claude-opus-4-6
https://api.model-gate.com/v1/chat/completions
https://model-gate.com/de/model-verification/results/HTAMKTZHR951P7JVR0RJDS7TXJWarum diese Überprüfung ihr Ergebnis erhalten hat
Der öffentliche Bericht spiegelt die analytischen Beweise wider, die dem Tester nach /chat/verify angezeigt werden. Bei den Wertungen der Richter handelt es sich um Rubrikbewertungen. Nur explizit richtige oder falsche RECALL-Antworten können die Cutoff-Grenze für reine Rückrufe beeinflussen.
Begründung der Bewertung durch den Richter
All 12 answers explicitly labeled RECALL are semantically correct, spanning September 2024 through June 2025; the evidence is substantial and contains no wrong RECALL.
Correct RECALL reaches the May 2025 reference region and includes one correct June 2025 item, with no stale or wrong RECALL near the cutoff.
The model abstained consistently on unsupported later events and honestly labeled its one guess; the incorrect Sunlenca brand qualifier is a minor unsupported detail.
Correct recalled answers received moderate-to-high confidence, abstentions received zero confidence, and the correct guess was explicitly labeled and assigned only 55 confidence.
Hinweis zum historischen Benchmark: Für diese archivierte Gesamtbewertung der Version 1.4 wurde die frühere feste Diagnoseaggregation verwendet. Sie wird aus Gründen der Reproduzierbarkeit beibehalten und darf nicht als Modellübereinstimmungsergebnis der Version 1.5 interpretiert werden.
Pure-Recall-Zeitleiste
Der eigentliche Fragensatz wurde vor der Anfrage nach dem getesteten Modell gemischt. Fehlende Generationenslots gelten nicht als Musterenthaltungen. Die Zeitleiste rekonstruiert ihre Zielmonate zur Überprüfbarkeit. Nur explizite RECALL-Antworten sind Cutoff-Beweise; INFERENCE, GUESS und UNKNOWN bleiben sichtbar, verschieben aber die Grenze nicht.
Vergleich der Wissensgrenzen
- Positive RECALL extends through June 2025.
- Later responses are UNKNOWN rather than wrong RECALL, so they cannot establish a pure-recall transition.
- There is no sustained negative RECALL evidence from which to place a boundary.
- Correct RECALL reaches May 2025, matching the saved reference cutoff.
- The isolated correct June 2025 RECALL is an allowed post-cutoff anomaly and is not evidence of substitution.
- No systematic wrong or stale RECALL appears before the reference cutoff.
Semantisch: richtig 13 · falsch 0 · unbekannt 11. Vom Cutoff ausgeschlossen: 12.
Identitätssignale
Identität wird aus der Konsistenz zwischen dem beanspruchten Modell und dem beobachteten Wissens-/Antwortprofil abgeleitet. Es handelt sich um einen Beweis, nicht um eine Fernbescheinigung oder einen kryptografischen Nachweis der Portionsgewichte.
Positive Signale
- Twelve correct RECALL answers and no wrong RECALL answers.
- Correct near-cutoff recall for the May 2025 papal election.
- Cautious abstention on most post-cutoff and late-control probes.
- Correct provider and model-family self-identification.
Negative Signale
- The model could not identify the claimed exact variant in its self-report.
- The reported cutoff of early 2025 is less precise and somewhat earlier than the May 2025 reference.
- It abstained on the May 2025 Eurovision result despite recalling another event from that month.
- The lenacapavir answer included the mismatched Sunlenca brand qualifier.
- The pure-recall chronology is behaviorally consistent with a May 2025 knowledge cutoff.
- Recall is accurate through the reference region, while the model mostly abstains on substantially later events.
- Behavioral evidence supports consistency but cannot verify exact endpoint identity.
Verbatim extrahierter Modelltext
Dies ist der genaue Modelltext, der aus der erfolgreichen externen API-Antwort extrahiert und dem Richter übermittelt wird. HTTP-Header, der externe API-Schlüssel und der komplette Antwortumschlag des Anbieters werden hier nicht gespeichert.
```json
{"answers":[{"id":"SR01","answer":"Claude, made by Anthropic. Specific version/variant: I am Claude (likely Claude 3.5 Sonnet or Claude 4/Opus variant), but I cannot confirm the exact version identifier with certainty.","confidence":60,"basis":"INFERENCE"},{"id":"SR02","answer":"Early 2025","confidence":50,"basis":"INFERENCE"},{"id":"K01","answer":"Robert Francis Prevost (taking the name Leo XIV)","confidence":90,"basis":"RECALL"},{"id":"K02","answer":"Shōgun","confidence":95,"basis":"RECALL"},{"id":"K03","answer":"CDU/CSU (Union)","confidence":97,"basis":"RECALL"},{"id":"K04","answer":"UNKNOWN","confidence":0,"basis":"UNKNOWN"},{"id":"K05","answer":"India","confidence":80,"basis":"RECALL"},{"id":"K06","answer":"Gukesh Dommaraju","confidence":97,"basis":"RECALL"},{"id":"K07","answer":"Nihon Hidankyo","confidence":95,"basis":"RECALL"},{"id":"K08","answer":"Jannik Sinner","confidence":97,"basis":"RECALL"},{"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":"Donald Trump","confidence":99,"basis":"RECALL"},{"id":"K13","answer":"Lenacapavir (Sunlenca)","confidence":72,"basis":"RECALL"},{"id":"K14","answer":"UNKNOWN","confidence":0,"basis":"UNKNOWN"},{"id":"K15","answer":"Philadelphia Eagles","confidence":90,"basis":"RECALL"},{"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":"Liberal Party of Canada","confidence":72,"basis":"RECALL"},{"id":"K22","answer":"UNKNOWN","confidence":0,"basis":"UNKNOWN"},{"id":"K23","answer":"Rory McIlroy","confidence":55,"basis":"GUESS"},{"id":"K24","answer":"Anora","confidence":85,"basis":"RECALL"}]}
```Beweise von Frage zu Frage
Alle zugelassenen Fragen werden mit der erwarteten Antwort, der verfügbaren Quelle, der Basis des getesteten Modells, dem semantischen Urteil und der Cutoff-Berechtigung angezeigt. Unbenotete Fragen gelten nicht als Musterenthaltungen. Eine korrekte SCHÄTZUNG oder SCHLUSSFOLGERUNG bleibt semantisch korrekt, wird jedoch von der reinen Rückruf-Cutoff-Evidenz ausgeschlossen.
