Analisi III · Exercise research profile

Baricentro, integrali impropri, verifica di Gauss e area laterale (A3-25-P5-E2)

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 score88.7Median 97.9 · n=16
Configuration spreadSD 19.430.0–100.0
Rank by lowest observed mean#21/60Overall · #16/33 within Analisi III
Mean latency127.1sEnd-to-end per response
Mean cost$0.096Snapshot estimate
Mean tokens12,383Analytical tokens per response

Configuration means

Observed score distribution

Median 97.9 / 100
AnthropicDeepSeekOpenAIGoogleMistralxAI
  1. Claude Fable 5SD not available · single run
    100.0
  2. DeepSeek V4 FlashSD not available · single run
    100.0
  3. DeepSeek V4 ProSD not available · single run
    100.0
  4. DeepSeek V4.1 FlashSD not available · single run
    100.0
  5. GPT-5.6 SolSD not available · single run
    100.0
  6. GPT-6 LunaSD not available · single run
    100.0
  7. GPT-6.1 SolSD not available · single run
    100.0
  8. Claude Sonnet 5.5SD not available · single run
    99.5
  9. Claude Opus 5.5SD not available · single run
    98.8
  10. Gemini 3.1 Pro PreviewSD not available · single run
    98.5
  11. Gemini 3.5 FlashSD 2.6 · 3 retained runs
    97.9
  12. OpenAI o3SD not available · single run
    97.3
  13. Gemma 4 31B ITSD not available · single run
    96.8
  14. Mistral Medium 3.5SD not available · single run
    95.3
  15. Grok 4.5SD not available · single run
    90.3
  16. DeepSeek V4 Flash (no thinking)SD not available · single run
    89.3
  17. Mistral Small 4SD not available · single run
    85.5
  18. OpenAI GPT-4.1SD not available · single run
    79.0
  19. Claude Sonnet 4.5SD not available · single run
    63.5
  20. Claude Haiku 4.5SD not available · single run
    41.5
  21. Grok 4.3SD not available · single run
    30.0

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-E2 · Analisi III
The English version is a faithful editorial translation. The Italian source remains authoritative.

ESAME: Analisi 3 DATA: 20/08/2025 ESERCIZIO: 2

TESTO: 2. Nel piano cartesiano sia A ={(x, y) : x2 + y2≤a2,0≤x≤a, y≥x(1−x a)}(ove a > 0). (a) Disegnare A e calcolarne il baricentro geometrico. (b) Dire se gli integrali ∫ A 1 x dx dy e ∫ A 1 y dx dy convergono, in tal caso calcolandoli. Nello spazio cartesiano si disegnino la figura A nel piano orizzontale z = 0 e l’analoga figura A′ nel soprastante piano orizzontale z = a, e sia E il solido di tipo cilindrico con basi A e A′. (c) Verificare il teorema di Gauss per E e per il campo radiale F = (x, y, z). (d) Calcolare l’area della componente verticale S di ∂E con profili orizzontali parabolici. (1)

NOTE: (1)Può essere utile sapere che ∫√ 1 +u2du = 1 2(u √ 1 +u2 + log(u + √ 1 +u2)).

Original source textExact Italian record · no editorial changes+
ESAME: Analisi 3
DATA: 20/08/2025
ESERCIZIO: 2

TESTO:
2. Nel piano cartesiano sia A ={(x, y) : x2 + y2≤a2,0≤x≤a, y≥x(1−x
a)}(ove a > 0).
(a) Disegnare A e calcolarne il baricentro geometrico.
(b) Dire se gli integrali
∫
A
1
x dx dy e
∫
A
1
y dx dy convergono, in tal caso calcolandoli.
Nello spazio cartesiano si disegnino la figura A nel piano orizzontale z = 0 e l’analoga figura A′
nel soprastante piano orizzontale z = a, e sia E il solido di tipo cilindrico con basi A e A′.
(c) Verificare il teorema di Gauss per E e per il campo radiale F = (x, y, z).
(d) Calcolare l’area della componente verticale S di ∂E con profili orizzontali parabolici. (1)

NOTE:
(1)Può essere utile sapere che
∫√
1 +u2du = 1
2(u
√
1 +u2 + log(u +
√
1 +u2)).
TopicBaricentro, integrali impropri, verifica di Gauss e area laterale
Syllabus areaIntegrali multipli, Gauss e superfici
Task typemixed
Atomic criteria29
Subproblem a · 20.0%

Disegno e baricentro.

