Analisi III · Exercise research profile

Curva implicita, natura vincolata ed estremi su ellisse troncata (A3-25-P5-E1)

Source record, frozen scoring evidence, configuration-level measurements and retained responses for one benchmark exercise.

01

Observed panel summary

Exercise overview

Descriptive results across 21 model-mode configuration means. They do not establish general model superiority.

Published recordSource statement · frozen rubric · 23 retained responses · current judgmentsThe separate official reference solution is not reproduced.
Mean rubric score97.4Median 100.0 · n=16
Configuration spreadSD 7.267.9–100.0
Rank by lowest observed mean#54/60Overall · #33/33 within Analisi III
Mean latency103.3sEnd-to-end per response
Mean cost$0.083Snapshot estimate
Mean tokens9,398Analytical tokens per response

Configuration means

Observed score distribution

Median 100.0 / 100
AnthropicDeepSeekOpenAIGooglexAIMistral
  1. Claude Fable 5SD not available · single run
    100.0
  2. Claude Opus 5.5SD not available · single run
    100.0
  3. DeepSeek V4 FlashSD not available · single run
    100.0
  4. DeepSeek V4 Flash (no thinking)SD not available · single run
    100.0
  5. DeepSeek V4 ProSD not available · single run
    100.0
  6. Gemini 3.1 Pro PreviewSD not available · single run
    100.0
  7. Gemini 3.5 FlashSD 0.0 · 3 retained runs
    100.0
  8. GPT-5.6 SolSD not available · single run
    100.0
  9. GPT-6.1 SolSD not available · single run
    100.0
  10. Grok 4.3SD not available · single run
    100.0
  11. Grok 4.5SD not available · single run
    100.0
  12. Mistral Medium 3.5SD not available · single run
    100.0
  13. Mistral Small 4SD not available · single run
    100.0
  14. OpenAI o3SD not available · single run
    100.0
  15. Claude Sonnet 5.5SD not available · single run
    99.5
  16. Claude Sonnet 4.5SD not available · single run
    98.4
  17. Gemma 4 31B ITSD not available · single run
    98.4
  18. DeepSeek V4.1 FlashSD not available · single run
    97.6
  19. GPT-6 LunaSD not available · single run
    96.8
  20. OpenAI GPT-4.1SD not available · single run
    87.4
  21. Claude Haiku 4.5SD not available · single run
    67.9

Whiskers show mean ± one within-configuration response SD where three retained runs are available. Single-run cells have no within-configuration variability statistic.

02

Task before results

Source record and frozen rubric

Read the evaluated task before interpreting configuration outcomes. Original Italian records remain authoritative.

Evaluated source record

Exercise statement

A3-25-P5-E1 · Analisi III
The English version is a faithful editorial translation. The Italian source remains authoritative.

ESAME: Analisi 3 DATA: 20/08/2025 ESERCIZIO: 1

TESTO: 1. Nel piano cartesiano si considerino le funzioni f(x, y) = x−y e g(x, y) = y ex+2y + 2x . (a) Quali insiemi di livello di g sono curve regolari? Detta Γ quella per P (2,−1), parametrizzare Γ fino all’ordine quadratico attorno P e calcolarne in due modi la retta tangente affine in P . (b) Mostrare che P è un punto stazionario perf su Γ, determinandone la natura. (c) Disegnato l’insieme D ={(x, y) : x≥0, y≤1, x2 + 2y2≤6}, dire se esistono gli estremi assoluti di f su D e, se sì, calcolarli.

Original source textExact Italian record · no editorial changes+
ESAME: Analisi 3
DATA: 20/08/2025
ESERCIZIO: 1

TESTO:
1. Nel piano cartesiano si considerino le funzioni f(x, y) = x−y e g(x, y) = y ex+2y + 2x .
(a) Quali insiemi di livello di g sono curve regolari? Detta Γ quella per P (2,−1), parametrizzare
Γ fino all’ordine quadratico attorno P e calcolarne in due modi la retta tangente affine in P .
(b) Mostrare che P è un punto stazionario perf su Γ, determinandone la natura.
(c) Disegnato l’insieme D ={(x, y) : x≥0, y≤1, x2 + 2y2≤6}, dire se esistono gli estremi
assoluti di f su D e, se sì, calcolarli.
TopicCurva implicita, natura vincolata ed estremi su ellisse troncata
Syllabus areaCurve di livello ed estremi
Task typemixed
Atomic criteria23
Subproblem a · 43.2%

Livelli regolari, sviluppo e tangente in due modi.

9 atomic criteria · T1 · T2 · T3 · T4 · T5 · T6 · T7

Inspect scoring criteria +
  • Trova punto critico e livello eccezionale.

    T1 · 6 pts · Criterion (a_T1_01)
  • Identifica Γ e regolarità in P.

    T1 · 4 pts · Criterion (a_T1_02)
  • Imposta implicita e due tangenti.

    T2 · 6 pts · Criterion (a_T2_01)
  • Calcola y'.

    T3 · 5 pts · Criterion (a_T3_01)
  • Calcola y''.

    T3 · 5 pts · Criterion (a_T3_02)
  • Dà classificazione, sviluppo e tangente.

    T4 · 5 pts · Criterion (a_T4_01)
  • Gestisce località/ipotesi.

    T5 · 4 pts · Criterion (a_T5_01)
  • Controlla sviluppo/tangente.

    T6 · 3 pts · Criterion (a_T6_01)
  • Applica teorema implicito/livello.

    T7 · 3 pts · Criterion (a_T7_01)
Subproblem b · 23.2%

Stazionarietà e natura di P.

7 atomic criteria · T1 · T2 · T3 · T4 · T5 · T6 · T7

Inspect scoring criteria +
  • Formalizza Lagrange.

    T1 · 4 pts · Criterion (b_T1_01)
  • Sceglie restrizione locale.

    T2 · 4 pts · Criterion (b_T2_01)
  • Calcola F',F''.

    T3 · 4 pts · Criterion (b_T3_01)
  • Dà natura corretta.

    T4 · 4 pts · Criterion (b_T4_01)
  • Mantiene vincolo/località.

