Flan-T5 XXL: Complete Benchmark Performance Guide

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

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

Key Specifications

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

Benchmark Performance

BenchmarkScoreUnitEvaluated AtNotesSource
MMLU52%2022-12-075-shotview
HUMANEVAL35.4pass@12022-12-07—view
GSM8K35.2%2022-12-070-shot CoTview
MATH21.4%2022-12-070-shot CoTview
BBH60.5%2022-12-073-shot CoTview
GPQA28.6%2022-12-070-shotview
IFEVAL51.3%2022-12-07prompt_strictview
ARC81.7%2022-12-07challengeview
MUSR42.2%2022-12-070-shotview
WINOGRANDE74.2%2022-12-070-shotview

Pricing

TierPriceCurrency
Input$0.5 / MtokUSD
Output$0.5 / 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 XXL

모델 개요

Google Flan-T5 XXL 11B 指令微调模型, 4K 上下文, 多任务指令微调, 零样本能力突出。

핵심 사양

공급업체버전출시일컨텍스트 창입력 모달리티출력 모달리티라이선스
Otherflan-t5-xxl2022-12-074KtexttextApache 2.0

벤치마크 성능

벤치마크점수단위비고
MMLU (Massive Multitask Language Understanding)52.0%5-shot
HumanEval35.4pass@1—
GSM8K (Grade School Math 8K)35.2%0-shot CoT
MATH21.4%0-shot CoT
BBH (BIG-Bench Hard)60.5%3-shot CoT
GPQA28.6%0-shot
IFEval51.3%prompt_strict
ARC81.7%challenge
MUSR42.2%0-shot
WinoGrande74.2%0-shot

가격

입력출력캐시 읽기캐시 쓰기
————

백만 토큰당

강점

  • 可靠的通用模型。

약점

  • MMLU 仅 52.0，知识推理偏弱。
  • HumanEval 35.4，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