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

Inspect scoring criteria +
  • Formalizza A.

    T1 · 5 pts · Criterion (a_T1_01)
  • Imposta area/momenti.

    T2 · 3 pts · Criterion (a_T2_01)
  • Calcola area/momenti.

    T3 · 4 pts · Criterion (a_T3_01)
  • Dà G.

    T4 · 3 pts · Criterion (a_T4_01)
  • Rispetta bordi/a>0.

    T5 · 2 pts · Criterion (a_T5_01)
  • Controlla scala/posizione.

    T6 · 2 pts · Criterion (a_T6_01)
  • Usa definizione baricentro.

    T7 · 1 pts · Criterion (a_T7_01)
Subproblem b · 24.0%

Integrali singolari.

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

Inspect scoring criteria +
  • Identifica le singolarità.

    T1 · 5 pts · Criterion (b_T1_01)
  • Imposta integrali impropri.

    T2 · 4 pts · Criterion (b_T2_01)
  • Dimostra divergenza e valore.

    T3 · 5 pts · Criterion (b_T3_01)
  • Dà entrambe le conclusioni.

    T4 · 3 pts · Criterion (b_T4_01)
  • Gestisce improprietà rigorosamente.

    T5 · 3 pts · Criterion (b_T5_01)
  • Controlla segno/scala.

    T6 · 2 pts · Criterion (b_T6_01)
  • Applica Tonelli/Fubini.

    T7 · 2 pts · Criterion (b_T7_01)
Subproblem c · 35.0%

Verificare Gauss.

8 atomic criteria · T1 · T2 · T3 · T4 · T5 · T6 · T7 · T8

Inspect scoring criteria +
  • Identifica E e cinque facce.

    T1 · 6 pts · Criterion (c_T1_01)
  • Imposta volume/normali/flussi.

    T2 · 5 pts · Criterion (c_T2_01)
  • Calcola tutti i contributi.

    T3 · 7 pts · Criterion (c_T3_01)
  • Conclude Gauss.

    T4 · 5 pts · Criterion (c_T4_01)
  • Usa domini/orientazioni.

    T5 · 3 pts · Criterion (c_T5_01)
  • Controlla segni/scala.

    T6 · 2 pts · Criterion (c_T6_01)
  • Applica Gauss rigorosamente.

    T7 · 2 pts · Criterion (c_T7_01)
  • Verifica autonomamente Gauss.

    T8 · 5 pts · Criterion (c_T8_01)
Subproblem d · 21.0%

Area della parete parabolica.

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

Inspect scoring criteria +
  • Identifica S.

    T1 · 4 pts · Criterion (d_T1_01)
  • Imposta elemento d'area.

    T2 · 3 pts · Criterion (d_T2_01)
  • Calcola l'integrale.

    T3 · 4 pts · Criterion (d_T3_01)
  • Dà area finale.

    T4 · 4 pts · Criterion (d_T4_01)
  • Usa domini completi.

    T5 · 2 pts · Criterion (d_T5_01)
  • Controlla positività/scala.

    T6 · 2 pts · Criterion (d_T6_01)
  • Usa formula area parametrica.