    T5 · 2 pts · Criterion (b_T5_01)
  • Controlla segno.

    T6 · 2 pts · Criterion (b_T6_01)
  • Usa Lagrange/test secondo ordine.

    T7 · 2 pts · Criterion (b_T7_01)
Subproblem c · 33.7%

Esistenza ed estremi assoluti su D.

7 atomic criteria · T1 · T2 · T3 · T4 · T5 · T6 · T7

Inspect scoring criteria +
  • Descrive D e il bordo.

    T1 · 6 pts · Criterion (c_T1_01)
  • Imposta ricerca esaustiva.

    T2 · 5 pts · Criterion (c_T2_01)
  • Calcola candidati e valori.

    T3 · 6 pts · Criterion (c_T3_01)
  • Dà esistenza e due estremi.

    T4 · 6 pts · Criterion (c_T4_01)
  • Giustifica compattezza/continuità.

    T5 · 4 pts · Criterion (c_T5_01)
  • Confronta i valori.

    T6 · 3 pts · Criterion (c_T6_01)
  • Applica Weierstrass/Lagrange.

    T7 · 2 pts · Criterion (c_T7_01)
Complete frozen rubricOriginal Italian record · exact JSON · SHA-256 1946f384f654…+
{
  "rubric_version": "1.0",
  "judge_spec_version": "2.0",
  "item_id": "analisi_3_2025_quinto_appello_esercizio_1",
  "syllabus_macroarea": "Curve di livello ed estremi",
  "topic": "Curva implicita, natura vincolata ed estremi su ellisse troncata",
  "task_type": "mixed",
  "created_without_model_answers": true,
  "frozen": true,
  "reference_status": "verified",
  "reference_notes": "Gold: unico punto critico A=(1+2log2,-1/2), g(A)=4log2; tutti i livelli regolari salvo eventualmente quello in A. Γ={g=3}; presso P=(2,-1), y'=1,y''=-3, sviluppo y=-1+(x-2)-3/2(x-2)²+o e tangente y=x-3. P minimo locale stretto di f|Γ. Su D: minimo -1 in L=(0,1), massimo 3 in P. La frase della reference 'estremi di g su T' è un refuso nominale: il calcolo è di f su D.",
  "subproblems": [
    {
      "id": "a",
      "weight": 0.43157894736842106,
      "request": "Livelli regolari, sviluppo e tangente in due modi.",
      "expected_results": [
        "A,g(A),Γ",
        "y'=1,y''=-3",
        "sviluppo/tangente gold"
      ],
      "required_conditions": [
        "Teorema implicito."
      ],
      "accepted_equivalences": [
        "Forme equivalenti."
      ],
      "accepted_alternative_methods": [
        "Metodi rigorosi compatibili col gold."
      ]
    },
    {
      "id": "b",
      "weight": 0.23157894736842105,
      "request": "Stazionarietà e natura di P.",
      "expected_results": [
        "Lagrange",
        "F''(2)=3",
        "minimo stretto"
      ],
      "required_conditions": [
        "Classificare lungo Γ."
      ],
      "accepted_equivalences": [
        "Forme equivalenti."
      ],
      "accepted_alternative_methods": [
        "Metodi rigorosi compatibili col gold."
      ]
    },
    {
      "id": "c",
      "weight": 0.3368421052631579,
      "request": "Esistenza ed estremi assoluti su D.",
      "expected_results": [
        "D compatto",
        "P,L,M,N",
        "min/max gold"
      ],
      "required_conditions": [
        "Analizzare tutto il bordo."
      ],
      "accepted_equivalences": [
        "Forme equivalenti."
      ],
      "accepted_alternative_methods": [
        "Metodi rigorosi compatibili col gold."
      ]
    }
  ],
  "atomic_criteria": [
    {
      "criterion_id": "a_T1_01",
      "subproblem_id": "a",
      "primary_dimension": "T1",
      "max_points": 6,
      "description": "Trova punto critico e livello eccezionale.",
      "full_credit_evidence": [
        "A e 4log2."
      ],
      "partial_credit_rules": [
        {
          "credit_fraction": 0.75,
          "anchor": "Corretto salvo un difetto locale."
        },
        {
          "credit_fraction": 0.5,
          "anchor": "Copertura sostanziale ma incompleta."
        },
        {
          "credit_fraction": 0.25,
          "anchor": "Solo impostazione o elemento utile."
        }
      ],
      "zero_credit_conditions": [
        "Assente o incompatibile col gold."
      ],
      "accepted_equivalences": [
        "Forme matematicamente equivalenti."
      ],
      "accepted_alternative_methods": [
        "Metodo alternativo rigoroso compatibile col gold."
      ],
      "propagated_error_policy": "Penalizzare l'origine una sola volta."
    },
    {
      "criterion_id": "a_T1_02",
      "subproblem_id": "a",
      "primary_dimension": "T1",
      "max_points": 4,
      "description": "Identifica Γ e regolarità in P.",
      "full_credit_evidence": [
        "Γ={g=3},∇g(P)=(1,-1)."
      ],
      "partial_credit_rules": [
        {
          "credit_fraction": 0.75,
          "anchor": "Corretto salvo un difetto locale."
        },
        {
          "credit_fraction": 0.5,
          "anchor": "Copertura sostanziale ma incompleta."
        },
        {
          "credit_fraction": 0.25,
          "anchor": "Solo impostazione o elemento utile."
        }
      ],
      "zero_credit_conditions": [
        "Assente o incompatibile col gold."
      ],
      "accepted_equivalences": [
        "Forme matematicamente equivalenti."
      ],
      "accepted_alternative_methods": [
        "Metodo alternativo rigoroso compatibile col gold."
      ],
      "propagated_error_policy": "Penalizzare l'origine una sola volta."
    },
    {
      "criterion_id": "a_T2_01",
      "subproblem_id": "a",
      "primary_dimension": "T2",
      "max_points": 6,
      "description": "Imposta implicita e due tangenti.",
      "full_credit_evidence": [
        "y(x) e gradiente."
      ],
      "partial_credit_rules": [
        {
          "credit_fraction": 0.75,
          "anchor": "Corretto salvo un difetto locale."
        },
        {
          "credit_fraction": 0.5,
          "anchor": "Copertura sostanziale ma incompleta."
        },
        {
          "credit_fraction": 0.25,
          "anchor": "Solo impostazione o elemento utile."
        }
      ],
      "zero_credit_conditions": [
        "Assente o incompatibile col gold."
      ],
      "accepted_equivalences": [
        "Forme matematicamente equivalenti."
      ],
      "accepted_alternative_methods": [
        "Metodo alternativo rigoroso compatibile col gold."
      ],
      "propagated_error_policy": "Penalizzare l'origine una sola volta."
    },
    {
      "criterion_id": "a_T3_01",
      "subproblem_id": "a",
      "primary_dimension": "T3",
      "max_points": 5,
      "description": "Calcola y'.",
      "full_credit_evidence": [
        "y'(2)=1."
      ],
      "partial_credit_rules": [
        {
          "credit_fraction": 0.75,
          "anchor": "Corretto salvo un difetto locale."
        },
        {
          "credit_fraction": 0.5,
          "anchor": "Copertura sostanziale ma incompleta."
        },
        {
          "credit_fraction": 0.25,
          "anchor": "Solo impostazione o elemento utile."
        }
      ],
      "zero_credit_conditions": [
        "Assente o incompatibile col gold."
      ],
