Flan-T5 XL: Complete Benchmark Performance Guide

other flan-t5-xl 2022-12-07 Apache 2.0

In-depth analysis of Flan-T5 XL performance on MMLU, HumanEval, GSM8K, MATH, BBH benchmarks, including pricing and use cases.

Key Specifications

Vendorother
Versionflan-t5-xl
Release Date2022-12-07
Context Window4096 tokens
Input Modalitiestext
Output Modalitiestext
LicenseApache 2.0
Documentationhttps://huggingface.co/models

Benchmark Performance

BenchmarkScoreUnitEvaluated AtNotesSource
MMLU60.4%2022-12-075-shotview
HUMANEVAL34pass@12022-12-07—view
GSM8K46.5%2022-12-070-shot CoTview
MATH27.8%2022-12-070-shot CoTview
BBH52.5%2022-12-073-shot CoTview
GPQA22.6%2022-12-070-shotview
IFEVAL55.7%2022-12-07prompt_strictview
ARC88%2022-12-07challengeview
MUSR40.2%2022-12-070-shotview
WINOGRANDE75.5%2022-12-070-shotview

Pricing

TierPriceCurrency
Input$0.3 / MtokUSD
Output$0.3 / MtokUSD
Cache Read$0 / MtokUSD
Cache Write$0 / MtokUSD

Source: https://huggingface.co/models · as of 2022-12-07

Compliance

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

Flan-T5 XL

모델 개요

Google Flan-T5 XL 3B 指令微调模型, 4K 上下文, 基于多任务指令微调, 适合零样本泛化任务。

핵심 사양

공급업체버전출시일컨텍스트 창입력 모달리티출력 모달리티라이선스
Otherflan-t5-xl2022-12-074KtexttextApache 2.0

벤치마크 성능

벤치마크점수단위비고
MMLU (Massive Multitask Language Understanding)60.4%5-shot
HumanEval34.0pass@1—
GSM8K (Grade School Math 8K)46.5%0-shot CoT
MATH27.8%0-shot CoT
BBH (BIG-Bench Hard)52.5%3-shot CoT
GPQA22.6%0-shot
IFEval55.7%prompt_strict
ARC88.0%challenge
MUSR40.2%0-shot
WinoGrande75.5%0-shot

가격

입력출력캐시 읽기캐시 쓰기
————

백만 토큰당

강점

  • 可靠的通用模型。

약점

  • HumanEval 34.0，代码能力较弱。
  • 闭源专有模型，不支持自托管。
  • 上下文窗口 4K 偏小。

사용 사례

  • 通用对话与问答

참고문헌