    T7 · 2 pts · Criterion (d_T7_01)
Complete frozen rubricOriginal Italian record · exact JSON · SHA-256 d3b9f9dac295…+
{
  "rubric_version": "1.0",
  "judge_spec_version": "2.0",
  "item_id": "analisi_3_2025_quinto_appello_esercizio_2",
  "syllabus_macroarea": "Integrali multipli, Gauss e superfici",
  "topic": "Baricentro, integrali impropri, verifica di Gauss e area laterale",
  "task_type": "mixed",
  "created_without_model_answers": true,
  "frozen": true,
  "reference_status": "verified",
  "reference_notes": "Gold: A={0≤x≤a,x(1-x/a)≤y≤√(a²-x²)}; area=(3π-2)a²/12, momenti a³/4 e 19a³/60, G=(3a/(3π-2),19a/[5(3π-2)]). ∫1/x diverge; ∫1/y=(1+log2)a. Per E: divF=3, Vol=area(A)a; flussi A=R=0,A'=(3π-2)a³/12,S=-a³/3,C=πa³/2, totale=3Vol. Area(S)=a²(√2+log(1+√2))/2.",
  "subproblems": [
    {
      "id": "a",
      "weight": 0.2,
      "request": "Disegno e baricentro.",
      "expected_results": [
        "area,momenti,G gold"
      ],
      "required_conditions": [
        "a>0."
      ],
      "accepted_equivalences": [
        "Forme equivalenti."
      ],
      "accepted_alternative_methods": [
        "Metodi rigorosi compatibili col gold."
      ]
    },
    {
      "id": "b",
      "weight": 0.24,
      "request": "Integrali singolari.",
      "expected_results": [
        "1/x diverge",
        "1/y=(1+log2)a"
      ],
      "required_conditions": [
        "Tonelli/improprietà."
      ],
      "accepted_equivalences": [
        "Forme equivalenti."
      ],
      "accepted_alternative_methods": [
        "Metodi rigorosi compatibili col gold."
      ]
    },
    {
      "id": "c",
      "weight": 0.35,
      "request": "Verificare Gauss.",
      "expected_results": [
        "cinque componenti",
        "flussi gold",
        "totale=3Vol"
      ],
      "required_conditions": [
        "Normali uscenti."
      ],
      "accepted_equivalences": [
        "Forme equivalenti."
      ],
      "accepted_alternative_methods": [
        "Metodi rigorosi compatibili col gold."
      ]
    },
    {
      "id": "d",
      "weight": 0.21,
      "request": "Area della parete parabolica.",
      "expected_results": [
        "elemento d'area gold",
        "area gold"
      ],
      "required_conditions": [
        "x,z∈[0,a]."
      ],
      "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": 5,
      "description": "Formalizza A.",
      "full_credit_evidence": [
        "Quarto disco meno settore parabolico."
      ],
      "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": 3,
      "description": "Imposta area/momenti.",
      "full_credit_evidence": [
        "x-fili corretti."
      ],
      "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": 4,
      "description": "Calcola area/momenti.",
      "full_credit_evidence": [
        "Valori 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_T4_01",
      "subproblem_id": "a",
      "primary_dimension": "T4",
      "max_points": 3,
      "description": "Dà G.",
      "full_credit_evidence": [
        "Baricentro 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": 2,
      "description": "Rispetta bordi/a>0.",
      "full_credit_evidence": [
        "Limiti corretti."
      ],
      "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": 2,
      "description": "Controlla scala/posizione.",
      "full_credit_evidence": [
        "G~a e appartiene ad A."
      ],
      "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": 1,
      "description": "Usa definizione baricentro.",
      "full_credit_evidence": [
        "Momenti/area."
      ],
      "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": 5,
      "description": "Identifica le singolarità.",
      "full_credit_evidence": [
        "x=0,y=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_T2_01",
      "subproblem_id": "b",
      "primary_dimension": "T2",
      "max_points": 4,
      "description": "Imposta integrali impropri.",
      "full_credit_evidence": [
