GPT-4 1106 Preview: Complete Benchmark Performance Guide

openai 4-1106-preview 2023-11-06 Proprietary

In-depth analysis of GPT-4 1106 Preview performance on MMLU, HumanEval, GSM8K, MATH, BBH benchmarks, including pricing and use cases.

Key Specifications

Vendoropenai
Version4-1106-preview
Release Date2023-11-06
Context Window128000 tokens
Input Modalitiestext
Output Modalitiestext
LicenseProprietary
Documentationhttps://platform.openai.com/docs/models

Benchmark Performance

Benchmark Score Unit Evaluated At Notes Source
MMLU 81.8 % 2023-11-06 5-shot view
HUMANEVAL 83.7 pass@1 2023-11-06 — view
GSM8K 85.4 % 2023-11-06 0-shot CoT view
MATH 52.1 % 2023-11-06 0-shot CoT view
BBH 80 % 2023-11-06 3-shot CoT view
GPQA 36.2 % 2023-11-06 0-shot view
IFEVAL 73.9 % 2023-11-06 prompt_strict view
ARC 94.3 % 2023-11-06 challenge view
MUSR 58.4 % 2023-11-06 0-shot view
WINOGRANDE 82 % 2023-11-06 0-shot view

Pricing

Tier Price Currency
Input$10 / MtokUSD
Output$30 / MtokUSD
Cache Read$0 / MtokUSD
Cache Write$0 / MtokUSD

Source: https://openai.com/api/pricing/ · as of 2023-11-06

Compliance

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

GPT-4 1106 Preview

Model Overview

OpenAI GPT-4 1106 预览版, 128K 上下文, 改进函数调用与 JSON 模式, 适合结构化输出任务。

Core Specifications

Vendor Version Release Date Context Window Input Modalities Output Modalities License
Openai 4-1106-preview 2023-11-06 128K text text Proprietary

Benchmark Performance

Benchmark Score Unit Notes
MMLU (Massive Multitask Language Understanding) 81.8 % 5-shot
HumanEval 83.7 pass@1 —
GSM8K (Grade School Math 8K) 85.4 % 0-shot CoT
MATH 52.1 % 0-shot CoT
BBH (BIG-Bench Hard) 80.0 % 3-shot CoT
GPQA 36.2 % 0-shot
IFEval 73.9 % prompt_strict
ARC 94.3 % challenge
MUSR 58.4 % 0-shot
WinoGrande 82.0 % 0-shot

Pricing

Input Output Cache Read Cache Write
— — — —

per million tokens

Strengths

  • MMLU score 81.8, strong knowledge reasoning.
  • HumanEval 83.7, excellent code generation.
  • GSM8K 85.4, robust math reasoning.
  • Context window 128K.

Weaknesses

  • Proprietary, not self-hostable.

Use Cases

  • Code generation and debugging
  • Long document summarization
  • Agent workflows and tool use

References