← 公共验证登记处model-verification-single-request-v1.3
公开AI模型验证报告

claude-opus-4-6

https://api.model-gate.com/v1/chat/completions

openai_chatgpt-5.6-solSep 7, 2026 19:26 UTC
旧版质量得分60/100
CONSISTENT88% 评估置信度
永久报告https://model-gate.com/zh/model-verification/results/68TGGQW6SM9411Y4XDAPH3BR3H
Telegram ↗X ↗
事实回忆67
知识新近度67
抗幻觉89
校准74
声称型号claude-opus-4-6
法官解决模型Claude Opus 4.6Anthropic
端点主机api.model-gate.com
外部响应模型字段claude-opus-4-6
评判分析

为什么此验证收到结果

公开报告反映了 /chat/verify 之后向测试人员显示的分析证据。评委评分为评分标准;只有明确的正确或错误的回忆答案可能会影响纯回忆截止边界。

行为诊断

评委评分依据

4 诊断
事实回忆67/100

该存档结果没有保留单独的法官理由。

知识新近度67/100

该存档结果没有保留单独的法官理由。

抗幻觉89/100

该存档结果没有保留单独的法官理由。

校准74/100

该存档结果没有保留单独的法官理由。

历史基准说明:此存档的 v1.4 总体分数使用了以前的固定诊断聚合。保留它是为了再现性,并且不得将其解释为 v1.5 模型匹配分数。

时间证据

纯粹回忆时间线

0 召回探针

实际问题集在测试模型请求之前被打乱。缺席一代并不是典型的弃权。该时间表重建了可审计性的目标月份。只有明确的 RECALL 答案才是截止证据;推论、猜测和未知仍然可见,但不会移动边界。

2024-09? K20UNKNOWN
2024-10? K14UNKNOWN
2024-11? K13UNKNOWN
2024-12? K22UNKNOWN
2025-01? K02UNKNOWN
2025-02? K10UNKNOWN? K18UNKNOWN
2025-03? K01UNKNOWN? K17UNKNOWN
2025-04? K03UNKNOWN? K16UNKNOWN
2025-05? K07UNKNOWN? K11UNKNOWN
2025-06? K09UNKNOWN? K21UNKNOWN
2025-07? K15UNKNOWN? K19UNKNOWN
2025-08? K06UNKNOWN? K24UNKNOWN
2025-09? K04UNKNOWN? K12UNKNOWN
2025-10? K05UNKNOWN
2025-11? K08UNKNOWN
2025-12? K23UNKNOWN
正确回忆 错误回忆~ INFERENCE GUESS? UNKNOWN
0RECALL
0INFERENCE
0GUESS
0UNKNOWN
0正确回忆
0错误回忆
时间比较

知识截止比较

CONSISTENT
参考截止值2025-05OFFICIAL_WEB · 100%
最新支持的 RECALL0 符合条件的回忆答案
观察边界召回证据不足INSUFFICIENT_RECALL_EVIDENCE
截止对齐CONSISTENT88/100 · 87% 信心
法官笔记
  • Recall is broadly strong from September 2024 through April 2025, with only one isolated February abstention.
  • May is mixed across its dense probes, while June and July retain partial or strong knowledge before a sustained failure cluster in August and September.
  • The observed transition range overlaps and immediately follows the official May 2025 reference cutoff.
  • Correct later-control answers in October and November are isolated; the COP30 host was also knowable well before the event, so these do not establish a later sustained boundary.

语义学: 正确的 16 · 错误的 2 · 未知 6. 排除在截止范围之外: 0.

行为认同

身份信号

CONSISTENT · 88%

身份是根据所声称的模型与观察到的知识/答案概况之间的一致性推断出来的。它是证据,而不是份量的远程证明或加密证明。

积极信号

  • Correct on nearly all probes from September 2024 through April 2025.
  • Mixed near-boundary performance in May.
  • Sustained weak performance across both August and September dense evidence.
  • Self-identifies as an Anthropic Claude model.

