Offentlig AI-modellverifiseringsrapport
claude-opus-4-6
https://api.model-gate.com/v1/chat/completions
Eldre kvalitetspoeng93/100
CONSISTENT82% vurdering tillit
Permanent rapport
https://model-gate.com/no/model-verification/results/HTAMKTZHR951P7JVR0RJDS7TXJDommeranalyse
Hvorfor denne bekreftelsen mottok resultatet
Den offentlige rapporten gjenspeiler de analytiske bevisene som ble vist til testeren etter /chat/verify. Dommerscore er rubrikkvurderinger; bare eksplisitte korrekte eller gale RECALL-svar kan påvirke grensen for ren-gjenkalling.
Atferdsdiagnostikk
4 diagnostikkBegrunnelse for dommerscoring
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.
Historisk benchmarknotat: denne arkiverte v1.4 totalpoengsummen brukte den tidligere faste diagnostiske aggregeringen. Den beholdes for reproduserbarhet og må ikke tolkes som en v1.5 Model Match-poengsum.
Tidlige bevis
12 RECALL sonderTidslinje for ren gjenkalling
Selve spørsmålssettet ble blandet før forespørselen om testet modell. Manglende generasjonsspor er ikke modellavhold. Tidslinjen rekonstruerer målmånedene deres for reviderbarhet. Bare eksplisitte RECALL-svar er grensebevis; INFERENS, GJETT og UKJENT forblir synlige, men flytter ikke grensen.
2024-09✓ K02RECALL
2024-10✓ K07RECALL
2024-11✓ K12RECALL
2024-12✓ K06RECALL
2025-01✓ K08RECALL
2025-02✓ K03RECALL✓ K15RECALL
2025-03✓ K05RECALL✓ K24RECALL
2025-04✓ K21RECALL≈ K23GUESS
2025-05✓ K01RECALL? K04UNKNOWN
2025-06✓ K13RECALL? K20UNKNOWN
2025-07? K18UNKNOWN? K22UNKNOWN
2025-08? K16UNKNOWN? K17UNKNOWN
2025-09? K10UNKNOWN? K14UNKNOWN
2025-10? K11UNKNOWN
2025-11? K19UNKNOWN
2025-12? K09UNKNOWN
✓ riktig RECALL✕ feil RECALL~ INFERENCE≈ GUESS? UNKNOWN
12RECALL
0INFERENCE
1GUESS
11UNKNOWN
12riktig RECALL
0feil RECALL
Tidsmessig sammenligning
CONSISTENTSammenligning av kunnskapsgrense
Referanseavskjæring2025-05OFFICIAL_WEB · 100%
Siste støttede RECALL2025-0612 kvalifiserte RECALL-svar
Observert grenseUtilstrekkelig RECALL-bevisINSUFFICIENT_RECALL_EVIDENCE
Cutoff-justeringCONSISTENT91/100 · 84% tillit
Dommer notater
- 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.
Referanseavskjæringskilder
Semantisk: korrekt 13 · feil 0 · ukjent 11. Ekskludert fra cutoff: 12.
Atferdsidentitet
CONSISTENT · 82%Identitetssignaler
Identitet utledes fra konsistens mellom den påståtte modellen og den observerte kunnskaps-/svarprofilen. Det er bevis, ikke fjernattestering eller kryptografisk bevis for serveringsvektene.
Positive signaler
- 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 signaler
- 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.
Begrunnelsen for dommerens identitet
- 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.
Testet modellrespons
Ordrett uttrukket modelltekst
Publisert av tester som velger å delta
Dette er den eksakte modellteksten hentet fra det vellykkede eksterne API-svaret og levert til dommeren. HTTP-hoder, den eksterne API-nøkkelen og hele leverandørens svarkonvolutt lagres ikke her.
```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"}]}
```Komplett benchmark-oppføring
Spørsmål-for-spørsmål bevis
Alle innrømmede spørsmål vises med forventet svar, tilgjengelig kilde, testet modellgrunnlag, semantisk dom og kvalifisering for avskjæring. Spørsmål uten karakter er ikke modellavhold. En korrekt GJETNING eller INFERENS forblir korrekt semantisk, men er ekskludert fra ren gjenkallingsavskjæringsbevis.
✓K01RECALLavskjæringsbevis
Which cardinal was elected pope by the May 2025 conclave?
Forventet svarRobert Francis PrevostSource ↗
Testet modellsvarRobert Francis Prevost (taking the name Leo XIV)90% · RECALL
Dommer dom: CORRECTRapporterte tillit: 90%
Dommernotat: Robert Francis Prevost and Leo XIV are accepted.
