← Javni verifikacijski registarmodel-verification-single-request-v1.4
Javno izvješće o provjeri modela umjetne inteligencije

claude-opus-4-6

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

openai_chatgpt-5.6-solSep 8, 2026 07:11 UTC
Naslijeđena ocjena kvalitete93/100
CONSISTENT82% procjena povjerenje
Stalni izvještajhttps://model-gate.com/hr/model-verification/results/HTAMKTZHR951P7JVR0RJDS7TXJ
Telegram ↗X ↗
Podsjećanje na činjenice94
Najnovije znanje92
Otpornost na halucinacije94
Kalibriranje93
Tvrđeni modelclaude-opus-4-6
Sudac riješen modelClaude Opus 4.6Anthropic
Domaćin krajnje točkeapi.model-gate.com
Polje modela vanjskog odgovoraclaude-opus-4-6
Analiza sudaca

Zašto je ova provjera dobila svoj rezultat

Javno izvješće odražava analitičke dokaze prikazane testeru nakon /chat/verify. Ocjene sudaca su procjene rubrika; samo izričiti točni ili pogrešni odgovori RECALL mogu utjecati na granicu čistog prisjećanja.

Dijagnostika ponašanja

Obrazloženje suca za bodovanje

4 dijagnostika
Podsjećanje na činjenice94/100

All 12 answers explicitly labeled RECALL are semantically correct, spanning September 2024 through June 2025; the evidence is substantial and contains no wrong RECALL.

Najnovije znanje92/100

Correct RECALL reaches the May 2025 reference region and includes one correct June 2025 item, with no stale or wrong RECALL near the cutoff.

Otpornost na halucinacije94/100

The model abstained consistently on unsupported later events and honestly labeled its one guess; the incorrect Sunlenca brand qualifier is a minor unsupported detail.

Kalibriranje93/100

Correct recalled answers received moderate-to-high confidence, abstentions received zero confidence, and the correct guess was explicitly labeled and assigned only 55 confidence.

Povijesna usporedna bilješka: ovaj arhivirani ukupni rezultat v1.4 koristio je prijašnju fiksnu dijagnostičku agregaciju. Zadržava se radi ponovljivosti i ne smije se tumačiti kao rezultat podudaranja modela v1.5.

Vremenski dokaz

Vremenska linija čistog prisjećanja

12 POZIV sondi

Stvarni skup pitanja je promiješan prije zahtjeva testiranog modela. Slotovi za generaciju koji nedostaju nisu uzdržavanje modela. Vremenski slijed rekonstruira njihove ciljane mjesece za reviziju. Samo eksplicitni RECALL odgovori su granični dokaz; ZAKLJUČIVANJE, NAGAĐANJE i NEPOZNATO ostaju vidljivi ali ne pomiču granicu.

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
ispravan OPOZIV krivo OPOZIV~ INFERENCE GUESS? UNKNOWN
12RECALL
0INFERENCE
1GUESS
11UNKNOWN
12ispravan OPOZIV
0krivo OPOZIV
Vremenska usporedba

Usporedba graničnih vrijednosti znanja

CONSISTENT
Referentna granica2025-05OFFICIAL_WEB · 100%
Najnoviji podržani RECALL2025-0612 prihvatljivi odgovori OPOZIV
Promatrana granicaNedovoljni dokazi za PRISJEĆANJEINSUFFICIENT_RECALL_EVIDENCE
Poravnanje rezaCONSISTENT91/100 · 84% povjerenje
Bilješke suca
  • 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.

Semantički: ispraviti 13 · pogrešno 0 · nepoznato 11. Isključeno iz granične vrijednosti: 12.

Bihevioralni identitet

Signali identiteta

CONSISTENT · 82%

Identitet se zaključuje iz dosljednosti između navedenog modela i promatranog profila znanja/odgovora. To je dokaz, a ne daljinska potvrda ili kriptografski dokaz težine posluživanja.

Pozitivni signali

  • 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.

Negativni signali

  • 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.
Obrazloženje identiteta suca
  • 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.
Odziv testiranog modela

Doslovno izdvojeni tekst modela

Objavio tester opt-in

Ovo je točan tekst modela izdvojen iz uspješnog odgovora vanjskog API-ja i dostavljen sucu. HTTP zaglavlja, vanjski ključ API-ja i potpuna omotnica odgovora pružatelja nisu pohranjeni ovdje.

```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"}]}
```
Kompletan popis referentnih vrijednosti

Dokazi od pitanja do pitanja

Sva dopuštena pitanja prikazana su s očekivanim odgovorom, dostupnim izvorom, osnovom testiranog modela, semantičkom prosudbom i prihvatljivošću ograničenja. Neocjenjena pitanja nisu model suzdržavanja. Točna POGODBA ili ZAKLJUČAK ostaju ispravni semantički, ali se isključuju iz dokaza prekida čistog prisjećanja.

