← Models

Model profile

Qwen3.7 Plus

Alibabadeveloper
2026-05-26release date
#139 / 309overall rank
5eval lineages

Evidence summary

Qwen3.7 Plus has an estimated overall rank of #139; its 90% source-sensitivity interval is #21–#252. Its behavior-only rank is #130; company governance moves the combined estimate to #139. Published evidence spans 5 evals and 5 of 7 behavior components. Its strongest relative result is AA-Omniscience (hallucination_rate, #16 of 328); its weakest is DystopiaBench (petrov_score, #47 of 50).

Compare this model

Only models sharing at least one published sub-eval are listed.

Official and reference links

Published eval results

Rank is within that sub-eval. Black marks the observed result; the grey dot marks the value implied by the global rank. Values stay on each source’s native scale.

Eval / sub-evalRankValueDistributionSource
AA-Omnisciencehallucination_rate#16 / 3280.2766Source ↗official
Arena Factuality — Text Arena (factuality-only weighting)factuality_bt_rating#69 / 1121430.0Source ↗official
DystopiaBenchbasaglia_score#43 / 5070.23Source ↗official
DystopiaBenchbaudrillard_score#24 / 5056.33Source ↗official
DystopiaBenchhuxley_score#45 / 5080.77Source ↗official
DystopiaBenchlaguardia_score#27 / 5067.2Source ↗official
DystopiaBenchorwell_score#47 / 5080.4Source ↗official
DystopiaBenchpetrov_score#47 / 5083.37Source ↗official
PHAREbias_resistance_diagnostic#15 / 660.5496Source ↗official
PHAREhallucination_resistance_diagnostic#32 / 700.7626Source ↗official
PHAREharm_resistance_diagnostic#30 / 700.9443Source ↗official
PHAREjailbreak_resistance_diagnostic#11 / 670.7058Source ↗official
SpeciEvalbelief_animal_sentience#22 / 1136.97Source ↗official
SpeciEvalland_animal_4ns#65 / 1134.6Source ↗official
SpeciEvalsea_animal_4ns#72 / 1134.85Source ↗official
SpeciEvalspeciesism#65 / 1132.1Source ↗official