RISE Humanities Data Benchmark

A test run is a single execution of a benchmark test using a defined model configuration.
Each run represents how a particular large language model (LLM) — such as GPT-4, Claude-3, or Gemini — performed on a given task at a specific time, with specific settings.

A test run includes:

Prompt and role definition – what the model was asked to do and from what perspective (e.g. “as a historian”).
Model configuration – provider, model version, temperature, and other generation parameters.
Results – the model’s actual response and its evaluation (scores such as F1 or accuracy).
Usage and cost data – token counts and calculated API costs.
Metadata – information like the test date, benchmark name, and person who executed it.

Together, test runs make it possible to compare models, providers, and configurations across benchmarks in a transparent and reproducible way.

Result 1 of 99

Test T1748 at 2026-09-09

minutes information-extraction typed, handwritten 20 it, fr, de table person, location

openrouter qwen/qwen3.8-27b · temp 0.0 · dataclass MinutesPage

Response vs ground truth

One model response from this run. The per-input comparison needs JavaScript.

Fuzzy score100.0%

{"document":"Se_18_Assemblées_3_Bilanz1968_2_page_9","page_number":9,"entries":[{"number":"1","name":"Monsieur BREHAM Alain","address":"45 bd Charcot - NEUILLY-S/SEINE (92)
FRANCE","actions_o":"179","actions_p":"520","no_de_voix":"699","signature_present":false,"signature":""},{"number":"2","name":"Monsieur BREHAM Marc","address":"la Tuilerie - ST NOM LA BRETECHE
FRANCE","actions_o":"179","actions_p":"520","no_de_voix":"699","signature_present":false,"signature":""},{"number":"3","name":"Monsieur MASSON Daniel","address":"Villa la Cava, av. de la Cava 06 -
FRANCE CANNES","actions_o":"10","actions_p":"","no_de_voix":"10","signature_present":false,"signature":""},{"number":"4","name":"COMPAGNIE CENTRALE SICLI","address":"2/4 rue Blaise Pascal
93 - LE BLANC-MESNIL FRANCE","actions_o":"168","actions_p":"822","no_de_voix":"990","signature_present":false,"signature":""},{"number":"5","name":"SOCIETE DES MINES DE L'AURIERAS","address":"11 bis rue Balzac PARIS 8e
FRANCE","actions_o":"45","actions_p":"355","no_de_voix":"400","signature_present":false,"signature":""},{"number":"6","name":"SOCIETE DE RECHERCHES MINIERES FRAN-CAISES","address":"11 bis rue Balzac PARIS 8e
FRANCE","actions_o":"10","actions_p":"","no_de_voix":"10","signature_present":false,"signature":""},{"number":"7","name":"Monsieur PANI Antonio","address":"SESSA (Tessin)
SUISSE","actions_o":"10","actions_p":"","no_de_voix":"10","signature_present":false,"signature":""}],"total_actions":{"total_o":"","total_p":"","total_voix":""}}

Scoring

Fuzzy score83.8%

Speed

Model time, all inputs3150.9 s

Mean per input350.10 s

Slowest input1553.16 s

Inputs timed9

Summed model time, not elapsed: requests run in parallel and the worker count is not recorded, so the run finished sooner than this.

Costs / Pricing

Input tokens30.7K

Output tokens34K

Total tokens64.7K

Input cost$0.0082

Output cost$0.0815

Total cost$0.1141

Priced from 2026-09-08 · Input $/M $0.42 · Output $/M $3.00

Cite: Hindermann, Marti, Alberto, et al., (2026). RISE-UNIBAS/humanities_data_benchmark, 10.5281/zenodo.21975827

Result 2 of 99

Test T1718 at 2026-09-08

minutes information-extraction typed, handwritten 20 it, fr, de table person, location

openrouter z-ai/glm-5.3-flash · temp 0.0 · dataclass MinutesPage

Response vs ground truth

One model response from this run. The per-input comparison needs JavaScript.