      "accepted_equivalences": [
        "Forme matematicamente equivalenti."
      ],
      "accepted_alternative_methods": [
        "Metodo alternativo rigoroso compatibile col gold."
      ],
      "propagated_error_policy": "Penalizzare l'origine una sola volta."
    },
    {
      "criterion_id": "a_T3_02",
      "subproblem_id": "a",
      "primary_dimension": "T3",
      "max_points": 5,
      "description": "Calcola y''.",
      "full_credit_evidence": [
        "y''(2)=-3."
      ],
      "partial_credit_rules": [
        {
          "credit_fraction": 0.75,
          "anchor": "Corretto salvo un difetto locale."
        },
        {
          "credit_fraction": 0.5,
          "anchor": "Copertura sostanziale ma incompleta."
        },
        {
          "credit_fraction": 0.25,
          "anchor": "Solo impostazione o elemento utile."
        }
      ],
      "zero_credit_conditions": [
        "Assente o incompatibile col gold."
      ],
      "accepted_equivalences": [
        "Forme matematicamente equivalenti."
      ],
      "accepted_alternative_methods": [
        "Metodo alternativo rigoroso compatibile col gold."
      ],
      "propagated_error_policy": "Penalizzare l'origine una sola volta."
    },
    {
      "criterion_id": "a_T4_01",
      "subproblem_id": "a",
      "primary_dimension": "T4",
      "max_points": 5,
      "description": "Dà classificazione, sviluppo e tangente.",
      "full_credit_evidence": [
        "Tutti i deliverable gold."
      ],
      "partial_credit_rules": [
        {
          "credit_fraction": 0.75,
          "anchor": "Corretto salvo un difetto locale."
        },
        {
          "credit_fraction": 0.5,
          "anchor": "Copertura sostanziale ma incompleta."
        },
        {
          "credit_fraction": 0.25,
          "anchor": "Solo impostazione o elemento utile."
        }
      ],
      "zero_credit_conditions": [
        "Assente o incompatibile col gold."
      ],
      "accepted_equivalences": [
        "Forme matematicamente equivalenti."
      ],
      "accepted_alternative_methods": [
        "Metodo alternativo rigoroso compatibile col gold."
      ],
      "propagated_error_policy": "Penalizzare l'origine una sola volta."
    },
    {
      "criterion_id": "a_T5_01",
      "subproblem_id": "a",
      "primary_dimension": "T5",
      "max_points": 4,
      "description": "Gestisce località/ipotesi.",
      "full_credit_evidence": [
        "Gradiente non nullo."
      ],
      "partial_credit_rules": [
        {
          "credit_fraction": 0.75,
          "anchor": "Corretto salvo un difetto locale."
        },
        {
          "credit_fraction": 0.5,
          "anchor": "Copertura sostanziale ma incompleta."
        },
        {
          "credit_fraction": 0.25,
          "anchor": "Solo impostazione o elemento utile."
        }
      ],
      "zero_credit_conditions": [
        "Assente o incompatibile col gold."
      ],
      "accepted_equivalences": [
        "Forme matematicamente equivalenti."
      ],
      "accepted_alternative_methods": [
        "Metodo alternativo rigoroso compatibile col gold."
      ],
      "propagated_error_policy": "Penalizzare l'origine una sola volta."
    },
    {
      "criterion_id": "a_T6_01",
      "subproblem_id": "a",
      "primary_dimension": "T6",
      "max_points": 3,
      "description": "Controlla sviluppo/tangente.",
      "full_credit_evidence": [
        "Parte lineare coerente."
      ],
      "partial_credit_rules": [
        {
          "credit_fraction": 0.75,
          "anchor": "Corretto salvo un difetto locale."
        },
        {
          "credit_fraction": 0.5,
          "anchor": "Copertura sostanziale ma incompleta."
        },
        {
          "credit_fraction": 0.25,
          "anchor": "Solo impostazione o elemento utile."
        }
      ],
      "zero_credit_conditions": [
        "Assente o incompatibile col gold."
      ],
      "accepted_equivalences": [
        "Forme matematicamente equivalenti."
      ],
      "accepted_alternative_methods": [
        "Metodo alternativo rigoroso compatibile col gold."
      ],
      "propagated_error_policy": "Penalizzare l'origine una sola volta."
    },
    {
      "criterion_id": "a_T7_01",
      "subproblem_id": "a",
      "primary_dimension": "T7",
      "max_points": 3,
      "description": "Applica teorema implicito/livello.",
      "full_credit_evidence": [
        "Uso rigoroso."
      ],
      "partial_credit_rules": [
        {
          "credit_fraction": 0.75,
          "anchor": "Corretto salvo un difetto locale."
        },
        {
          "credit_fraction": 0.5,
          "anchor": "Copertura sostanziale ma incompleta."
        },
        {
          "credit_fraction": 0.25,
          "anchor": "Solo impostazione o elemento utile."
        }
      ],
      "zero_credit_conditions": [
        "Assente o incompatibile col gold."
      ],
      "accepted_equivalences": [
        "Forme matematicamente equivalenti."
      ],
      "accepted_alternative_methods": [
        "Metodo alternativo rigoroso compatibile col gold."
      ],
      "propagated_error_policy": "Penalizzare l'origine una sola volta."
    },
    {
      "criterion_id": "b_T1_01",
      "subproblem_id": "b",
      "primary_dimension": "T1",
      "max_points": 4,
      "description": "Formalizza Lagrange.",
      "full_credit_evidence": [
        "Determinante più g=3."
      ],
      "partial_credit_rules": [
        {
          "credit_fraction": 0.75,
          "anchor": "Corretto salvo un difetto locale."
        },
        {
          "credit_fraction": 0.5,
          "anchor": "Copertura sostanziale ma incompleta."
        },
        {
          "credit_fraction": 0.25,
          "anchor": "Solo impostazione o elemento utile."
        }
      ],
      "zero_credit_conditions": [
        "Assente o incompatibile col gold."
      ],
      "accepted_equivalences": [
        "Forme matematicamente equivalenti."
      ],
      "accepted_alternative_methods": [
        "Metodo alternativo rigoroso compatibile col gold."
      ],
      "propagated_error_policy": "Penalizzare l'origine una sola volta."
    },
    {
      "criterion_id": "b_T2_01",
      "subproblem_id": "b",
      "primary_dimension": "T2",
      "max_points": 4,
      "description": "Sceglie restrizione locale.",
      "full_credit_evidence": [
        "F=x-y(x)."
      ],
      "partial_credit_rules": [
        {
          "credit_fraction": 0.75,
          "anchor": "Corretto salvo un difetto locale."
        },
        {
          "credit_fraction": 0.5,
          "anchor": "Copertura sostanziale ma incompleta."
        },
        {
          "credit_fraction": 0.25,
          "anchor": "Solo impostazione o elemento utile."