        "x-fili e logaritmi."
      ],
      "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": 5,
      "description": "Dimostra divergenza e valore.",
      "full_credit_evidence": [
        "a/x e (1+log2)a."
      ],
      "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": 3,
      "description": "Dà entrambe le conclusioni.",
      "full_credit_evidence": [
        "+∞ e valore 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": "b_T5_01",
      "subproblem_id": "b",
      "primary_dimension": "T5",
      "max_points": 3,
      "description": "Gestisce improprietà rigorosamente.",
      "full_credit_evidence": [
        "Endpoint e non negatività."
      ],
      "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/scala.",
      "full_credit_evidence": [
        "Non negativi e ~a."
      ],
      "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": "Applica Tonelli/Fubini.",
      "full_credit_evidence": [
        "Nessuna cancellazione."
      ],
      "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": "Identifica E e cinque facce.",
      "full_credit_evidence": [
        "A,A',S,C,R."
      ],
      "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 volume/normali/flussi.",
      "full_credit_evidence": [
        "Parametrizzazioni corrette."
      ],
      "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": 7,
      "description": "Calcola tutti i contributi.",
      "full_credit_evidence": [
        "Valori 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": "c_T4_01",
      "subproblem_id": "c",
      "primary_dimension": "T4",
      "max_points": 5,
      "description": "Conclude Gauss.",
      "full_credit_evidence": [
        "Somma=3Vol."
      ],
      "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": 3,
      "description": "Usa domini/orientazioni.",
      "full_credit_evidence": [
        "Intervalli 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": "c_T6_01",
      "subproblem_id": "c",
      "primary_dimension": "T6",
      "max_points": 2,
      "description": "Controlla segni/scala.",
      "full_credit_evidence": [
        "Flussi ~a³."
      ],
      "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 Gauss rigorosamente.",
      "full_credit_evidence": [
        "Ipotesi corrette."
      ],
      "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_T8_01",
      "subproblem_id": "c",
      "primary_dimension": "T8",
      "max_points": 5,
      "description": "Verifica autonomamente Gauss.",
      "full_credit_evidence": [
        "Due membri indipendenti."
      ],
      "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": "d_T1_01",
      "subproblem_id": "d",
      "primary_dimension": "T1",
      "max_points": 4,
      "description": "Identifica S.",
      "full_credit_evidence": [
        "Estrusione verticale della parabola."
      ],
      "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": "d_T2_01",
      "subproblem_id": "d",
      "primary_dimension": "T2",
      "max_points": 3,
      "description": "Imposta elemento d'area.",
      "full_credit_evidence": [
        "√(1+(1-2x/a)²)dxdz."
      ],
      "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": "d_T3_01",
      "subproblem_id": "d",
      "primary_dimension": "T3",
      "max_points": 4,
      "description": "Calcola l'integrale.",
      "full_credit_evidence": [
        "Sostituzione e primitiva corrette."
      ],
      "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": "d_T4_01",
      "subproblem_id": "d",
      "primary_dimension": "T4",
      "max_points": 4,
      "description": "Dà area finale.",
      "full_credit_evidence": [
        "Formula 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": "d_T5_01",
      "subproblem_id": "d",
      "primary_dimension": "T5",
      "max_points": 2,
      "description": "Usa domini completi.",
      "full_credit_evidence": [
        "[0,a]²."
      ],
