MODEL HISTORY

Qwen3 235B A22B 2507 (Reasoning) 指标历史

Qwen3 235B A22B 2507 (Reasoning) 的公开评测事实历史,共 78 条观测、53 项指标;只记录来源变化,不插值、不合成本站总分。

数据快照:2026-09-18T01:47:51.386Z查看原始来源 ↗
历史观测78仅在事实变化时追加
指标数量53不同量纲保持分离
后续变更25初始观测不计作变更
首次收录2026/07/21本站可追溯起点
最近观测2026/09/18不是模型发布日期

怎样理解这份历史

每条记录对应来源快照中的一个原始指标。同一口径下相同值重复抓取不会制造新记录;数值、临时状态或来源状态变化时追加,核实后的方法版本另立指标身份。首个快照是本站的可追溯起点,不代表该指标第一次对外发布。当前模型来源为 Artificial Analysis。

Index、Elo、百分比等单位不能互相相减,也不会在这里合成为“综合总分”。

GDPval-AA 与 AA-Briefcase 的实时 Elo 现按裁判协议 v4.3.1 单独记录;旧记录的版本、值与日期保留,未区分裁判的旧值仅作历史参考。Intelligence Index 仍为 v4.3,官方用于指数的 Elo 贡献在模型加入时固定,不能用当前实时 Elo 重算指数。核对方法说明 ↗