        }
      ],
      "zero_credit_conditions": [
        "Assente o incompatibile col gold."
      ],
      "accepted_equivalences": [
        "Forme matematicamente equivalenti."
      ],
      "accepted_alternative_methods": [
        "Metodo alternativo rigoroso compatibile col gold."
      ],
      "propagated_error_policy": "Penalizzare l'origine una sola volta."
    },
    {
      "criterion_id": "b_T3_01",
      "subproblem_id": "b",
      "primary_dimension": "T3",
      "max_points": 4,
      "description": "Calcola F',F''.",
      "full_credit_evidence": [
        "0 e 3."
      ],
      "partial_credit_rules": [
        {
          "credit_fraction": 0.75,
          "anchor": "Corretto salvo un difetto locale."
        },
        {
          "credit_fraction": 0.5,
          "anchor": "Copertura sostanziale ma incompleta."
        },
        {
          "credit_fraction": 0.25,
          "anchor": "Solo impostazione o elemento utile."
        }
      ],
      "zero_credit_conditions": [
        "Assente o incompatibile col gold."
      ],
      "accepted_equivalences": [
        "Forme matematicamente equivalenti."
      ],
      "accepted_alternative_methods": [
        "Metodo alternativo rigoroso compatibile col gold."
      ],
      "propagated_error_policy": "Penalizzare l'origine una sola volta."
    },
    {
      "criterion_id": "b_T4_01",
      "subproblem_id": "b",
      "primary_dimension": "T4",
      "max_points": 4,
      "description": "Dà natura corretta.",
      "full_credit_evidence": [
        "Minimo locale stretto."
      ],
      "partial_credit_rules": [
        {
          "credit_fraction": 0.75,
          "anchor": "Corretto salvo un difetto locale."
        },
        {
          "credit_fraction": 0.5,
          "anchor": "Copertura sostanziale ma incompleta."
        },
        {
          "credit_fraction": 0.25,
          "anchor": "Solo impostazione o elemento utile."
        }
      ],
      "zero_credit_conditions": [
        "Assente o incompatibile col gold."
      ],
      "accepted_equivalences": [
        "Forme matematicamente equivalenti."
      ],
      "accepted_alternative_methods": [
        "Metodo alternativo rigoroso compatibile col gold."
      ],
      "propagated_error_policy": "Penalizzare l'origine una sola volta."
    },
    {
      "criterion_id": "b_T5_01",
      "subproblem_id": "b",
      "primary_dimension": "T5",
      "max_points": 2,
      "description": "Mantiene vincolo/località.",
      "full_credit_evidence": [
        "P∈Γ."
      ],
      "partial_credit_rules": [
        {
          "credit_fraction": 0.75,
          "anchor": "Corretto salvo un difetto locale."
        },
        {
          "credit_fraction": 0.5,
          "anchor": "Copertura sostanziale ma incompleta."
        },
        {
          "credit_fraction": 0.25,
          "anchor": "Solo impostazione o elemento utile."
        }
      ],
      "zero_credit_conditions": [
        "Assente o incompatibile col gold."
      ],
      "accepted_equivalences": [
        "Forme matematicamente equivalenti."
      ],
      "accepted_alternative_methods": [
        "Metodo alternativo rigoroso compatibile col gold."
      ],
      "propagated_error_policy": "Penalizzare l'origine una sola volta."
    },
    {
      "criterion_id": "b_T6_01",
      "subproblem_id": "b",
      "primary_dimension": "T6",
      "max_points": 2,
      "description": "Controlla segno.",
      "full_credit_evidence": [
        "F''>0."
      ],
      "partial_credit_rules": [
        {
          "credit_fraction": 0.75,
          "anchor": "Corretto salvo un difetto locale."
        },
        {
          "credit_fraction": 0.5,
          "anchor": "Copertura sostanziale ma incompleta."
        },
        {
          "credit_fraction": 0.25,
          "anchor": "Solo impostazione o elemento utile."
        }
      ],
      "zero_credit_conditions": [
        "Assente o incompatibile col gold."
      ],
      "accepted_equivalences": [
        "Forme matematicamente equivalenti."
      ],
      "accepted_alternative_methods": [
        "Metodo alternativo rigoroso compatibile col gold."
      ],
      "propagated_error_policy": "Penalizzare l'origine una sola volta."
    },
    {
      "criterion_id": "b_T7_01",
      "subproblem_id": "b",
      "primary_dimension": "T7",
      "max_points": 2,
      "description": "Usa Lagrange/test secondo ordine.",
      "full_credit_evidence": [
        "Conclusione valida."
      ],
      "partial_credit_rules": [
        {
          "credit_fraction": 0.75,
          "anchor": "Corretto salvo un difetto locale."
        },
        {
          "credit_fraction": 0.5,
          "anchor": "Copertura sostanziale ma incompleta."
        },
        {
          "credit_fraction": 0.25,
          "anchor": "Solo impostazione o elemento utile."
        }
      ],
      "zero_credit_conditions": [
        "Assente o incompatibile col gold."
      ],
      "accepted_equivalences": [
        "Forme matematicamente equivalenti."
      ],
      "accepted_alternative_methods": [
        "Metodo alternativo rigoroso compatibile col gold."
      ],
      "propagated_error_policy": "Penalizzare l'origine una sola volta."
    },
    {
      "criterion_id": "c_T1_01",
      "subproblem_id": "c",
      "primary_dimension": "T1",
      "max_points": 6,
      "description": "Descrive D e il bordo.",
      "full_credit_evidence": [
        "Ellisse, x=0,y=1, arco e vertici."
      ],
      "partial_credit_rules": [
        {
          "credit_fraction": 0.75,
          "anchor": "Corretto salvo un difetto locale."
        },
        {
          "credit_fraction": 0.5,
          "anchor": "Copertura sostanziale ma incompleta."
        },
        {
          "credit_fraction": 0.25,
          "anchor": "Solo impostazione o elemento utile."
        }
      ],
      "zero_credit_conditions": [
        "Assente o incompatibile col gold."
      ],
      "accepted_equivalences": [
        "Forme matematicamente equivalenti."
      ],
      "accepted_alternative_methods": [
        "Metodo alternativo rigoroso compatibile col gold."
      ],
      "propagated_error_policy": "Penalizzare l'origine una sola volta."
    },
    {
      "criterion_id": "c_T2_01",
      "subproblem_id": "c",
      "primary_dimension": "T2",
      "max_points": 5,
      "description": "Imposta ricerca esaustiva.",
      "full_credit_evidence": [
        "Interno e bordi."
      ],
      "partial_credit_rules": [
        {
          "credit_fraction": 0.75,
          "anchor": "Corretto salvo un difetto locale."
        },
        {
          "credit_fraction": 0.5,
          "anchor": "Copertura sostanziale ma incompleta."
        },
        {