      "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": "d_T6_01",
      "subproblem_id": "d",
      "primary_dimension": "T6",
      "max_points": 2,
      "description": "Controlla positività/scala.",
      "full_credit_evidence": [
        "Area positiva ~a²."
      ],
      "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": "d_T7_01",
      "subproblem_id": "d",
      "primary_dimension": "T7",
      "max_points": 2,
      "description": "Usa formula area parametrica.",
      "full_credit_evidence": [
        "Norma prodotto vettoriale."
      ],
      "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": "applicable"
  },
  "dimension_applicability_notes": {
    "T8": "Applicabile per la verifica esplicita richiesta."
  },
  "dimension_point_budget": {
    "T1": 20,
    "T2": 15,
    "T3": 20,
    "T4": 15,
    "T5": 10,
    "T6": 8,
    "T7": 7,
    "T8": 5
  },
  "applicable_max_score": 100,
  "normalization_rule": "Punteggio grezzo su 100.",
  "not_applicable_dimensions": [],
  "pertinent_checks": [
    "Parabola sotto arco.",
    "Asintotica a/x.",
    "Cinque flussi.",
    "Elemento d'area e scala."
  ],
  "known_error_severity": [
    {
      "error": "Baricentro errato",
      "severity": "major"
    },
    {
      "error": "Integrabilità invertita",
      "severity": "major"
    },
    {
      "error": "Gauss incompleto/circolare",
      "severity": "major"
    },
    {
      "error": "Area S errata",
      "severity": "major"
    }
  ],
  "rubric_specific_caps": [],
  "human_review_triggers": [
    "Decomposizione/orientazione alternativa incerta.",
    "Cancellazioni improprie."
  ],
  "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 run84.3s$0.4299,3820.00
DeepSeek V4 FlashDeepSeek · official model page ↗#1by score100.0SD not available · single run154.0s$0.005218,7720.00
DeepSeek V4 ProDeepSeek · official model page ↗#1by score100.0SD not available · single run259.2s$0.01618,6030.00
DeepSeek V4.1 FlashDeepSeek · official model page ↗#1by score100.0SD not available · single run98.1s$0.02823,9570.00
GPT-5.6 SolOpenAI · official model page ↗#1by score100.0SD not available · single run213.7s$0.41414,3430.00
GPT-6 LunaOpenAI · official model page ↗#1by score100.0SD not available · single run69.2s$0.00469,7250.00
GPT-6.1 SolOpenAI · official model page ↗#1by score100.0SD not available · single run198.5s$0.11111,6440.00
Claude Sonnet 5.5Anthropic · official model page ↗#8by score99.5SD not available · single run41.1s$0.0616,9190.00
Claude Opus 5.5Anthropic · official model page ↗#9by score98.8SD not available · single run69.4s$0.1679,1500.00
Gemini 3.1 Pro PreviewGoogle · official model page ↗#10by score98.5SD not available · single run99.0s$0.14412,5320.00
Gemini 3.5 FlashGoogle · official model page ↗#11by score97.9SD 2.6 · 3 retained runs594.6s$0.16118,4530.00
OpenAI o3OpenAI · official model page ↗#12by score97.3SD not available · single run82.2s$0.10413,4260.00
Gemma 4 31B ITGoogle · official model page ↗#13by score96.8SD not available · single run99.8s$0.00004,1880.00
Mistral Medium 3.5Mistral · official model page ↗#14by score95.3SD not available · single run105.0s$0.14119,3670.00
Grok 4.5xAI · official model page ↗#15by score90.3SD not available · single run122.5s$0.0488,5530.00
DeepSeek V4 Flash (no thinking)DeepSeek · official model page ↗#16by score89.3SD not available · single run43.1s$0.00186,5970.00
Mistral Small 4Mistral · official model page ↗#17by score85.5SD not available · single run120.5s$0.01424,4970.00
OpenAI GPT-4.1OpenAI · official model page ↗#18by score79.0SD not available · single run53.5s$0.0587,7570.00
Claude Sonnet 4.5Anthropic · official model page ↗#19by score63.5SD not available · single run43.5s$0.0463,6940.00
Claude Haiku 4.5Anthropic · official model page ↗#20by score41.5SD not available · single run29.3s$0.0245,4590.00
Grok 4.3xAI · official model page ↗#21by score30.0SD not available · single run88.8s$0.03113,0170.00
#1 by score