APPEND-ONLY FACTS

观测记录

按观测时间倒序;同日多项指标分别保留。

Qwen3 235B A22B 2507 (Reasoning) 的公开评测事实历史
观测日期基准 / 版本指标原始值来源状态
Artificial Analysis GDPval-AA任务 v2 · 裁判 v4.3.1实时 Elo · 裁判协议 v4.3.1Eloelo495Artificial Analysis ↗第三方评测有效
Artificial Analysis AA-Briefcase来源未标任务版本 · 裁判 v4.3.1实时 Elo · 裁判协议 v4.3.1Eloelo190Artificial Analysis ↗第三方评测有效
Artificial Analysis intelligence component evaluationsv4.3.1实时 Elo · 裁判协议 v4.3.1AA-Briefcase overall Eloelo190Artificial Analysis ↗第三方评测有效
Artificial Analysis intelligence component evaluationsv4.3.1实时 Elo · 裁判协议 v4.3.1GDPval-AA v2elo495Artificial Analysis ↗第三方评测有效
Artificial Analysis Openness Indexvsource-unversionedModel availabilitypoints6.0Artificial Analysis ↗第三方评测有效
Artificial Analysis Openness Indexvsource-unversionedModel transparencypoints2.0Artificial Analysis ↗第三方评测有效
Artificial Analysis Openness Indexvsource-unversionedOpenness Indexindex44.4Artificial Analysis ↗第三方评测有效
Artificial Analysis Openness Indexvsource-unversionedPosttraining data accesspoints0.0Artificial Analysis ↗第三方评测有效
Artificial Analysis Openness Indexvsource-unversionedPosttraining data licensepoints0.0Artificial Analysis ↗第三方评测有效
Artificial Analysis Openness Indexvsource-unversionedPretraining data accesspoints0.0Artificial Analysis ↗第三方评测有效
Artificial Analysis Openness Indexvsource-unversionedPretraining data licensepoints0.0Artificial Analysis ↗第三方评测有效
Artificial Analysis GDPval-AAv2历史参考 · 原记录未区分当前裁判协议,不作跨协议能力变化比较Eloelo495Artificial Analysis ↗第三方评测有效
Artificial Analysis AA-Briefcasevsource-unversioned历史参考 · 原记录未区分当前裁判协议,不作跨协议能力变化比较Eloelo190Artificial Analysis ↗第三方评测有效
Artificial Analysis intelligence component evaluationsv4.3AutomationBench-AA partial scorefraction2.2%Artificial Analysis ↗第三方评测有效
Artificial Analysis intelligence component evaluationsv4.3历史参考 · 原记录未区分当前裁判协议,不作跨协议能力变化比较AA-Briefcase overall Eloelo190Artificial Analysis ↗第三方评测有效
Artificial Analysis intelligence component evaluationsv4.3CritPtfraction0.0%Artificial Analysis ↗第三方评测有效
Artificial Analysis intelligence component evaluationsv4.3GDP.pdf all-passfraction4.8%Artificial Analysis ↗第三方评测有效
Artificial Analysis intelligence component evaluationsv4.3历史参考 · 原记录未区分当前裁判协议,不作跨协议能力变化比较GDPval-AA v2elo495Artificial Analysis ↗第三方评测有效
Artificial Analysis intelligence component evaluationsv4.3Humanity's Last Examfraction15.9%Artificial Analysis ↗第三方评测有效
Artificial Analysis capability indicesv4.3Intelligence Indexindex12.7Artificial Analysis ↗第三方评测有效
Artificial Analysis intelligence component evaluationsv4.3AA-LCR v1.1fraction72.0%Artificial Analysis ↗第三方评测有效
Artificial Analysis intelligence component evaluationsv4.3AA-Omniscienceindex-46.5Artificial Analysis ↗第三方评测有效
Artificial Analysis intelligence component evaluationsv4.3AA-Omniscience accuracyfraction22.8%Artificial Analysis ↗第三方评测有效
Artificial Analysis intelligence component evaluationsv4.3AA-Omniscience hallucination ratefraction89.8%Artificial Analysis ↗第三方评测有效
Artificial Analysis intelligence component evaluationsv4.3SciCodefraction41.4%Artificial Analysis ↗第三方评测有效
Artificial Analysis intelligence component evaluationsv4.3Terminal-Bench v4.0fraction0.0%Artificial Analysis ↗第三方评测有效
Artificial Analysis model aggregatevpublic-model-v1端到端响应时间seconds40.4 秒Model Coordinate repository snapshots第三方评测有效
Artificial Analysis model aggregatevpublic-model-v1生成速度tokens_per_second66.5 Token/sModel Coordinate repository snapshots第三方评测有效
Artificial Analysis model aggregatevpublic-model-v1首个回答 Token 等待seconds32.9 秒Model Coordinate repository snapshots第三方评测有效
Artificial Analysis model aggregatevpublic-model-v1端到端响应时间seconds39.7 秒Model Coordinate repository snapshots第三方评测有效
Artificial Analysis intelligence component evaluationsv4.1历史参考 · 原记录未区分当前裁判协议,不作跨协议能力变化比较GDPval-AAelo548Artificial Analysis ↗第三方评测有效
Artificial Analysis intelligence component evaluationsv4.1GDPval-AA normalizedfraction2.4%Artificial Analysis ↗第三方评测有效
Artificial Analysis intelligence component evaluationsv4.1Humanity's Last Examfraction15.9%Artificial Analysis第三方评测有效
Artificial Analysis model aggregatevpublic-model-v1输入价格 / 1M Tokenusd_per_1m_tokensUS$0.23Model Coordinate repository snapshots第三方评测有效
Artificial Analysis capability indicesvpublic-model-v1Intelligence Indexindex19.9Artificial Analysis第三方评测有效
Artificial Analysis intelligence component evaluationsv4.1AA-LCRfraction70.7%Artificial Analysis第三方评测有效
Artificial Analysis intelligence component evaluationsv4.1AA-Omniscienceindex-46.5Artificial Analysis第三方评测有效
Artificial Analysis model aggregatevpublic-model-v1输出价格 / 1M Tokenusd_per_1m_tokensUS$2.3Model Coordinate repository snapshots第三方评测有效
Artificial Analysis model aggregatevpublic-model-v1生成速度tokens_per_second67.7 Token/sModel Coordinate repository snapshots第三方评测有效