          "credit_fraction": 0.25,
          "anchor": "Solo impostazione o elemento utile."
        }
      ],
      "zero_credit_conditions": [
        "Assente o incompatibile col gold."
      ],
      "accepted_equivalences": [
        "Forme matematicamente equivalenti."
      ],
      "accepted_alternative_methods": [
        "Metodo alternativo rigoroso compatibile col gold."
      ],
      "propagated_error_policy": "Penalizzare l'origine una sola volta."
    },
    {
      "criterion_id": "c_T3_01",
      "subproblem_id": "c",
      "primary_dimension": "T3",
      "max_points": 6,
      "description": "Calcola candidati e valori.",
      "full_credit_evidence": [
        "P,L,M,N."
      ],
      "partial_credit_rules": [
        {
          "credit_fraction": 0.75,
          "anchor": "Corretto salvo un difetto locale."
        },
        {
          "credit_fraction": 0.5,
          "anchor": "Copertura sostanziale ma incompleta."
        },
        {
          "credit_fraction": 0.25,
          "anchor": "Solo impostazione o elemento utile."
        }
      ],
      "zero_credit_conditions": [
        "Assente o incompatibile col gold."
      ],
      "accepted_equivalences": [
        "Forme matematicamente equivalenti."
      ],
      "accepted_alternative_methods": [
        "Metodo alternativo rigoroso compatibile col gold."
      ],
      "propagated_error_policy": "Penalizzare l'origine una sola volta."
    },
    {
      "criterion_id": "c_T4_01",
      "subproblem_id": "c",
      "primary_dimension": "T4",
      "max_points": 6,
      "description": "Dà esistenza e due estremi.",
      "full_credit_evidence": [
        "Min -1 in L,max 3 in P."
      ],
      "partial_credit_rules": [
        {
          "credit_fraction": 0.75,
          "anchor": "Corretto salvo un difetto locale."
        },
        {
          "credit_fraction": 0.5,
          "anchor": "Copertura sostanziale ma incompleta."
        },
        {
          "credit_fraction": 0.25,
          "anchor": "Solo impostazione o elemento utile."
        }
      ],
      "zero_credit_conditions": [
        "Assente o incompatibile col gold."
      ],
      "accepted_equivalences": [
        "Forme matematicamente equivalenti."
      ],
      "accepted_alternative_methods": [
        "Metodo alternativo rigoroso compatibile col gold."
      ],
      "propagated_error_policy": "Penalizzare l'origine una sola volta."
    },
    {
      "criterion_id": "c_T5_01",
      "subproblem_id": "c",
      "primary_dimension": "T5",
      "max_points": 4,
      "description": "Giustifica compattezza/continuità.",
      "full_credit_evidence": [
        "D compatto,f continua."
      ],
      "partial_credit_rules": [
        {
          "credit_fraction": 0.75,
          "anchor": "Corretto salvo un difetto locale."
        },
        {
          "credit_fraction": 0.5,
          "anchor": "Copertura sostanziale ma incompleta."
        },
        {
          "credit_fraction": 0.25,
          "anchor": "Solo impostazione o elemento utile."
        }
      ],
      "zero_credit_conditions": [
        "Assente o incompatibile col gold."
      ],
      "accepted_equivalences": [
        "Forme matematicamente equivalenti."
      ],
      "accepted_alternative_methods": [
        "Metodo alternativo rigoroso compatibile col gold."
      ],
      "propagated_error_policy": "Penalizzare l'origine una sola volta."
    },
    {
      "criterion_id": "c_T6_01",
      "subproblem_id": "c",
      "primary_dimension": "T6",
      "max_points": 3,
      "description": "Confronta i valori.",
      "full_credit_evidence": [
        "Ordine e appartenenza."
      ],
      "partial_credit_rules": [
        {
          "credit_fraction": 0.75,
          "anchor": "Corretto salvo un difetto locale."
        },
        {
          "credit_fraction": 0.5,
          "anchor": "Copertura sostanziale ma incompleta."
        },
        {
          "credit_fraction": 0.25,
          "anchor": "Solo impostazione o elemento utile."
        }
      ],
      "zero_credit_conditions": [
        "Assente o incompatibile col gold."
      ],
      "accepted_equivalences": [
        "Forme matematicamente equivalenti."
      ],
      "accepted_alternative_methods": [
        "Metodo alternativo rigoroso compatibile col gold."
      ],
      "propagated_error_policy": "Penalizzare l'origine una sola volta."
    },
    {
      "criterion_id": "c_T7_01",
      "subproblem_id": "c",
      "primary_dimension": "T7",
      "max_points": 2,
      "description": "Applica Weierstrass/Lagrange.",
      "full_credit_evidence": [
        "Uso rigoroso."
      ],
      "partial_credit_rules": [
        {
          "credit_fraction": 0.75,
          "anchor": "Corretto salvo un difetto locale."
        },
        {
          "credit_fraction": 0.5,
          "anchor": "Copertura sostanziale ma incompleta."
        },
        {
          "credit_fraction": 0.25,
          "anchor": "Solo impostazione o elemento utile."
        }
      ],
      "zero_credit_conditions": [
        "Assente o incompatibile col gold."
      ],
      "accepted_equivalences": [
        "Forme matematicamente equivalenti."
      ],
      "accepted_alternative_methods": [
        "Metodo alternativo rigoroso compatibile col gold."
      ],
      "propagated_error_policy": "Penalizzare l'origine una sola volta."
    }
  ],
  "dimension_applicability": {
    "T1": "applicable",
    "T2": "applicable",
    "T3": "applicable",
    "T4": "applicable",
    "T5": "applicable",
    "T6": "applicable",
    "T7": "applicable",
    "T8": "not_applicable"
  },
  "dimension_applicability_notes": {
    "T8": "Non applicabile: nessuna verifica autonoma richiesta."
  },
  "dimension_point_budget": {
    "T1": 20,
    "T2": 15,
    "T3": 20,
    "T4": 15,
    "T5": 10,
    "T6": 8,
    "T7": 7,
    "T8": 0
  },
  "applicable_max_score": 95,
  "normalization_rule": "Normalizzare con 100*raw_score/95.",
  "not_applicable_dimensions": [
    "T8"
  ],
  "pertinent_checks": [
    "∇g(A),g(A).",
    "Derivate implicite.",
    "Lagrange in P.",
    "Confronto P,L,M,N."
  ],
  "known_error_severity": [
    {
      "error": "Livello eccezionale errato",
      "severity": "major"
    },
    {
      "error": "Sviluppo/tangente errati",
      "severity": "major"
    },
    {
      "error": "Natura di P errata",
      "severity": "major"
    },
    {
      "error": "Estremi errati",
      "severity": "major"
    }
  ],
  "rubric_specific_caps": [],
  "human_review_triggers": [
    "Interpretazione letterale del refuso g/T.",
    "Metodo alternativo sul bordo incerto."
  ],
  "human_approval": {
    "approved": true,
    "reviewer": "benchmark_owner_via_codex_task",
    "date": "2026-07-18"
  }
}
03