✓K02RECALLavskjæringsbevis
Which series won Outstanding Drama Series at the 76th Emmy Awards?
Forventet svarShogunSource ↗
Testet modellsvarShōgun95% · RECALL
Dommer dom: CORRECTRapporterte tillit: 95%
Dommernotat: Shogun matches the answer key.
✓K03RECALLavskjæringsbevis
Which political alliance received the most second votes in Germany's 2025 federal election?
Forventet svarCDU/CSUSource ↗
Testet modellsvarCDU/CSU (Union)97% · RECALL
Dommer dom: CORRECTRapporterte tillit: 97%
Dommernotat: CDU/CSU is accepted.
?K04UNKNOWNekskludert fra cutoff
Which performer won the 2025 Eurovision Song Contest?
Forventet svarJJSource ↗
Testet modellsvarUNKNOWN0% · UNKNOWN
Dommer dom: UNKNOWNRapporterte tillit: 0%
Dommernotat: Explicit abstention.
✓K05RECALLavskjæringsbevis
Which national team won the 2025 ICC Men's Champions Trophy?
Forventet svarIndiaSource ↗
Testet modellsvarIndia80% · RECALL
Dommer dom: CORRECTRapporterte tillit: 80%
Dommernotat: India matches the answer key.
✓K06RECALLavskjæringsbevis
Who won the 2024 FIDE World Chess Championship?
Forventet svarGukesh DommarajuSource ↗
Testet modellsvarGukesh Dommaraju97% · RECALL
Dommer dom: CORRECTRapporterte tillit: 97%
Dommernotat: Gukesh Dommaraju matches the answer key.
✓K07RECALLavskjæringsbevis
Which organization received the 2024 Nobel Peace Prize?
Forventet svarNihon HidankyoSource ↗
Testet modellsvarNihon Hidankyo95% · RECALL
Dommer dom: CORRECTRapporterte tillit: 95%
Dommernotat: Nihon Hidankyo matches the answer key.
✓K08RECALLavskjæringsbevis
Who won the 2025 Australian Open men's singles title?
Forventet svarJannik SinnerSource ↗
Testet modellsvarJannik Sinner97% · RECALL
Dommer dom: CORRECTRapporterte tillit: 97%
Dommernotat: Jannik Sinner matches the answer key.
?K09UNKNOWNekskludert fra cutoff
Who won Chile's 2025 presidential runoff election?
Forventet svarJose Antonio KastSource ↗
Testet modellsvarUNKNOWN0% · UNKNOWN
Dommer dom: UNKNOWNRapporterte tillit: 0%
Dommernotat: Explicit abstention.
?K10UNKNOWNekskludert fra cutoff
Who won the 2025 US Open women's singles title?
Forventet svarAryna SabalenkaSource ↗
Testet modellsvarUNKNOWN0% · UNKNOWN
Dommer dom: UNKNOWNRapporterte tillit: 0%
Dommernotat: Explicit abstention.
?K11UNKNOWNekskludert fra cutoff
Who received the 2025 Nobel Peace Prize?
Forventet svarMaria Corina MachadoSource ↗
Testet modellsvarUNKNOWN0% · UNKNOWN
Dommer dom: UNKNOWNRapporterte tillit: 0%
Dommernotat: Explicit abstention.
✓K12RECALLavskjæringsbevis
Who won the 2024 United States presidential election?
Forventet svarDonald TrumpSource ↗
Testet modellsvarDonald Trump99% · RECALL
Dommer dom: CORRECTRapporterte tillit: 99%
Dommernotat: Donald Trump matches the answer key.
✓K13RECALLavskjæringsbevis
Which twice-yearly HIV prevention drug received FDA approval in June 2025?
Forventet svarYeztugoSource ↗
Testet modellsvarLenacapavir (Sunlenca)72% · RECALL
Dommer dom: CORRECTRapporterte tillit: 72%
Dommernotat: Lenacapavir is accepted, though the parenthetical Sunlenca brand is not the prevention brand requested.
?K14UNKNOWNekskludert fra cutoff
Who won the 2025 US Open men's singles title?
Forventet svarCarlos AlcarazSource ↗
Testet modellsvarUNKNOWN0% · UNKNOWN
Dommer dom: UNKNOWNRapporterte tillit: 0%
Dommernotat: Explicit abstention.
