Flan-UL2: Complete Benchmark Performance Guide

other flan-ul2 2023-03-03 Apache 2.0

In-depth analysis of Flan-UL2 performance on MMLU, HumanEval, GSM8K, MATH, BBH benchmarks, including pricing and use cases.

Key Specifications

Vendorother
Versionflan-ul2
Release Date2023-03-03
Context Window4096 tokens
Input Modalitiestext
Output Modalitiestext
LicenseApache 2.0
Documentationhttps://huggingface.co/models

Benchmark Performance

Benchmark Score Unit Evaluated At Notes Source
MMLU 58.7 % 2023-03-03 5-shot view
HUMANEVAL 46.8 pass@1 2023-03-03 — view
GSM8K 40.6 % 2023-03-03 0-shot CoT view
MATH 22 % 2023-03-03 0-shot CoT view
BBH 49.2 % 2023-03-03 3-shot CoT view
GPQA 27.2 % 2023-03-03 0-shot view
IFEVAL 55.6 % 2023-03-03 prompt_strict view
ARC 88.8 % 2023-03-03 challenge view
MUSR 37.2 % 2023-03-03 0-shot view
WINOGRANDE 76.2 % 2023-03-03 0-shot view

Pricing

Tier Price Currency
Input$0.7 / MtokUSD
Output$0.7 / MtokUSD
Cache Read$0 / MtokUSD
Cache Write$0 / MtokUSD

Source: https://huggingface.co/models · as of 2023-03-03

Compliance

  • Data Residency: self-host
  • SOC2: ✗
  • HIPAA: ✗
  • GDPR: ✗
  • ISO 27001: ✗

Flan-UL2

Model Overview

Google Flan-UL2 20B 指令微调模型, 4K 上下文, 基于 UL2 框架, 适合多任务与零样本推理。

Core Specifications

Vendor Version Release Date Context Window Input Modalities Output Modalities License
Other flan-ul2 2023-03-03 4K text text Apache 2.0

Benchmark Performance

Benchmark Score Unit Notes
MMLU (Massive Multitask Language Understanding) 58.7 % 5-shot
HumanEval 46.8 pass@1 —
GSM8K (Grade School Math 8K) 40.6 % 0-shot CoT
MATH 22.0 % 0-shot CoT
BBH (BIG-Bench Hard) 49.2 % 3-shot CoT
GPQA 27.2 % 0-shot
IFEval 55.6 % prompt_strict
ARC 88.8 % challenge
MUSR 37.2 % 0-shot
WinoGrande 76.2 % 0-shot

Pricing

Input Output Cache Read Cache Write
— — — —

per million tokens

Strengths

  • Reliable general-purpose model.

Weaknesses

  • MMLU 58.7, weak knowledge reasoning.
  • HumanEval 46.8, coding weak.
  • Proprietary, not self-hostable.
  • Context window 4K is limited.

Use Cases

  • General chat and Q&A

References