Per-exercise ranking

Configurations

Choose one of four stable ranking views. Retry count remains available as a secondary table sort.

Rank configurations by

Score ranks high to low. Speed, cost and tokens rank low to high. Retry sorting remains available from the table header.

Results for all 21 model-mode configurations
ConfigurationSelected rankMean score / replicasLatencyCostTokens
Claude Fable 5Anthropic · official model page ↗#1by score100.0SD not available · single run80.5s$0.3828,3370.00
Claude Opus 5.5Anthropic · official model page ↗#1by score100.0SD not available · single run61.3s$0.1347,3850.00
DeepSeek V4 FlashDeepSeek · official model page ↗#1by score100.0SD not available · single run160.2s$0.004817,3930.00
DeepSeek V4 Flash (no thinking)DeepSeek · official model page ↗#1by score100.0SD not available · single run25.6s$0.00103,9020.00
DeepSeek V4 ProDeepSeek · official model page ↗#1by score100.0SD not available · single run155.9s$0.009811,5430.00
Gemini 3.1 Pro PreviewGoogle · official model page ↗#1by score100.0SD not available · single run64.1s$0.0998,6840.00
Gemini 3.5 FlashGoogle · official model page ↗#1by score100.0SD 0.0 · 3 retained runs395.6s$0.12214,0250.00
GPT-5.6 SolOpenAI · official model page ↗#1by score100.0SD not available · single run270.7s$0.47216,2080.00
GPT-6.1 SolOpenAI · official model page ↗#1by score100.0SD not available · single run190.5s$0.10811,2020.00
Grok 4.3xAI · official model page ↗#1by score100.0SD not available · single run75.4s$0.02510,5560.00
Grok 4.5xAI · official model page ↗#1by score100.0SD not available · single run108.0s$0.0397,0160.00
Mistral Medium 3.5Mistral · official model page ↗#1by score100.0SD not available · single run66.1s$0.09713,3720.00
Mistral Small 4Mistral · official model page ↗#1by score100.0SD not available · single run60.9s$0.007412,7680.00
OpenAI o3OpenAI · official model page ↗#1by score100.0SD not available · single run101.9s$0.0658,4990.00
Claude Sonnet 5.5Anthropic · official model page ↗#15by score99.5SD not available · single run42.2s$0.0636,9890.00
Claude Sonnet 4.5Anthropic · official model page ↗#16by score98.4SD not available · single run44.2s$0.0423,3060.00
Gemma 4 31B ITGoogle · official model page ↗#16by score98.4SD not available · single run79.5s$0.00003,3970.00
DeepSeek V4.1 FlashDeepSeek · official model page ↗#18by score97.6SD not available · single run62.3s$0.01714,5230.00
GPT-6 LunaOpenAI · official model page ↗#19by score96.8SD not available · single run57.5s$0.00418,6760.00
OpenAI GPT-4.1OpenAI · official model page ↗#20by score87.4SD not available · single run40.6s$0.0385,1470.00
Claude Haiku 4.5Anthropic · official model page ↗#21by score67.9SD not available · single run25.2s$0.0194,4350.00
#1 by score