Artificial Analysis model aggregatevpublic-model-v1首个回答 Token 等待seconds32.3 秒Model Coordinate repository snapshots第三方评测有效
Artificial Analysis model aggregatevpublic-model-v1端到端响应时间seconds43.4 秒Model Coordinate repository snapshots第三方评测有效
Artificial Analysis model aggregatevpublic-model-v1生成速度tokens_per_second61.4 Token/sModel Coordinate repository snapshots第三方评测有效
Artificial Analysis model aggregatevpublic-model-v1首个回答 Token 等待seconds35.3 秒Model Coordinate repository snapshots第三方评测有效
Artificial Analysis model aggregatevpublic-model-v1端到端响应时间seconds48.4 秒Model Coordinate repository snapshots第三方评测有效
Artificial Analysis intelligence component evaluationsv4.1历史参考 · 原记录未区分当前裁判协议,不作跨协议能力变化比较GDPval-AAelo546Artificial Analysis ↗第三方评测有效
Artificial Analysis intelligence component evaluationsv4.1GDPval-AA normalizedfraction2.3%Artificial Analysis ↗第三方评测有效
Artificial Analysis model aggregatevpublic-model-v1生成速度tokens_per_second54.8 Token/sModel Coordinate repository snapshots第三方评测有效
Artificial Analysis model aggregatevpublic-model-v1首个回答 Token 等待seconds39.3 秒Model Coordinate repository snapshots第三方评测有效
Artificial Analysis model aggregatevpublic-model-v1端到端响应时间seconds46.7 秒Model Coordinate repository snapshots第三方评测有效
Artificial Analysis model aggregatevpublic-model-v1生成速度tokens_per_second57.1 Token/sModel Coordinate repository snapshots第三方评测有效
Artificial Analysis model aggregatevpublic-model-v1首个回答 Token 等待seconds37.9 秒Model Coordinate repository snapshots第三方评测有效
Artificial Analysis capability indicesvpublic-model-v1Agentic Indexindex3.8Artificial Analysis第三方评测有效
Artificial Analysis agentic capability indexvunversionedagentic capability indexindex3.8Artificial Analysis第三方评测有效
Artificial Analysis coding capability indexvunversionedcoding capability indexindex22.1Artificial Analysis第三方评测有效
Artificial Analysis finance capability indexvunversionedfinance capability indexindex14.1Artificial Analysis第三方评测有效
Artificial Analysis strategy capability indexvunversionedstrategy capability indexindex14.4Artificial Analysis第三方评测有效
Artificial Analysis legal capability indexvunversionedlegal capability indexindex15.3Artificial Analysis第三方评测有效
Artificial Analysis healthcare capability indexvunversionedhealthcare capability indexindex12.3Artificial Analysis第三方评测有效
Artificial Analysis engineering capability indexvunversionedengineering capability indexindex24.8Artificial Analysis第三方评测有效
Artificial Analysis economics capability indexvunversionedeconomics capability indexindex24.6Artificial Analysis第三方评测有效
Artificial Analysis capability indicesvpublic-model-v1Coding Indexindex22.1Artificial Analysis第三方评测有效
Artificial Analysis model aggregatevpublic-model-v1上下文窗口tokens256,000Model Coordinate repository snapshots第三方评测有效
Artificial Analysis intelligence component evaluationsv4.1CritPtfraction0.0%Artificial Analysis第三方评测有效
Artificial Analysis model aggregatevpublic-model-v1端到端响应时间seconds41.8 秒Model Coordinate repository snapshots第三方评测有效
Artificial Analysis intelligence component evaluationsv4.1历史参考 · 原记录未区分当前裁判协议,不作跨协议能力变化比较GDPval-AAelo541Artificial Analysis ↗第三方评测有效
Artificial Analysis intelligence component evaluationsv4.1GDPval-AA normalizedfraction2.0%Artificial Analysis ↗第三方评测有效
Artificial Analysis intelligence component evaluationsv4.1GPQA Diamondfraction79.0%Artificial Analysis第三方评测有效
Artificial Analysis intelligence component evaluationsv4.1Humanity's Last Examfraction15.0%Artificial Analysis第三方评测有效
Artificial Analysis model aggregatevpublic-model-v1输入价格 / 1M Tokenusd_per_1m_tokensUS$0.7Model Coordinate repository snapshots第三方评测有效
Artificial Analysis capability indicesvpublic-model-v1Intelligence Indexindex19.6Artificial Analysis第三方评测有效
Artificial Analysis intelligence component evaluationsv4.1AA-LCRfraction67.0%Artificial Analysis第三方评测有效
Artificial Analysis intelligence component evaluationsv4.1AA-Omniscienceindex-45.5Artificial Analysis第三方评测有效
Artificial Analysis model aggregatevpublic-model-v1输出价格 / 1M Tokenusd_per_1m_tokensUS$8.4Model Coordinate repository snapshots第三方评测有效
Artificial Analysis model aggregatevpublic-model-v1生成速度tokens_per_second64.1 Token/sModel Coordinate repository snapshots第三方评测有效
Artificial Analysis intelligence component evaluationsv4.1SciCodefraction42.4%Artificial Analysis第三方评测有效
Artificial Analysis intelligence component evaluationsv4.1Tau Bankingfraction7.8%Artificial Analysis第三方评测有效
Artificial Analysis intelligence component evaluationsv4.1Terminal-Bench v2.1fraction12.0%Artificial Analysis第三方评测有效
Artificial Analysis model aggregatevpublic-model-v1首个回答 Token 等待seconds34.0 秒Model Coordinate repository snapshots第三方评测有效