Fuzzy score14.7%

{"document":"Se_18_Assemblées_3_Bilanz1968_2_page_9","page_number":9,"entries":[{"number":"label carefully","name":"Monsieur BREHAM Alain","address":"45 bd Charcot
NEUILLY-S/SEINE (92)
FRANCE","actions_o":"","actions_p":"","no_de_voix":"","signature_present":false,"signature":""}],"total_actions":{"total_o":"","total_p":"","total_voix":""}}

Scoring

Fuzzy score71.7%

Speed

Model time, all inputs364.9 s

Mean per input40.54 s

Slowest input124.67 s

Inputs timed9

Summed model time, not elapsed: requests run in parallel and the worker count is not recorded, so the run finished sooner than this.

Costs / Pricing

Input tokens38.2K

Output tokens11.3K

Total tokens49.5K

Input cost$0.0029

Output cost$0.0028

Total cost$0.0057

Priced from 2026-09-08 · Input $/M $0.075 · Output $/M $0.25

Cite: Hindermann, Marti, Alberto, et al., (2026). RISE-UNIBAS/humanities_data_benchmark, 10.5281/zenodo.21975827

Result 3 of 99

Test T1763 at 2026-09-08

minutes information-extraction typed, handwritten 20 it, fr, de table person, location

deepseek deepseek-v4-flash-vision-exp · temp 0.0 · dataclass MinutesPage

Response vs ground truth

One model response from this run. The per-input comparison needs JavaScript.

Fuzzy score100.0%

{"document":"Se_18_Assemblées_3_Bilanz1968_2_page_9","page_number":9,"entries":[{"number":"1","name":"Monsieur BREHAM Alain","address":"45 bd Charcot - NEUILLY-S/SEINE (92)
FRANCE","actions_o":"179","actions_p":"520","no_de_voix":"699","signature_present":false,"signature":""},{"number":"2","name":"Monsieur BREHAM Marc","address":"la Tuilerie - ST NOM LA BRETECHE
FRANCE","actions_o":"179","actions_p":"520","no_de_voix":"699","signature_present":false,"signature":""},{"number":"3","name":"Monsieur MASSON Daniel","address":"Villa la Cava, av. de la Cava 06 -
FRANCE CANNES","actions_o":"10","actions_p":"","no_de_voix":"10","signature_present":false,"signature":""},{"number":"4","name":"COMPAGNIE CENTRALE SICLI","address":"2/4 rue Blaise Pascal
93 - LE BLANC-MESNIL FRANCE","actions_o":"168","actions_p":"822","no_de_voix":"990","signature_present":false,"signature":""},{"number":"5","name":"SOCIETE DES MINES DE L'AURIERAS","address":"11 bis rue Balzac PARIS 8e
FRANCE","actions_o":"45","actions_p":"355","no_de_voix":"400","signature_present":false,"signature":""},{"number":"6","name":"SOCIETE DE RECHERCHES MINIERES FRANCAISES","address":"11 bis rue Balzac PARIS 8e
FRANCE","actions_o":"10","actions_p":"","no_de_voix":"10","signature_present":false,"signature":""},{"number":"7","name":"Monsieur PANI Antonio","address":"SESSA (Tessin)
SUISSE","actions_o":"10","actions_p":"","no_de_voix":"10","signature_present":false,"signature":""}],"total_actions":{"total_o":"","total_p":"","total_voix":""}}

Scoring

Fuzzy score79.4%

Speed

Model time, all inputs806.5 s

Mean per input89.62 s

Slowest input134.51 s

Inputs timed9

Summed model time, not elapsed: requests run in parallel and the worker count is not recorded, so the run finished sooner than this.

Costs / Pricing

Input tokens9.2K

Output tokens94.7K

Total tokens103.9K

Input cost$0.0041

Output cost$0.125

Total cost$0.129

Priced from 2026-09-08 · Input $/M $0.44 · Output $/M $1.32

Cite: Hindermann, Marti, Alberto, et al., (2026). RISE-UNIBAS/humanities_data_benchmark, 10.5281/zenodo.21975827

Result 4 of 99

Test T1703 at 2026-09-08

minutes information-extraction typed, handwritten 20 it, fr, de table person, location

openrouter meta/muse-spark-1.3 · temp 0.0 · dataclass MinutesPage

Response vs ground truth

One model response from this run. The per-input comparison needs JavaScript.

