Qwen2.5 72B Instruct

Alibaba / Qwen Team · qwen/qwen2-5-72b-instruct

ProviderAlibaba / Qwen Team
Familyqwen
Typellm-chat
Statusactive
Released2024-09
Updated2024-09

Reported benchmark scores

These scores carry one collection date for the whole card (2026-04) and a source list rather than a source per score, so they cannot be attributed individually. They are shown as reported and are not verified evidence. Benchmark pages carry the reviewed, dated evidence where it exists.
BenchmarkCatalogue standingScore
AlpacaEvalunassessed38.1
Arena Elo — Codingunassessed1290.0
Arena Elo — Hard Promptsunassessed1317.3
Arena Elo — Mathunassessed1270.0
Arena Elo — Overall (Text)unassessed1280.0
Arena Elo — Style Controlunassessed1302.3
Arena Elo — Visionunassessed1122.0
BIG-Bench Hardunassessed66.3
BBQ (Bias Benchmark for QA)unassessed75.2
GPQA Diamondunassessed54.8
HELM Safetyunassessed80.5
HumanEvalunassessed84.5
IFEvalunassessed82.0
LiveCodeBenchunassessed55.5
MATH-500unassessed83.2
MMLU-Prounassessed71.5
MultiPL-E: C#unassessed74.5
MultiPL-E: Juliaunassessed54.8
MultiPL-E: Kotlin (unconfirmed)unassessed65.5
MultiPL-E: Luaunassessed49.5
MultiPL-E: Perlunassessed44.2
MultiPL-E: PHPunassessed72.2
MultiPL-E: Runassessed50.5
MultiPL-E: Rubyunassessed58.5
MultiPL-E: Scalaunassessed53.2
MultiPL-E: Swiftunassessed58.8
MuSRunassessed28.3
ToxiGenunassessed84.8

Data

This card as JSON · Edit on GitHub