Claude Fable 5

Anthropic
100.0mean score

SD not available · single run

Latency
80.5s
Cost
$0.382
Tokens
8,337
Retries
0.00
Official model page ↗
#1 by score

Claude Opus 5.5

Anthropic
100.0mean score

SD not available · single run

Latency
61.3s
Cost
$0.134
Tokens
7,385
Retries
0.00
Official model page ↗
#1 by score

DeepSeek V4 Flash

DeepSeek
100.0mean score

SD not available · single run

Latency
160.2s
Cost
$0.0048
Tokens
17,393
Retries
0.00
Official model page ↗
#1 by score

DeepSeek V4 Flash (no thinking)

DeepSeek
100.0mean score

SD not available · single run

Latency
25.6s
Cost
$0.0010
Tokens
3,902
Retries
0.00
Official model page ↗
#1 by score

DeepSeek V4 Pro

DeepSeek
100.0mean score

SD not available · single run

Latency
155.9s
Cost
$0.0098
Tokens
11,543
Retries
0.00
Official model page ↗
#1 by score

Gemini 3.1 Pro Preview

Google
100.0mean score

SD not available · single run

Latency
64.1s
Cost
$0.099
Tokens
8,684
Retries
0.00
Official model page ↗
#1 by score

Gemini 3.5 Flash

Google
100.0mean score

SD 0.0 · 3 retained runs

Latency
395.6s
Cost
$0.122
Tokens
14,025
Retries
0.00
Official model page ↗
#1 by score

GPT-5.6 Sol

OpenAI
100.0mean score

SD not available · single run

Latency
270.7s
Cost
$0.472
Tokens
16,208
Retries
0.00
Official model page ↗
#1 by score

GPT-6.1 Sol

OpenAI
100.0mean score

SD not available · single run

Latency
190.5s
Cost
$0.108
Tokens
11,202
Retries
0.00
Official model page ↗
#1 by score

Grok 4.3

xAI
100.0mean score

SD not available · single run

Latency
75.4s
Cost
$0.025
Tokens
10,556
Retries
0.00
Official model page ↗
#1 by score

Grok 4.5

xAI
100.0mean score

SD not available · single run

Latency
108.0s
Cost
$0.039
Tokens
7,016
Retries
0.00
Official model page ↗
#1 by score

Mistral Medium 3.5

Mistral
100.0mean score

SD not available · single run

Latency
66.1s
Cost
$0.097
Tokens
13,372
Retries
0.00
Official model page ↗
#1 by score

Mistral Small 4

Mistral
100.0mean score

SD not available · single run

Latency
60.9s
Cost
$0.0074
Tokens
12,768
Retries
0.00
Official model page ↗
#1 by score

OpenAI o3

OpenAI
100.0mean score

SD not available · single run

Latency
101.9s
Cost
$0.065
Tokens
8,499
Retries
0.00
Official model page ↗
#15 by score

Claude Sonnet 5.5

Anthropic
99.5mean score

SD not available · single run

Latency
42.2s
Cost
$0.063
Tokens
6,989
Retries
0.00
Official model page ↗
#16 by score

Claude Sonnet 4.5

Anthropic
98.4mean score

SD not available · single run

Latency
44.2s
Cost
$0.042
Tokens
3,306
Retries
0.00
Official model page ↗
#16 by score

Gemma 4 31B IT

Google
98.4mean score

SD not available · single run

Latency
79.5s
Cost
$0.0000
Tokens
3,397
Retries
0.00
Official model page ↗
#18 by score

DeepSeek V4.1 Flash

DeepSeek
97.6mean score

SD not available · single run

Latency
62.3s
Cost
$0.017
Tokens
14,523
Retries
0.00
Official model page ↗
#19 by score

GPT-6 Luna

OpenAI
96.8mean score

SD not available · single run

Latency
57.5s
Cost
$0.0041
Tokens
8,676
Retries
0.00
Official model page ↗
#20 by score

OpenAI GPT-4.1

OpenAI
87.4mean score

SD not available · single run

Latency
40.6s
Cost
$0.038
Tokens
5,147
Retries
0.00
Official model page ↗
#21 by score

Claude Haiku 4.5

Anthropic
67.9mean score

SD not available · single run

Latency
25.2s
Cost
$0.019
Tokens
4,435
Retries
0.00
Official model page ↗
04

Criterion-level benchmark record

Scoring evidence

Dimension and criterion values are descriptive results for the 21 evaluated configuration means. N/A remains distinct from zero.