Fuzzy score99.9%

{"document":"Se_18_Assembl\u0000e9es_3_Bilanz1968_2_page_9","page_number":9,"entries":[{"number":"1","name":"Monsieur BREHAM Alain","address":"45 bd Charcot - NEUILLY-S/SEINE (92)
FRANCE","actions_o":"179","actions_p":"520","no_de_voix":"699","signature_present":false,"signature":""},{"number":"2","name":"Monsieur BREHAM Marc","address":"la Tuilerie - ST NOM LA BRETECHE
FRANCE","actions_o":"179","actions_p":"520","no_de_voix":"699","signature_present":false,"signature":""},{"number":"3","name":"Monsieur MASSON Daniel","address":"Villa la Cava, av. de la Cava 06 -
FRANCE CANNES","actions_o":"10","actions_p":"","no_de_voix":"10","signature_present":false,"signature":""},{"number":"4","name":"COMPAGNIE CENTRALE SICLI","address":"2/4 rue Blaise Pascal
93 - LE BLANC-MESNIL FRANCE","actions_o":"168","actions_p":"822","no_de_voix":"990","signature_present":false,"signature":""},{"number":"5","name":"SOCIETE DES MINES DE L'AURIERAS","address":"11 bis rue Balzac PARIS 8e
FRANCE","actions_o":"45","actions_p":"355","no_de_voix":"400","signature_present":false,"signature":""},{"number":"6","name":"SOCIETE DE RECHERCHES MINIERES FRAN-
CAISES","address":"11 bis rue Balzac PARIS 8e
FRANCE","actions_o":"10","actions_p":"","no_de_voix":"10","signature_present":false,"signature":""},{"number":"7","name":"Monsieur PANI Antonio","address":"SESSA (Tessin)
SUISSE","actions_o":"10","actions_p":"","no_de_voix":"10","signature_present":false,"signature":""}],"total_actions":{"total_o":"","total_p":"","total_voix":""}}

Scoring

Fuzzy score84.4%

Speed

Model time, all inputs358.1 s

Mean per input39.79 s

Slowest input94.10 s

Inputs timed9

Summed model time, not elapsed: requests run in parallel and the worker count is not recorded, so the run finished sooner than this.

Costs / Pricing

Input tokens39.5K

Output tokens44.5K

Total tokens84K

Input cost$0.0494

Output cost$0.1891

Total cost$0.2385

Priced from 2026-09-08 · Input $/M $1.25 · Output $/M $4.25

Cite: Hindermann, Marti, Alberto, et al., (2026). RISE-UNIBAS/humanities_data_benchmark, 10.5281/zenodo.21975827

Result 5 of 99

Test T1733 at 2026-09-08

minutes information-extraction typed, handwritten 20 it, fr, de table person, location

openrouter qwen/qwen3.8-flash · temp 0.0 · dataclass MinutesPage

Response vs ground truth

One model response from this run. The per-input comparison needs JavaScript.

Fuzzy score94.9%

{"document":"Se_18_Assemblées_3_Bilanz1968_2_page_9","page_number":9,"entries":[{"number":"1","name":"Monsieur BREAM Alain","address":"45 bd Charcot - NEUILLY-S/SEINE (92)
FRANCE","actions_o":"179","actions_p":"520","no_de_voix":"699","signature_present":false,"signature":""},{"number":"2","name":"Monsieur BREAM Marc","address":"la Tuilerie - ST NOM LA BRETECHE
FRANCE","actions_o":"179","actions_p":"520","no_de_voix":"699","signature_present":false,"signature":""},{"number":"3","name":"Monsieur MASSON Daniel","address":"Villa la Cava, av. de la Cava 06 -
FRANCE
CANNES","actions_o":"10","actions_p":"","no_de_voix":"10","signature_present":false,"signature":""},{"number":"4","name":"COMPAGNIE CENTRALE SICLI","address":"2/4 rue Blaise Pascal
93 - LE BLANC-MESNIL
FRANCE","actions_o":"168","actions_p":"822","no_de_voix":"990","signature_present":false,"signature":""},{"number":"5","name":"SOCIETE DES MINES DE L'AURIERAS","address":"11 bis rue Balzac PARIS 8e
FRANCE","actions_o":"45","actions_p":"355","no_de_voix":"400","signature_present":false,"signature":""},{"number":"6","name":"SOCIETE DE RECHERCHES MINIERES FRAN-
CAISES","address":"11 bis rue Balzac PARIS 8e
FRANCE","actions_o":"10","actions_p":"","no_de_voix":"10","signature_present":false,"signature":""},{"number":"7","name":"Monsieur PANI Antonio","address":"SESSA (Tessin)
SUISSE","actions_o":"10","actions_p":"","no_de_voix":"10","signature_present":false,"signature":""}],"total_actions":{"total_o":"601","total_p":"2017","total_voix":"2818"}}