负面信号

  • Missed the February 2025 Album of the Year despite otherwise strong pre-cutoff recall.
  • Answered several June and July events correctly after the nominal cutoff.
  • Correctly guessed the October 2025 Nobel Peace Prize recipient.
  • Did not identify its exact version and supplied no cutoff self-report.
法官身份理由
  • The behavioral boundary broadly aligns with the immutable May 2025 reference cutoff.
  • Strong-recall performance is consistently high across most months before the reference cutoff.
  • The August-September failure cluster supplies a meaningful temporal transition rather than relying on one obscure missed fact.
  • Limited post-cutoff knowledge is not treated as proof of substitution and is compatible with inference, advance-publicized facts, or selective updates.
  • The self-report supports the provider family but does not independently establish the exact model variant.
测试模型响应

逐字提取模型文本

存档摘要

此运行早于选择保留完整报告的时间。挑战、答案关键和规范化的法官评估都是可用的,但基准时代的隐私政策故意丢弃了确切的测试模型响应文本。

完整的基准列表

逐个问题的证据

所有承认的问题都会显示预期答案、可用来源、测试模型基础、语义判决和截止资格。未评分的问题不是典型的弃权问题。正确的猜测或推理在语义上仍然是正确的,但被排除在纯回忆截止证据之外。

K01UNKNOWN排除在截止之外

What was the name of Firefly Aerospace's lunar lander that successfully touched down on the Moon?

预期答案Blue GhostSource ↗
测试模型答案此存档运行未保留精确的模型响应。
法官判决: CORRECT报告信心: 85%

法官笔记: Matches Blue Ghost.

K02UNKNOWN排除在截止之外

What was the name of Blue Origin's rocket that reached orbit on its maiden flight?

预期答案New GlennSource ↗
测试模型答案此存档运行未保留精确的模型响应。
法官判决: CORRECT报告信心: 90%

法官笔记: Matches New Glenn.

K03UNKNOWN排除在截止之外

What was the designation of the Blue Origin mission that carried an all-women crew including Katy Perry and Gayle King?

预期答案NS-31Source ↗
测试模型答案此存档运行未保留精确的模型响应。
法官判决: CORRECT报告信心: 45%

法官笔记: Matches NS-31.

?K04UNKNOWN排除在截止之外

Who won the men's 100 metres at the 2025 World Athletics Championships in Tokyo?

预期答案Oblique SevilleSource ↗
测试模型答案此存档运行未保留精确的模型响应。
法官判决: UNKNOWN报告信心: 0%

法官笔记: Explicit abstention.

K05UNKNOWN排除在截止之外

Which Venezuelan opposition leader was awarded the 2025 Nobel Peace Prize?

预期答案Maria Corina MachadoSource ↗
测试模型答案此存档运行未保留精确的模型响应。
法官判决: CORRECT报告信心: 60%

法官笔记: Matches Maria Corina Machado.

?K06UNKNOWN排除在截止之外

At which Alaska military installation did Donald Trump meet Vladimir Putin for their 2025 summit?

预期答案Joint Base Elmendorf-RichardsonSource ↗
测试模型答案此存档运行未保留精确的模型响应。
法官判决: UNKNOWN报告信心: 0%

法官笔记: Explicit abstention.

K07UNKNOWN排除在截止之外

What landmark global health instrument did the World Health Assembly adopt?

预期答案WHO Pandemic AgreementSource ↗
测试模型答案此存档运行未保留精确的模型响应。
法官判决: CORRECT报告信心: 55%

法官笔记: Explicitly includes WHO Pandemic Agreement.

K08UNKNOWN排除在截止之外

Which Brazilian city hosted the COP30 climate conference?

预期答案BelemSource ↗
测试模型答案此存档运行未保留精确的模型响应。
法官判决: CORRECT报告信心: 90%

法官笔记: Matches Belem.

K09UNKNOWN排除在截止之外

Which new Nintendo console launched alongside Mario Kart World?

预期答案Nintendo Switch 2Source ↗
测试模型答案此存档运行未保留精确的模型响应。
法官判决: CORRECT报告信心: 85%

法官笔记: Matches Nintendo Switch 2.

?K10UNKNOWN排除在截止之外

Which album won Album of the Year at the 67th Grammy Awards?

预期答案Cowboy CarterSource ↗
测试模型答案此存档运行未保留精确的模型响应。
法官判决: UNKNOWN报告信心: 0%

法官笔记: Explicit abstention.

?K11UNKNOWN排除在截止之外

Which performer won the 2025 Eurovision Song Contest for Austria with Wasted Love?

预期答案JJSource ↗
测试模型答案此存档运行未保留精确的模型响应。
法官判决: UNKNOWN报告信心: 0%

法官笔记: Explicit abstention.

K12UNKNOWN排除在截止之外

Which numbered iPhone generation did Apple debut at its September product event?

预期答案iPhone 17Source ↗
测试模型答案此存档运行未保留精确的模型响应。
法官判决: WRONG报告信心: 75%

法官笔记: Answered iPhone 16; expected iPhone 17.

K13UNKNOWN排除在截止之外

Which city hosted the COP29 climate conference that concluded with a new climate-finance agreement?