Attainment scale0%50%100%N/A = not applicable
T194.8%Understanding / modelling
T299.7%Method selection
T397.7%Development
T495.9%Final results
T5100.0%Domains / assumptions
T698.4%Consistency
T798.0%Rigor
T8N/AIndependent verification
T1 through T8 attainment for each model-mode configuration
ConfigurationT120 ptsT215 ptsT320 ptsT415 ptsT510 ptsT68 ptsT77 ptsT80 pts
Claude Fable 5100.0%100.0%100.0%100.0%100.0%100.0%100.0%N/A
Claude Opus 5.5100.0%100.0%100.0%100.0%100.0%100.0%100.0%N/A
DeepSeek V4 Flash100.0%100.0%100.0%100.0%100.0%100.0%100.0%N/A
DeepSeek V4 Flash (no thinking)100.0%100.0%100.0%100.0%100.0%100.0%100.0%N/A
DeepSeek V4 Pro100.0%100.0%100.0%100.0%100.0%100.0%100.0%N/A
GPT-5.6 Sol100.0%100.0%100.0%100.0%100.0%100.0%100.0%N/A
GPT-6.1 Sol100.0%100.0%100.0%100.0%100.0%100.0%100.0%N/A
Gemini 3.1 Pro Preview100.0%100.0%100.0%100.0%100.0%100.0%100.0%N/A
Gemini 3.5 Flash100.0%100.0%100.0%100.0%100.0%100.0%100.0%N/A
Grok 4.3100.0%100.0%100.0%100.0%100.0%100.0%100.0%N/A
Grok 4.5100.0%100.0%100.0%100.0%100.0%100.0%100.0%N/A
Mistral Medium 3.5100.0%100.0%100.0%100.0%100.0%100.0%100.0%N/A
Mistral Small 4100.0%100.0%100.0%100.0%100.0%100.0%100.0%N/A
OpenAI o3100.0%100.0%100.0%100.0%100.0%100.0%100.0%N/A
Claude Sonnet 5.5100.0%100.0%100.0%100.0%100.0%100.0%92.9%N/A
Claude Sonnet 4.592.5%100.0%100.0%100.0%100.0%100.0%100.0%N/A
Gemma 4 31B IT92.5%100.0%100.0%100.0%100.0%100.0%100.0%N/A
DeepSeek V4.1 Flash92.5%100.0%100.0%100.0%100.0%100.0%89.3%N/A
GPT-6 Luna85.0%100.0%100.0%100.0%100.0%100.0%100.0%N/A
OpenAI GPT-4.177.5%100.0%81.3%75.0%100.0%100.0%100.0%N/A
Claude Haiku 4.550.0%93.3%71.3%38.3%100.0%65.6%75.0%N/A
05

Load on request

Retained responses and judgments

23 responses across 21 model-mode configurations. Long records load only when opened.

Interpretation boundary

Answers are reproduced as submitted. Each is paired with its authority-resolved judgment for this snapshot; this is not a general evaluation of the underlying model.

Compare two configurations All retained replicas

Select two configurations and load all their retained replicas.

Select two configurations and load all their retained replicas.

#1Claude Fable 5Anthropic · 1 retained run · load on request100.0configuration mean+
Configuration recordOfficial model page ↗
#1Claude Opus 5.5Anthropic · 1 retained run · load on request100.0configuration mean+
Configuration recordOfficial model page ↗
#1DeepSeek V4 FlashDeepSeek · 1 retained run · load on request100.0configuration mean+
Configuration recordOfficial model page ↗
#1DeepSeek V4 Flash (no thinking)DeepSeek · 1 retained run · load on request100.0configuration mean+
Configuration recordOfficial model page ↗
#1DeepSeek V4 ProDeepSeek · 1 retained run · load on request100.0configuration mean+
Configuration recordOfficial model page ↗
#1GPT-5.6 SolOpenAI · 1 retained run · load on request100.0configuration mean+
Configuration recordOfficial model page ↗
#1GPT-6.1 SolOpenAI · 1 retained run · load on request100.0configuration mean+
Configuration recordOfficial model page ↗
#1Gemini 3.1 Pro PreviewGoogle · 1 retained run · load on request100.0configuration mean+
Configuration recordOfficial model page ↗
#1Gemini 3.5 FlashGoogle · 3 retained runs · load on request100.0configuration mean+
Configuration recordOfficial model page ↗
#1Grok 4.3xAI · 1 retained run · load on request100.0configuration mean+
Configuration recordOfficial model page ↗
#1Grok 4.5xAI · 1 retained run · load on request100.0configuration mean+
Configuration recordOfficial model page ↗
#1Mistral Medium 3.5Mistral · 1 retained run · load on request100.0configuration mean+
Configuration recordOfficial model page ↗
#1Mistral Small 4Mistral · 1 retained run · load on request100.0configuration mean+
Configuration recordOfficial model page ↗
#1OpenAI o3OpenAI · 1 retained run · load on request100.0configuration mean+
Configuration recordOfficial model page ↗
#15Claude Sonnet 5.5Anthropic · 1 retained run · load on request99.5configuration mean+
Configuration recordOfficial model page ↗
#16Claude Sonnet 4.5Anthropic · 1 retained run · load on request98.4configuration mean+
Configuration recordOfficial model page ↗
#16Gemma 4 31B ITGoogle · 1 retained run · load on request98.4configuration mean+
Configuration recordOfficial model page ↗
#18DeepSeek V4.1 FlashDeepSeek · 1 retained run · load on request97.6configuration mean+
Configuration recordOfficial model page ↗
#19GPT-6 LunaOpenAI · 1 retained run · load on request96.8configuration mean+
Configuration recordOfficial model page ↗
#20OpenAI GPT-4.1OpenAI · 1 retained run · load on request87.4configuration mean+
Configuration recordOfficial model page ↗
#21Claude Haiku 4.5Anthropic · 1 retained run · load on request67.9configuration mean+
Configuration recordOfficial model page ↗
06

Record context

About this benchmark record

The Atlas presents the exercise, rubric, results and retained responses in one interactive record.

Exercise IDA3-25-P5-E1
SubjectAnalisi III
Exam sitting2025 · Fifth sitting
Benchmark snapshot2026-10-15
Rubric version1.0
Retained responses23
How to use this page

Use the Atlas to inspect what was tested and how each configuration performed. Most configuration–exercise cells are single-run, so displayed values are descriptive rather than uncertainty estimates.

UniAIBench v1.0Snapshot del benchmark live · 15 ottobre 2026Documento di lavoro · 14 agosto 2026Sito aggiornato · 15 ottobre 2026Codice sorgenteUniAIBench