vendor Version Release Date Context Window Input Modalities Output Modalities License
Openai o1-preview 2024-09-12 128K text text Proprietary

Benchmark Performance

Benchmark Score Unit Notes
MMLU (Massive Multitask Language Understanding) 85.3 % 5-shot
HumanEval 90.1 pass@1 —
GSM8K (Grade School Math 8K) 92.5 % 0-shot CoT
MATH 71.5 % 0-shot CoT
BBH (BIG-Bench Hard) 84.5 % 3-shot CoT
GPQA 57.7 % 0-shot
IFEval 84.4 % prompt_strict
ARC 96.0 % challenge
MUSR 64.1 % 0-shot
WinoGrande 85.2 % 0-shot

Pricing

Input Output Cache Read Cache Write
— — — —

per million tokens

Strengths

  • MMLU score 85.3, strong knowledge reasoning.
  • HumanEval 90.1, excellent code generation.
  • GSM8K 92.5, robust math reasoning.

Weaknesses

  • Proprietary, not self-hostable.

Use Cases

  • Code generation and debugging
  • Agent workflows and tool use

References