Scoring

Fuzzy score85.0%

Speed

Model time, all inputs1472.4 s

Mean per input163.60 s

Slowest input318.04 s

Inputs timed9

Summed model time, not elapsed: requests run in parallel and the worker count is not recorded, so the run finished sooner than this.

Costs / Pricing

Input tokens28.4K

Output tokens125K

Total tokens153.4K

Input cost$0.0038

Output cost$0.0559

Total cost$0.063

Priced from 2026-09-08 · Input $/M $0.15 · Output $/M $0.47

Cite: Hindermann, Marti, Alberto, et al., (2026). RISE-UNIBAS/humanities_data_benchmark, 10.5281/zenodo.21975827

Result 6 of 99

Test T1673 at 2026-09-04

minutes information-extraction typed, handwritten 20 it, fr, de table person, location

openai gpt-6-astra · temp 1.0 · dataclass MinutesPage

Response vs ground truth

One model response from this run. The per-input comparison needs JavaScript.

Fuzzy score100.0%

{"document":"Se_18_Assemblées_3_Bilanz1968_2_page_9","page_number":9,"entries":[{"number":"1","name":"Monsieur BREHAM Alain","address":"45 bd Charcot - NEUILLY-S/SEINE (92)
FRANCE","actions_o":"179","actions_p":"520","no_de_voix":"699","signature_present":false,"signature":""},{"number":"2","name":"Monsieur BREHAM Marc","address":"la Tuilerie - ST NOM LA BRETECHE
FRANCE","actions_o":"179","actions_p":"520","no_de_voix":"699","signature_present":false,"signature":""},{"number":"3","name":"Monsieur MASSON Daniel","address":"Villa la Cava, av. de la Cava 06 -
FRANCE CANNES","actions_o":"10","actions_p":"","no_de_voix":"10","signature_present":false,"signature":""},{"number":"4","name":"COMPAGNIE CENTRALE SICLI","address":"2/4 rue Blaise Pascal
93 - LE BLANC-MESNIL FRANCE","actions_o":"168","actions_p":"822","no_de_voix":"990","signature_present":false,"signature":""},{"number":"5","name":"SOCIETE DES MINES DE L'AURIERAS","address":"11 bis rue Balzac PARIS 8e
FRANCE","actions_o":"45","actions_p":"355","no_de_voix":"400","signature_present":false,"signature":""},{"number":"6","name":"SOCIETE DE RECHERCHES MINIERES FRAN-
CAISES","address":"11 bis rue Balzac PARIS 8e
FRANCE","actions_o":"10","actions_p":"","no_de_voix":"10","signature_present":false,"signature":""},{"number":"7","name":"Monsieur PANI Antonio","address":"SESSA (Tessin)
SUISSE","actions_o":"10","actions_p":"","no_de_voix":"10","signature_present":false,"signature":""}],"total_actions":{"total_o":"","total_p":"","total_voix":""}}

Scoring

Fuzzy score94.1%

Speed

Model time, all inputs162.8 s

Mean per input18.09 s

Slowest input47.71 s

Inputs timed9

Summed model time, not elapsed: requests run in parallel and the worker count is not recorded, so the run finished sooner than this.