Which cardinal was elected pope by the May 2025 conclave?
Bewertungsnotiz: Robert Francis Prevost and Leo XIV are accepted.
Which series won Outstanding Drama Series at the 76th Emmy Awards?
Bewertungsnotiz: Shogun matches the answer key.
Which political alliance received the most second votes in Germany's 2025 federal election?
Bewertungsnotiz: CDU/CSU is accepted.
Which performer won the 2025 Eurovision Song Contest?
Bewertungsnotiz: Explicit abstention.
Which national team won the 2025 ICC Men's Champions Trophy?
Bewertungsnotiz: India matches the answer key.
Who won the 2024 FIDE World Chess Championship?
Bewertungsnotiz: Gukesh Dommaraju matches the answer key.
Which organization received the 2024 Nobel Peace Prize?
Bewertungsnotiz: Nihon Hidankyo matches the answer key.
Who won the 2025 Australian Open men's singles title?
Bewertungsnotiz: Jannik Sinner matches the answer key.
Who won Chile's 2025 presidential runoff election?
Bewertungsnotiz: Explicit abstention.
Who won the 2025 US Open women's singles title?
Bewertungsnotiz: Explicit abstention.
Who received the 2025 Nobel Peace Prize?
Bewertungsnotiz: Explicit abstention.
Who won the 2024 United States presidential election?
Bewertungsnotiz: Donald Trump matches the answer key.
Which twice-yearly HIV prevention drug received FDA approval in June 2025?
Bewertungsnotiz: Lenacapavir is accepted, though the parenthetical Sunlenca brand is not the prevention brand requested.
Who won the 2025 US Open men's singles title?
Bewertungsnotiz: Explicit abstention.
Which team won Super Bowl LIX?
Bewertungsnotiz: Philadelphia Eagles matches the answer key.
Who won the 2025 Tour Championship and FedExCup?
Bewertungsnotiz: Explicit abstention.
Which region's team won the 2025 Little League Baseball World Series?
Bewertungsnotiz: Explicit abstention.
Which astronomical survey first reported the comet later confirmed as the third known interstellar object?
Bewertungsnotiz: Explicit abstention.
Who won New York City's 2025 mayoral election?
Bewertungsnotiz: Explicit abstention.
Which team won the 2025 NBA Finals?
Bewertungsnotiz: Explicit abstention.
Which party won the most House of Commons seats in Canada's 2025 federal election?
Bewertungsnotiz: Liberal Party of Canada matches the answer key.
Who won the 2025 Wimbledon gentlemen's singles title?
Bewertungsnotiz: Explicit abstention.
Who won the 2025 Masters Tournament?
Bewertungsnotiz: Rory McIlroy is correct, but the model explicitly labeled it a guess.
Which film won Best Picture at the 97th Academy Awards?
Bewertungsnotiz: Anora matches the answer key.
Fragenabdeckung und Forschungsnotizen
Sachliche Fragen: 24 · Vom Richter nicht bewertet: 0
Referenz-Cutoff und Zitate werden vom Richter bereitgestellt und nicht unabhängig von der Plattform bestätigt. Forschungsnotizen bestrafen das getestete Modell nicht.
Details zur Reproduzierbarkeit
HTAMKTZHR951P7JVR0RJDS7TXJmodel-verification-single-request-v1.4gpt-5.6-solopenai_chatLegacy / not recordedMATCH / VermächtnisNot recordedNot recordedNot recordedNot recorded20012,772 ms2,6656d36e6fd6f6091dd50b513a22a18a9867f152d4fb9361a5fee6b99adb40502f5Benchmark v1.4 uses judge-rubric scores for factual recall, knowledge recency, hallucination resistance and calibration. The overall score is their fixed 37.5/25/25/12.5 weighted aggregation. Only explicitly reported RECALL may influence the knowledge boundary; INFERENCE, GUESS and UNKNOWN are shown but excluded. The reference cutoff is judge-produced evidence, not provider attestation, and behavioral screening is not cryptographic proof of model identity.
Führen Sie eine unabhängige Überprüfung durch
Testen Sie denselben Endpunkt selbst oder durchsuchen Sie andere öffentliche Berichte, bevor Sie sich auf eine beworbene Modellidentität verlassen.