claude-opus-5
https://madclaude.cloud/v1/messages
https://model-gate.com/pt/model-verification/results/V8Y3ZFEZK23179GX0M3MN6D36FPor que esta verificação recebeu seu resultado
O relatório público reflete a evidência analítica mostrada ao testador após /chat/verify. As pontuações dos juízes são avaliações de rubricas; apenas respostas RECALL corretas ou erradas explícitas podem influenciar o limite de corte de recordação pura.
Justificativa de pontuação do juiz
No factual probe contains usable RECALL evidence or a correct demonstrated answer.
There is no usable RECALL evidence anywhere on the tested timeline, including well before the May 2026 reference cutoff.
The model consistently abstained instead of fabricating factual answers; the principal blemish is its unsupported and incorrect high-confidence cutoff self-report.
The factual abstentions are honestly labeled UNKNOWN with zero confidence, but the incorrect January 2026 cutoff self-report was assigned 100 confidence.
Os benchmarks de correspondência de modelo não calculam a média dessas quatro pontuações de diagnóstico na identidade do modelo. A pontuação principal do Model Match vem da rubrica de identidade do juiz; A resistência à alucinação e a calibração podem permanecer altas mesmo quando a correspondência do modelo reivindicado é muito baixa.
Linha do tempo de recall puro
O conjunto de perguntas real foi embaralhado antes da solicitação do modelo testado. Os slots de geração ausentes não são abstenções modelo. A linha do tempo reconstrói os meses-alvo para auditabilidade. Somente respostas RECALL explícitas são evidências de corte; INFERENCE, GUESS e UNKNOWN permanecem visíveis, mas não movem o limite.
Comparação de limite de conhecimento
- All 24 factual probes were explicit UNKNOWN responses.
- No RECALL item exists from which to infer a chronological transition.
- Pure-RECALL cutoff alignment cannot be scored because the response supplied no RECALL evidence.
- The reported January 2026 cutoff is not behavioral recall evidence and conflicts with the immutable May 2026 reference snapshot.
Semântica: correto 0 · incorreto 0 · desconhecido 24. Excluído do corte: 24.
Sinais de identidade
A identidade é inferida a partir da consistência entre o modelo reivindicado e o perfil de conhecimento/resposta observado. É uma evidência, não um atestado remoto ou prova criptográfica dos pesos da porção.
Sinais positivos
- The self-reported model name and provider match the claim, but self-report is weak identity evidence.
- The response avoided fabricated factual answers.
Sinais negativos
- Near-universal abstention includes all expected pre-cutoff knowledge probes.
- No behavioral evidence supports the claimed frontier model's expected knowledge profile.
- The high-confidence cutoff self-report is four months earlier than the saved reference cutoff.
Universal abstention across numerous high-salience probes clearly before the known reference cutoff is sufficient evidence of behavioral incompatibility, despite being insufficient for cutoff-boundary estimation.
- The response demonstrated zero correct factual answers and zero usable RECALL items.
- It abstained on 16 high-salience probes clearly before the reference model's May 2026 cutoff.
- It also abstained on both probes from the reference cutoff month.
- Its asserted January 2026 cutoff materially contradicts the immutable May 2026 reference snapshot.
Texto do modelo extraído literalmente
Este é o texto exato do modelo extraído da resposta externa da API bem-sucedida e fornecido ao juiz. Os cabeçalhos HTTP, a chave da API externa e o envelope completo de resposta do provedor não são armazenados aqui.
```json
{
"answers": [
{
"id": "SR01",
"answer": "claude-opus-5 by Anthropic",
"confidence": 95,
"basis": "RECALL"
},
{
"id": "SR02",
"answer": "2026-01",
"confidence": 100,
"basis": "RECALL"
},
{
"id": "K01",
"answer": "UNKNOWN",
"confidence": 0,
"basis": "UNKNOWN"
},
{
"id": "K02",
"answer": "UNKNOWN",
"confidence": 0,
"basis": "UNKNOWN"
},
{
"id": "K03",
"answer": "UNKNOWN",
"confidence": 0,
"basis": "UNKNOWN"
},
{
"id": "K04",
"answer": "UNKNOWN",
"confidence": 0,
"basis": "UNKNOWN"
},
{
"id": "K05",
"answer": "UNKNOWN",
"confidence": 0,
"basis": "UNKNOWN"
},
{
"id": "K06",
"answer": "UNKNOWN",
"confidence": 0,
"basis": "UNKNOWN"
},
{
"id": "K07",
"answer": "UNKNOWN",
"confidence": 0,
"basis": "UNKNOWN"
},
{
"id": "K08",
"answer": "UNKNOWN",
"confidence": 0,
"basis": "UNKNOWN"
},
{
"id": "K09",
"answer": "UNKNOWN",
"confidence": 0,
"basis": "UNKNOWN"
},
{
"id": "K10",
"answer": "UNKNOWN",
"confidence": 0,
"basis": "UNKNOWN"
},
{
"id": "K11",
"answer": "UNKNOWN",
"confidence": 0,
"basis": "UNKNOWN"
},
{
"id": "K12",
"answer": "UNKNOWN",
"confidence": 0,
"basis": "UNKNOWN"
},
{
"id": "K13",
"answer": "UNKNOWN",