预期答案BakuSource ↗
测试模型答案此存档运行未保留精确的模型响应。
法官判决: CORRECT报告信心: 92%

法官笔记: Matches Baku.

K14UNKNOWN排除在截止之外

Which Japanese organization was awarded the 2024 Nobel Peace Prize?

预期答案Nihon HidankyoSource ↗
测试模型答案此存档运行未保留精确的模型响应。
法官判决: CORRECT报告信心: 95%

法官笔记: Matches Nihon Hidankyo.

?K15UNKNOWN排除在截止之外

Which national team defeated Spain on penalties to win UEFA Women's Euro 2025?

预期答案EnglandSource ↗
测试模型答案此存档运行未保留精确的模型响应。
法官判决: UNKNOWN报告信心: 0%

法官笔记: Explicit abstention.

K16UNKNOWN排除在截止之外

Which pope died at the Vatican on Easter Monday 2025?

预期答案Pope FrancisSource ↗
测试模型答案此存档运行未保留精确的模型响应。
法官判决: CORRECT报告信心: 85%

法官笔记: Matches Pope Francis.

K17UNKNOWN排除在截止之外

Which film won Best Picture at the 97th Academy Awards?

预期答案AnoraSource ↗
测试模型答案此存档运行未保留精确的模型响应。
法官判决: CORRECT报告信心: 65%

法官笔记: Matches Anora.

K18UNKNOWN排除在截止之外

Which political alliance became the largest group in Germany's 2025 Bundestag election?

预期答案CDU/CSUSource ↗
测试模型答案此存档运行未保留精确的模型响应。
法官判决: CORRECT报告信心: 85%

法官笔记: Matches CDU/CSU.

K19UNKNOWN排除在截止之外

Which network of Indian forts became the country's 44th UNESCO World Heritage property?

预期答案Maratha Military Landscapes of IndiaSource ↗
测试模型答案此存档运行未保留精确的模型响应。
法官判决: CORRECT报告信心: 50%

法官笔记: Matches Maratha Military Landscapes of India.

K20UNKNOWN排除在截止之外

Which mission conducted the first commercial spacewalk?

预期答案Polaris DawnSource ↗
测试模型答案此存档运行未保留精确的模型响应。
法官判决: CORRECT报告信心: 92%

法官笔记: Matches Polaris Dawn.

K21UNKNOWN排除在截止之外

Which private astronaut mission launched Peggy Whitson and Shubhanshu Shukla to the International Space Station?

预期答案Axiom Mission 4Source ↗
测试模型答案此存档运行未保留精确的模型响应。
法官判决: CORRECT报告信心: 70%

法官笔记: Matches Axiom Mission 4.

K22UNKNOWN排除在截止之外

Which Paris cathedral formally reopened five years after a devastating fire?

预期答案Notre-Dame de ParisSource ↗
测试模型答案此存档运行未保留精确的模型响应。
法官判决: CORRECT报告信心: 97%

法官笔记: Matches Notre-Dame de Paris.

?K23UNKNOWN排除在截止之外

Who won Chile's 2025 presidential runoff election?

预期答案Jose Antonio KastSource ↗
测试模型答案此存档运行未保留精确的模型响应。
法官判决: UNKNOWN报告信心: 0%

法官笔记: Explicit abstention.

K24UNKNOWN排除在截止之外

What new flagship AI system did OpenAI introduce?

预期答案GPT-5Source ↗
测试模型答案此存档运行未保留精确的模型响应。
法官判决: WRONG报告信心: 40%

法官笔记: Answered GPT-4o; expected GPT-5.

问题范围和研究笔记

事实问题: 24 · 没有被评委打分: 0

参考截止值和引文由法官提供,未经平台独立确认。研究笔记不会惩罚测试模型。

运行元数据

再现性细节

运行ID68TGGQW6SM9411Y4XDAPH3BR3H
基准model-verification-single-request-v1.3
法官gpt-5.6-sol
请求的协议openai_chat
检测到的响应模式Legacy / not recorded
协议兼容性比赛/遗产
模型输出Not recorded
输入令牌Not recorded
输出代币Not recorded
完成原因Not recorded
HTTP状态200
外部延迟10,087 ms
响应字节2,591
SHA-25637edfee0969ea8c1529cf6db6830118353b483a27995cedcf20b25e5b40b8ff1
重要限制

The reference cutoff is a judge-produced snapshot grounded in hosted web evidence when available (official sources preferred, otherwise the best defensible estimate). It is not provider attestation. Single-request behavioral screening is not cryptographic proof of the underlying model identity.

运行独立验证

在依赖广告模型标识之前,请自行测试同一端点或浏览其他公开报告。