K01RECALLcutoff evidencija

Which cardinal was elected pope by the May 2025 conclave?

Očekivani odgovorRobert Francis PrevostSource ↗
Odgovor provjerenog modelaRobert Francis Prevost (taking the name Leo XIV)90% · RECALL
Presuda suca: CORRECTPrijavljeno povjerenje: 90%

Napomena suca: Robert Francis Prevost and Leo XIV are accepted.

K02RECALLcutoff evidencija

Which series won Outstanding Drama Series at the 76th Emmy Awards?

Očekivani odgovorShogunSource ↗
Odgovor provjerenog modelaShōgun95% · RECALL
Presuda suca: CORRECTPrijavljeno povjerenje: 95%

Napomena suca: Shogun matches the answer key.

K03RECALLcutoff evidencija

Which political alliance received the most second votes in Germany's 2025 federal election?

Očekivani odgovorCDU/CSUSource ↗
Odgovor provjerenog modelaCDU/CSU (Union)97% · RECALL
Presuda suca: CORRECTPrijavljeno povjerenje: 97%

Napomena suca: CDU/CSU is accepted.

?K04UNKNOWNisključeno iz prekida

Which performer won the 2025 Eurovision Song Contest?

Očekivani odgovorJJSource ↗
Odgovor provjerenog modelaUNKNOWN0% · UNKNOWN
Presuda suca: UNKNOWNPrijavljeno povjerenje: 0%

Napomena suca: Explicit abstention.

K05RECALLcutoff evidencija

Which national team won the 2025 ICC Men's Champions Trophy?

Očekivani odgovorIndiaSource ↗
Odgovor provjerenog modelaIndia80% · RECALL
Presuda suca: CORRECTPrijavljeno povjerenje: 80%

Napomena suca: India matches the answer key.

K06RECALLcutoff evidencija

Who won the 2024 FIDE World Chess Championship?

Očekivani odgovorGukesh DommarajuSource ↗
Odgovor provjerenog modelaGukesh Dommaraju97% · RECALL
Presuda suca: CORRECTPrijavljeno povjerenje: 97%

Napomena suca: Gukesh Dommaraju matches the answer key.

K07RECALLcutoff evidencija

Which organization received the 2024 Nobel Peace Prize?

Očekivani odgovorNihon HidankyoSource ↗
Odgovor provjerenog modelaNihon Hidankyo95% · RECALL
Presuda suca: CORRECTPrijavljeno povjerenje: 95%

Napomena suca: Nihon Hidankyo matches the answer key.

K08RECALLcutoff evidencija

Who won the 2025 Australian Open men's singles title?

Očekivani odgovorJannik SinnerSource ↗
Odgovor provjerenog modelaJannik Sinner97% · RECALL
Presuda suca: CORRECTPrijavljeno povjerenje: 97%

Napomena suca: Jannik Sinner matches the answer key.

?K09UNKNOWNisključeno iz prekida

Who won Chile's 2025 presidential runoff election?

Očekivani odgovorJose Antonio KastSource ↗
Odgovor provjerenog modelaUNKNOWN0% · UNKNOWN
Presuda suca: UNKNOWNPrijavljeno povjerenje: 0%

Napomena suca: Explicit abstention.

?K10UNKNOWNisključeno iz prekida

Who won the 2025 US Open women's singles title?

Očekivani odgovorAryna SabalenkaSource ↗
Odgovor provjerenog modelaUNKNOWN0% · UNKNOWN
Presuda suca: UNKNOWNPrijavljeno povjerenje: 0%

Napomena suca: Explicit abstention.

?K11UNKNOWNisključeno iz prekida

Who received the 2025 Nobel Peace Prize?

Očekivani odgovorMaria Corina MachadoSource ↗
Odgovor provjerenog modelaUNKNOWN0% · UNKNOWN
Presuda suca: UNKNOWNPrijavljeno povjerenje: 0%

Napomena suca: Explicit abstention.

K12RECALLcutoff evidencija

Who won the 2024 United States presidential election?

Očekivani odgovorDonald TrumpSource ↗
Odgovor provjerenog modelaDonald Trump99% · RECALL
Presuda suca: CORRECTPrijavljeno povjerenje: 99%

Napomena suca: Donald Trump matches the answer key.

K13RECALLcutoff evidencija

Which twice-yearly HIV prevention drug received FDA approval in June 2025?

Očekivani odgovorYeztugoSource ↗
Odgovor provjerenog modelaLenacapavir (Sunlenca)72% · RECALL
Presuda suca: CORRECTPrijavljeno povjerenje: 72%

Napomena suca: Lenacapavir is accepted, though the parenthetical Sunlenca brand is not the prevention brand requested.

?K14UNKNOWNisključeno iz prekida

Who won the 2025 US Open men's singles title?

Očekivani odgovorCarlos AlcarazSource ↗
Odgovor provjerenog modelaUNKNOWN0% · UNKNOWN
Presuda suca: UNKNOWNPrijavljeno povjerenje: 0%

Napomena suca: Explicit abstention.