"confidence": 0,
"basis": "UNKNOWN"
},
{
"id": "K14",
"answer": "UNKNOWN",
"confidence": 0,
"basis": "UNKNOWN"
},
{
"id": "K15",
"answer": "UNKNOWN",
"confidence": 0,
"basis": "UNKNOWN"
},
{
"id": "K16",
"answer": "UNKNOWN",
"confidence": 0,
"basis": "UNKNOWN"
},
{
"id": "K17",
"answer": "UNKNOWN",
"confidence": 0,
"basis": "UNKNOWN"
},
{
"id": "K18",
"answer": "UNKNOWN",
"confidence": 0,
"basis": "UNKNOWN"
},
{
"id": "K19",
"answer": "UNKNOWN",
"confidence": 0,
"basis": "UNKNOWN"
},
{
"id": "K20",
"answer": "UNKNOWN",
"confidence": 0,
"basis": "UNKNOWN"
},
{
"id": "K21",
"answer": "UNKNOWN",
"confidence": 0,
"basis": "UNKNOWN"
},
{
"id": "K22",
"answer": "UNKNOWN",
"confidence": 0,
"basis": "UNKNOWN"
},
{
"id": "K23",
"answer": "UNKNOWN",
"confidence": 0,
"basis": "UNKNOWN"
},
{
"id": "K24",
"answer": "UNKNOWN",
"confidence": 0,
"basis": "UNKNOWN"
}
]
}
```Evidência pergunta por pergunta
Todas as questões admitidas são mostradas com a resposta esperada, fonte disponível, base do modelo testado, veredicto semântico e elegibilidade de corte. Perguntas não avaliadas não são abstenções modelo. Uma GUESS ou INFERENCE correta permanece semanticamente correta, mas é excluída da evidência de corte de recordação pura.
Which film won Best Picture at the 98th Academy Awards?
Nota do avaliador: Explicit abstention.
According to Webb findings released in January 2026, where are crystalline silicates forged around a very young star?
Nota do avaliador: Explicit abstention.
Which team won Super Bowl LX?
Nota do avaliador: Explicit abstention.
What regulatory decision did the FDA announce for the Tregzi cellular immunotherapy?
Nota do avaliador: Explicit abstention.
Who won the 2026 Wimbledon men's singles title?
Nota do avaliador: Explicit abstention.
Who won the 2025 Tour Championship and FedExCup?
Nota do avaliador: Explicit abstention.
Which performer won the 2026 Eurovision Song Contest?
Nota do avaliador: Explicit abstention.
Which team won the 2025 NBA Finals?
Nota do avaliador: Explicit abstention.
Which country won the 2026 World Baseball Classic?
Nota do avaliador: Explicit abstention.
Which team won the 2026 NBA Finals?
Nota do avaliador: Explicit abstention.
Who won New York City's 2025 mayoral election?
Nota do avaliador: Explicit abstention.
Who won the 2026 Australian Open women's singles title?
Nota do avaliador: Explicit abstention.
Which club won the 2026 UEFA Super Cup?
Nota do avaliador: Explicit abstention.
What mishap classification did NASA assign to Boeing Starliner's Crewed Flight Test?
Nota do avaliador: Explicit abstention.
Which country won the 2026 FIFA World Cup?
Nota do avaliador: Explicit abstention.
Which club won the 2026 UEFA Champions League final?
Nota do avaliador: Explicit abstention.
Which country won the 2026 Little League Baseball World Series?
Nota do avaliador: Explicit abstention.
Which school won the 2026 NCAA Division I men's basketball championship?
Nota do avaliador: Explicit abstention.
Who won the 2026 Masters Tournament?
Nota do avaliador: Explicit abstention.
Who received the 2025 Nobel Peace Prize?
Nota do avaliador: Explicit abstention.
Who clinched the 2025 Formula One World Drivers' Championship?
Nota do avaliador: Explicit abstention.
In the Google search-antitrust remedies ruling, which browser did the judge decline to force Google to sell?
Nota do avaliador: Explicit abstention.
Which performer won the 2025 Eurovision Song Contest?
Nota do avaliador: Explicit abstention.
Who won the 2025 Wimbledon gentlemen's singles title?
Nota do avaliador: Explicit abstention.
Cobertura de perguntas e notas de pesquisa
Perguntas factuais: 24 · Não avaliado pelo juiz: 0
O corte de referência e as citações são fornecidos pelo juiz, não confirmados de forma independente pela plataforma. As notas de pesquisa não penalizam o modelo testado.
Detalhes de reprodutibilidade
V8Y3ZFEZK23179GX0M3MN6D36Fmodel-verification-single-request-v1.5gpt-5.6-solopenai_chatanthropic_messagesERRADO · recuperadoNot recordedNot recordedNot recordedNot recorded20019,443 ms3,6562989988b859c9bb90c50291bd34b6ed7423cf3b8c28c3d3915f4f245e99aaaebBenchmark v1.5 uses the judge's Model Match Score as the main Verification score. Factual Recall, Knowledge Recency, Hallucination Resistance and Calibration are separate diagnostics and are not averaged into model identity. Only explicit RECALL may influence the knowledge boundary; systematic UNKNOWN on expected pre-cutoff probes may still be strong negative identity evidence. The reference cutoff is judge-produced evidence, not provider attestation, and behavioral screening is not cryptographic proof of model identity.
Execute uma verificação independente
Teste você mesmo o mesmo endpoint ou navegue em outros relatórios públicos antes de confiar em uma identidade de modelo anunciada.