MODEL HISTORY
Gemini 3.1 Flash-Lite 指标历史
Gemini 3.1 Flash-Lite 的公开评测事实历史,共 77 条观测、50 项指标;只记录来源变化,不插值、不合成本站总分。
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。
| 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 v4.3.1 | Eloelo | 596 | Artificial 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 v4.3.1 | Eloelo | 226 | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.3.1实时 Elo · 裁判协议 v4.3.1 | AA-Briefcase overall Eloelo | 226 | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.3.1实时 Elo · 裁判协议 v4.3.1 | GDPval-AA v2elo | 596 | Artificial 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 | Eloelo | 596 | Artificial 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 | Eloelo | 226 | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.3 | AutomationBench-AA partial scorefraction | 6.8% | 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 | AA-Briefcase overall Eloelo | 226 | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.3 | CritPtfraction | 1.1% | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.3 | GDP.pdf all-passfraction | 7.8% | 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 v2elo | 596 | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.3 | Humanity's Last Examfraction | 17.2% | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis capability indicesv4.3 | Intelligence Indexindex | 16.0 | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.3 | AA-LCR v1.1fraction | 74.3% | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.3 | AA-Omniscienceindex | -16.4 | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.3 | AA-Omniscience accuracyfraction | 36.3% | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.3 | AA-Omniscience hallucination ratefraction | 82.7% | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.3 | SciCodefraction | 43.4% | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.3 | Terminal-Bench v4.0fraction | 0.5% | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis model aggregatevpublic-model-v1 | 端到端响应时间seconds | 6.8 秒 | Model Coordinate repository snapshots第三方评测 | 有效 | |
| Artificial Analysis model aggregatevpublic-model-v1 | 生成速度tokens_per_second | 310.5 Token/s | Model Coordinate repository snapshots第三方评测 | 有效 | |
| Artificial Analysis model aggregatevpublic-model-v1 | 首个回答 Token 等待seconds | 5.2 秒 | Model Coordinate repository snapshots第三方评测 | 有效 | |
| Artificial Analysis capability indicesvpublic-model-v1 | Agentic Indexindex | 6.5 | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis model aggregatevpublic-model-v1 | 端到端响应时间seconds | 7.4 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-AAelo | 649 | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | GDPval-AA normalizedfraction | 7.5% | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | Humanity's Last Examfraction | 17.2% | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis capability indicesvpublic-model-v1 | Intelligence Indexindex | 25.6 | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | AA-LCRfraction | 71.3% | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | AA-Omniscienceindex | -16.4 | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis model aggregatevpublic-model-v1 | 生成速度tokens_per_second | 350.4 Token/s | Model Coordinate repository snapshots第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | Tau Bankingfraction | 9.7% | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis model aggregatevpublic-model-v1 | 首个回答 Token 等待seconds | 5.9 秒 | Model Coordinate repository snapshots第三方评测 | 有效 | |
| Artificial Analysis Analyst Agentv80-tasks-5-attempts | pass^5percent | 8.8% | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis Analyst Agentv80-tasks-5-attempts | pass@1percent | 24.0% | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis Analyst Agentv80-tasks-5-attempts | pass@5percent | 43.8% | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis model aggregatevpublic-model-v1 | 端到端响应时间seconds | 7.5 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-AAelo | 647 | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | GDPval-AA normalizedfraction | 7.4% | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis model aggregatevpublic-model-v1 | 生成速度tokens_per_second | 329.0 Token/s | Model Coordinate repository snapshots第三方评测 | 有效 | |
| Artificial Analysis model aggregatevpublic-model-v1 | 首个回答 Token 等待seconds | 6.0 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seconds | 7.8 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-AAelo | 647 | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | GDPval-AA normalizedfraction | 7.3% | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis model aggregatevpublic-model-v1 | 生成速度tokens_per_second | 289.2 Token/s | Model Coordinate repository snapshots第三方评测 | 有效 | |
| Artificial Analysis model aggregatevpublic-model-v1 | 首个回答 Token 等待seconds | 6.0 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seconds | 7.4 秒 | Model Coordinate repository snapshots第三方评测 | 有效 | |
| Artificial Analysis model aggregatevpublic-model-v1 | 生成速度tokens_per_second | 331.2 Token/s | Model Coordinate repository snapshots第三方评测 | 有效 | |
| Artificial Analysis model aggregatevpublic-model-v1 | 首个回答 Token 等待seconds | 5.9 秒 | Model Coordinate repository snapshots第三方评测 | 有效 | |
| Artificial Analysis capability indicesvpublic-model-v1 | Agentic Indexindex | 6.2 | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis model aggregatevpublic-model-v1 | 缓存读取价格 / 1M Tokenusd_per_1m_tokens | US$0.025 | Model Coordinate repository snapshots第三方评测 | 有效 | |
| Artificial Analysis agentic capability indexvunversioned | agentic capability indexindex | 6.2 | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis coding capability indexvunversioned | coding capability indexindex | 34.7 | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis finance capability indexvunversioned | finance capability indexindex | 20.4 | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis strategy capability indexvunversioned | strategy capability indexindex | 21.7 | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis legal capability indexvunversioned | legal capability indexindex | 26.4 | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis healthcare capability indexvunversioned | healthcare capability indexindex | 17.5 | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis engineering capability indexvunversioned | engineering capability indexindex | 30.7 | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis economics capability indexvunversioned | economics capability indexindex | 30.5 | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis capability indicesvpublic-model-v1 | Coding Indexindex | 34.7 | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis model aggregatevpublic-model-v1 | 上下文窗口tokens | 1,000,000 | Model Coordinate repository snapshots第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | CritPtfraction | 1.1% | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis model aggregatevpublic-model-v1 | 端到端响应时间seconds | 7.2 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-AAelo | 642 | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | GDPval-AA normalizedfraction | 7.1% | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | GPQA Diamondfraction | 82.2% | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | Humanity's Last Examfraction | 16.2% | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis model aggregatevpublic-model-v1 | 输入价格 / 1M Tokenusd_per_1m_tokens | US$0.25 | Model Coordinate repository snapshots第三方评测 | 有效 | |
| Artificial Analysis capability indicesvpublic-model-v1 | Intelligence Indexindex | 25.0 | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | AA-LCRfraction | 65.3% | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | AA-Omniscienceindex | -15.5 | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis model aggregatevpublic-model-v1 | 输出价格 / 1M Tokenusd_per_1m_tokens | US$1.5 | Model Coordinate repository snapshots第三方评测 | 有效 | |
| Artificial Analysis model aggregatevpublic-model-v1 | 生成速度tokens_per_second | 335.3 Token/s | Model Coordinate repository snapshots第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | SciCodefraction | 41.9% | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | Tau Bankingfraction | 8.7% | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | Terminal-Bench v2.1fraction | 31.1% | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis model aggregatevpublic-model-v1 | 首个回答 Token 等待seconds | 5.7 秒 | Model Coordinate repository snapshots第三方评测 | 有效 |