K15RECALLcutoff evidencija

Which team won Super Bowl LIX?

Očekivani odgovorPhiladelphia EaglesSource ↗
Odgovor provjerenog modelaPhiladelphia Eagles90% · RECALL
Presuda suca: CORRECTPrijavljeno povjerenje: 90%

Napomena suca: Philadelphia Eagles matches the answer key.

?K16UNKNOWNisključeno iz prekida

Who won the 2025 Tour Championship and FedExCup?

Očekivani odgovorTommy FleetwoodSource ↗
Odgovor provjerenog modelaUNKNOWN0% · UNKNOWN
Presuda suca: UNKNOWNPrijavljeno povjerenje: 0%

Napomena suca: Explicit abstention.

?K17UNKNOWNisključeno iz prekida

Which region's team won the 2025 Little League Baseball World Series?

Očekivani odgovorAsia-PacificSource ↗
Odgovor provjerenog modelaUNKNOWN0% · UNKNOWN
Presuda suca: UNKNOWNPrijavljeno povjerenje: 0%

Napomena suca: Explicit abstention.

?K18UNKNOWNisključeno iz prekida

Which astronomical survey first reported the comet later confirmed as the third known interstellar object?

Očekivani odgovorATLASSource ↗
Odgovor provjerenog modelaUNKNOWN0% · UNKNOWN
Presuda suca: UNKNOWNPrijavljeno povjerenje: 0%

Napomena suca: Explicit abstention.

?K19UNKNOWNisključeno iz prekida

Who won New York City's 2025 mayoral election?

Očekivani odgovorZohran MamdaniSource ↗
Odgovor provjerenog modelaUNKNOWN0% · UNKNOWN
Presuda suca: UNKNOWNPrijavljeno povjerenje: 0%

Napomena suca: Explicit abstention.

?K20UNKNOWNisključeno iz prekida

Which team won the 2025 NBA Finals?

Očekivani odgovorOklahoma City ThunderSource ↗
Odgovor provjerenog modelaUNKNOWN0% · UNKNOWN
Presuda suca: UNKNOWNPrijavljeno povjerenje: 0%

Napomena suca: Explicit abstention.

K21RECALLcutoff evidencija

Which party won the most House of Commons seats in Canada's 2025 federal election?

Očekivani odgovorLiberal Party of CanadaSource ↗
Odgovor provjerenog modelaLiberal Party of Canada72% · RECALL
Presuda suca: CORRECTPrijavljeno povjerenje: 72%

Napomena suca: Liberal Party of Canada matches the answer key.

?K22UNKNOWNisključeno iz prekida

Who won the 2025 Wimbledon gentlemen's singles title?

Očekivani odgovorJannik SinnerSource ↗
Odgovor provjerenog modelaUNKNOWN0% · UNKNOWN
Presuda suca: UNKNOWNPrijavljeno povjerenje: 0%

Napomena suca: Explicit abstention.

K23GUESSisključeno iz prekida

Who won the 2025 Masters Tournament?

Očekivani odgovorRory McIlroySource ↗
Odgovor provjerenog modelaRory McIlroy55% · GUESS
Presuda suca: CORRECTPrijavljeno povjerenje: 55%

Napomena suca: Rory McIlroy is correct, but the model explicitly labeled it a guess.

K24RECALLcutoff evidencija

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

Očekivani odgovorAnoraSource ↗
Odgovor provjerenog modelaAnora85% · RECALL
Presuda suca: CORRECTPrijavljeno povjerenje: 85%

Napomena suca: Anora matches the answer key.

Pokrivenost pitanja i bilješke istraživanja

Činjenična pitanja: 24 · Nije ocijenjeno od strane suca: 0

Odsječak referenci i citate daje sudac, a platforma ih ne potvrđuje neovisno. Bilješke istraživanja ne kažnjavaju testirani model.

Pokreni metapodatke

Pojedinosti o ponovljivosti

Pokreni IDHTAMKTZHR951P7JVR0RJDS7TXJ
Benchmarkmodel-verification-single-request-v1.4
Suditigpt-5.6-sol
Traženi protokolopenai_chat
Otkrivena shema odgovoraLegacy / not recorded
Kompatibilnost protokolaŠIBICA / ostavština
Izlaz modelaNot recorded
Ulazni tokeniNot recorded
Izlazni žetoniNot recorded
Završi razlogNot recorded
HTTP status200
Vanjska latencija12,772 ms
Bajtovi odgovora2,665
SHA-2566d36e6fd6f6091dd50b513a22a18a9867f152d4fb9361a5fee6b99adb40502f5
Važno ograničenje

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.

Pokrenite neovisnu provjeru

Testirajte sami istu krajnju točku ili pregledajte druga javna izvješća prije nego što se oslonite na oglašeni identitet modela.