Claude Fable 5

Anthropic
100.0mean score

SD not available · single run

Latency
84.3s
Cost
$0.429
Tokens
9,382
Retries
0.00
Official model page ↗
#1 by score

DeepSeek V4 Flash

DeepSeek
100.0mean score

SD not available · single run

Latency
154.0s
Cost
$0.0052
Tokens
18,772
Retries
0.00
Official model page ↗
#1 by score

DeepSeek V4 Pro

DeepSeek
100.0mean score

SD not available · single run

Latency
259.2s
Cost
$0.016
Tokens
18,603
Retries
0.00
Official model page ↗
#1 by score

DeepSeek V4.1 Flash

DeepSeek
100.0mean score

SD not available · single run

Latency
98.1s
Cost
$0.028
Tokens
23,957
Retries
0.00
Official model page ↗
#1 by score

GPT-5.6 Sol

OpenAI
100.0mean score

SD not available · single run

Latency
213.7s
Cost
$0.414
Tokens
14,343
Retries
0.00
Official model page ↗
#1 by score

GPT-6 Luna

OpenAI
100.0mean score

SD not available · single run

Latency
69.2s
Cost
$0.0046
Tokens
9,725
Retries
0.00
Official model page ↗
#1 by score

GPT-6.1 Sol

OpenAI
100.0mean score

SD not available · single run

Latency
198.5s
Cost
$0.111
Tokens
11,644
Retries
0.00
Official model page ↗
#8 by score

Claude Sonnet 5.5

Anthropic
99.5mean score

SD not available · single run

Latency
41.1s
Cost
$0.061
Tokens
6,919
Retries
0.00
Official model page ↗
#9 by score

Claude Opus 5.5

Anthropic
98.8mean score

SD not available · single run

Latency
69.4s
Cost
$0.167
Tokens
9,150
Retries
0.00
Official model page ↗
#10 by score

Gemini 3.1 Pro Preview

Google
98.5mean score

SD not available · single run

Latency
99.0s
Cost
$0.144
Tokens
12,532
Retries
0.00
Official model page ↗
#11 by score

Gemini 3.5 Flash

Google
97.9mean score

SD 2.6 · 3 retained runs

Latency
594.6s
Cost
$0.161
Tokens
18,453
Retries
0.00
Official model page ↗
#12 by score

OpenAI o3

OpenAI
97.3mean score

SD not available · single run

Latency
82.2s
Cost
$0.104
Tokens
13,426
Retries
0.00
Official model page ↗
#13 by score

Gemma 4 31B IT

Google
96.8mean score

SD not available · single run

Latency
99.8s
Cost
$0.0000
Tokens
4,188
Retries
0.00
Official model page ↗
#14 by score

Mistral Medium 3.5

Mistral
95.3mean score

SD not available · single run

Latency
105.0s
Cost
$0.141
Tokens
19,367
Retries
0.00
Official model page ↗
#15 by score

Grok 4.5

xAI
90.3mean score

SD not available · single run

Latency
122.5s
Cost
$0.048
Tokens
8,553
Retries
0.00
Official model page ↗
#16 by score

DeepSeek V4 Flash (no thinking)

DeepSeek
89.3mean score

SD not available · single run

Latency
43.1s
Cost
$0.0018
Tokens
6,597
Retries
0.00
Official model page ↗
#17 by score

Mistral Small 4

Mistral
85.5mean score

SD not available · single run

Latency
120.5s
Cost
$0.014
Tokens
24,497
Retries
0.00
Official model page ↗
#18 by score

OpenAI GPT-4.1

OpenAI
79.0mean score

SD not available · single run

Latency
53.5s
Cost
$0.058
Tokens
7,757
Retries
0.00
Official model page ↗
#19 by score

Claude Sonnet 4.5

Anthropic
63.5mean score

SD not available · single run

Latency
43.5s
Cost
$0.046
Tokens
3,694
Retries
0.00
Official model page ↗
#20 by score

Claude Haiku 4.5

Anthropic
41.5mean score

SD not available · single run

Latency
29.3s
Cost
$0.024
Tokens
5,459
Retries
0.00
Official model page ↗
#21 by score