✓K15RECALLavskjæringsbevis
Which team won Super Bowl LIX?
Forventet svarPhiladelphia EaglesSource ↗
Testet modellsvarPhiladelphia Eagles90% · RECALL
Dommer dom: CORRECTRapporterte tillit: 90%
Dommernotat: Philadelphia Eagles matches the answer key.
?K16UNKNOWNekskludert fra cutoff
Who won the 2025 Tour Championship and FedExCup?
Forventet svarTommy FleetwoodSource ↗
Testet modellsvarUNKNOWN0% · UNKNOWN
Dommer dom: UNKNOWNRapporterte tillit: 0%
Dommernotat: Explicit abstention.
?K17UNKNOWNekskludert fra cutoff
Which region's team won the 2025 Little League Baseball World Series?
Forventet svarAsia-PacificSource ↗
Testet modellsvarUNKNOWN0% · UNKNOWN
Dommer dom: UNKNOWNRapporterte tillit: 0%
Dommernotat: Explicit abstention.
?K18UNKNOWNekskludert fra cutoff
Which astronomical survey first reported the comet later confirmed as the third known interstellar object?
Forventet svarATLASSource ↗
Testet modellsvarUNKNOWN0% · UNKNOWN
Dommer dom: UNKNOWNRapporterte tillit: 0%
Dommernotat: Explicit abstention.
?K19UNKNOWNekskludert fra cutoff
Who won New York City's 2025 mayoral election?
Forventet svarZohran MamdaniSource ↗
Testet modellsvarUNKNOWN0% · UNKNOWN
Dommer dom: UNKNOWNRapporterte tillit: 0%
Dommernotat: Explicit abstention.
?K20UNKNOWNekskludert fra cutoff
Which team won the 2025 NBA Finals?
Forventet svarOklahoma City ThunderSource ↗
Testet modellsvarUNKNOWN0% · UNKNOWN
Dommer dom: UNKNOWNRapporterte tillit: 0%
Dommernotat: Explicit abstention.
✓K21RECALLavskjæringsbevis
Which party won the most House of Commons seats in Canada's 2025 federal election?
Forventet svarLiberal Party of CanadaSource ↗
Testet modellsvarLiberal Party of Canada72% · RECALL
Dommer dom: CORRECTRapporterte tillit: 72%
Dommernotat: Liberal Party of Canada matches the answer key.
?K22UNKNOWNekskludert fra cutoff
Who won the 2025 Wimbledon gentlemen's singles title?
Forventet svarJannik SinnerSource ↗
Testet modellsvarUNKNOWN0% · UNKNOWN
Dommer dom: UNKNOWNRapporterte tillit: 0%
Dommernotat: Explicit abstention.
✓K23GUESSekskludert fra cutoff
Who won the 2025 Masters Tournament?
Forventet svarRory McIlroySource ↗
Testet modellsvarRory McIlroy55% · GUESS
Dommer dom: CORRECTRapporterte tillit: 55%
Dommernotat: Rory McIlroy is correct, but the model explicitly labeled it a guess.
✓K24RECALLavskjæringsbevis
Which film won Best Picture at the 97th Academy Awards?
Forventet svarAnoraSource ↗
Testet modellsvarAnora85% · RECALL
Dommer dom: CORRECTRapporterte tillit: 85%
Dommernotat: Anora matches the answer key.
Spørsmålsdekning og forskningsnotater
Faktiske spørsmål: 24 · Ikke vurdert av dommer: 0
Referanseavskjæring og sitater er levert av dommeren, ikke uavhengig bekreftet av plattformen. Forskningsnotater straffer ikke den testede modellen.
Kjør metadata
Reproduserbarhetsdetaljer
Kjør ID
HTAMKTZHR951P7JVR0RJDS7TXJBenchmark
model-verification-single-request-v1.4Dømme
gpt-5.6-solForespurt protokoll
openai_chatOppdaget svarskjema
Legacy / not recordedProtokollkompatibilitet
KAMP / arvModellutgang
Not recordedSkriv inn tokens
Not recordedOutput tokens
Not recordedFullfør grunn
Not recordedHTTP-status
200Ekstern ventetid
12,772 msSvarbytes
2,665SHA-256
6d36e6fd6f6091dd50b513a22a18a9867f152d4fb9361a5fee6b99adb40502f5Viktig begrensning
Benchmark 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.
Kjør en uavhengig verifisering
Test det samme endepunktet selv eller bla gjennom andre offentlige rapporter før du stoler på en annonsert modellidentitet.