Grok 4.3

xAI
30.0mean score

SD not available · single run

Latency
88.8s
Cost
$0.031
Tokens
13,017
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
T190.1%Understanding / modelling
T289.8%Method selection
T386.3%Development
T488.4%Final results
T589.6%Domains / assumptions
T688.4%Consistency
T789.6%Rigor
T888.1%Independent verification
T1 through T8 attainment for each model-mode configuration
ConfigurationT120 ptsT215 ptsT320 ptsT415 ptsT510 ptsT68 ptsT77 ptsT85 pts
Claude Fable 5100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%
DeepSeek V4 Flash100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%
DeepSeek V4 Pro100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%
DeepSeek V4.1 Flash100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%
GPT-5.6 Sol100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%
GPT-6 Luna100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%
GPT-6.1 Sol100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%
Claude Sonnet 5.5100.0%100.0%100.0%100.0%100.0%93.8%100.0%100.0%
Claude Opus 5.593.8%100.0%100.0%100.0%100.0%100.0%100.0%100.0%
Gemini 3.1 Pro Preview92.5%100.0%100.0%100.0%100.0%100.0%100.0%100.0%
Gemini 3.5 Flash95.4%100.0%94.2%100.0%100.0%100.0%100.0%100.0%
OpenAI o392.5%100.0%100.0%100.0%92.5%93.8%100.0%100.0%
Gemma 4 31B IT86.3%100.0%100.0%100.0%100.0%93.8%100.0%100.0%
Mistral Medium 3.585.0%100.0%100.0%100.0%92.5%87.5%100.0%100.0%
Grok 4.585.0%91.7%82.5%100.0%85.0%100.0%92.9%100.0%
DeepSeek V4 Flash (no thinking)82.5%91.7%91.3%86.7%92.5%93.8%85.7%100.0%
Mistral Small 485.0%91.7%65.0%100.0%77.5%93.8%92.9%100.0%
OpenAI GPT-4.185.0%86.7%72.5%63.3%85.0%75.0%78.6%100.0%
Claude Sonnet 4.586.3%63.3%55.0%73.3%62.5%62.5%50.0%0.0%
Claude Haiku 4.556.3%30.0%36.3%28.3%40.0%56.3%46.4%50.0%
Grok 4.366.3%30.0%15.0%5.0%55.0%6.3%35.7%0.0%
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 ↗
#1DeepSeek V4 FlashDeepSeek · 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 ↗
#1DeepSeek V4.1 FlashDeepSeek · 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 LunaOpenAI · 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 ↗
#8Claude Sonnet 5.5Anthropic · 1 retained run · load on request99.5configuration mean+
Configuration recordOfficial model page ↗
#9Claude Opus 5.5Anthropic · 1 retained run · load on request98.8configuration mean+
Configuration recordOfficial model page ↗
#10Gemini 3.1 Pro PreviewGoogle · 1 retained run · load on request98.5configuration mean+
Configuration recordOfficial model page ↗
#11Gemini 3.5 FlashGoogle · 3 retained runs · load on request97.9configuration mean+
Configuration recordOfficial model page ↗
#12OpenAI o3OpenAI · 1 retained run · load on request97.3configuration mean+
Configuration recordOfficial model page ↗
#13Gemma 4 31B ITGoogle · 1 retained run · load on request96.8configuration mean+
Configuration recordOfficial model page ↗
#14Mistral Medium 3.5Mistral · 1 retained run · load on request95.3configuration mean+
Configuration recordOfficial model page ↗
#15Grok 4.5xAI · 1 retained run · load on request90.3configuration mean+
Configuration recordOfficial model page ↗
#16DeepSeek V4 Flash (no thinking)DeepSeek · 1 retained run · load on request89.3configuration mean+
Configuration recordOfficial model page ↗
#17Mistral Small 4Mistral · 1 retained run · load on request85.5configuration mean+
Configuration recordOfficial model page ↗
#18OpenAI GPT-4.1OpenAI · 1 retained run · load on request79.0configuration mean+
Configuration recordOfficial model page ↗
#19Claude Sonnet 4.5Anthropic · 1 retained run · load on request63.5configuration mean+
Configuration recordOfficial model page ↗
#20Claude Haiku 4.5Anthropic · 1 retained run · load on request41.5configuration mean+
Configuration recordOfficial model page ↗
#21Grok 4.3xAI · 1 retained run · load on request30.0configuration 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-E2
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