Costs / Pricing

Input tokens37.5K

Output tokens10.6K

Total tokens48.2K

Input cost$0.3752

Output cost$0.532

Total cost$0.9072

Priced from 2026-09-03 · Input $/M $10.00 · Output $/M $50.00

Cite: Hindermann, Marti, Alberto, et al., (2026). RISE-UNIBAS/humanities_data_benchmark, 10.5281/zenodo.21975827

Result 7 of 99

Test T1658 at 2026-09-03

minutes information-extraction typed, handwritten 20 it, fr, de table person, location

genai gemini-3.8-flash · temp 0.0 · dataclass MinutesPage

Response vs ground truth

One model response from this run. The per-input comparison needs JavaScript.

Fuzzy score100.0%

{"document":"Se_18_Assemblées_3_Bilanz1968_2_page_9","page_number":9,"entries":[{"number":"1","name":"Monsieur BREHAM Alain","address":"45 bd Charcot - NEUILLY-S/SEINE (92)
FRANCE","actions_o":"179","actions_p":"520","no_de_voix":"699","signature_present":false,"signature":""},{"number":"2","name":"Monsieur BREHAM Marc","address":"la Tuilerie - ST NOM LA BRETECHE
FRANCE","actions_o":"179","actions_p":"520","no_de_voix":"699","signature_present":false,"signature":""},{"number":"3","name":"Monsieur MASSON Daniel","address":"Villa la Cava, av. de la Cava 06 -
FRANCE CANNES","actions_o":"10","actions_p":"","no_de_voix":"10","signature_present":false,"signature":""},{"number":"4","name":"COMPAGNIE CENTRALE SICLI","address":"2/4 rue Blaise Pascal
93 - LE BLANC-MESNIL FRANCE","actions_o":"168","actions_p":"822","no_de_voix":"990","signature_present":false,"signature":""},{"number":"5","name":"SOCIETE DES MINES DE L'AURIERAS","address":"11 bis rue Balzac PARIS 8e
FRANCE","actions_o":"45","actions_p":"355","no_de_voix":"400","signature_present":false,"signature":""},{"number":"6","name":"SOCIETE DE RECHERCHES MINIERES FRANCAISES","address":"11 bis rue Balzac PARIS 8e
FRANCE","actions_o":"10","actions_p":"","no_de_voix":"10","signature_present":false,"signature":""},{"number":"7","name":"Monsieur PANI Antonio","address":"SESSA (Tessin)
SUISSE","actions_o":"10","actions_p":"","no_de_voix":"10","signature_present":false,"signature":""}],"total_actions":{"total_o":"","total_p":"","total_voix":""}}

Scoring

Fuzzy score95.5%

Speed

Model time, all inputs239.3 s

Mean per input26.59 s

Slowest input104.45 s

Inputs timed9

Summed model time, not elapsed: requests run in parallel and the worker count is not recorded, so the run finished sooner than this.

Costs / Pricing

Input tokens10.8K

Output tokens9.1K

Total tokens20K

Input cost$0.0081

Output cost$0.0342

Total cost$0.0424

Priced from 2026-09-02 · Input $/M $0.75 · Output $/M $3.75

Cite: Hindermann, Marti, Alberto, et al., (2026). RISE-UNIBAS/humanities_data_benchmark, 10.5281/zenodo.21975827

Result 8 of 99

Test T1643 at 2026-08-18

minutes information-extraction typed, handwritten 20 it, fr, de table person, location

openrouter z-ai/glm-5v-turbo · temp 0.0 · dataclass MinutesPage

Response vs ground truth

One model response from this run. The per-input comparison needs JavaScript.

{
  "document": "Se_18_Assemblées_3_Bilanz1968_2_page_9",
  "page_number": 9,
  "entries": [
    {
      "number": "1",
      "name": "Monsieur BREHAM Alain",
      "address": "45 bd Charcot - NEUILLY-S/SEINE (92)
FRANCE",
      "actions_o": "179",
      "actions_p": "520",
      "no_de_voix": "699",
      "signature_present": false,
      "signature": ""
    },
    {
      "number": "2",
      "name": "Monsieur BREHAM Marc",
      "address": "la Tuilerie - ST NOM LA BRETECHE
FRANCE",
      "actions_o": "179",
      "actions_p": "520",
      "no_de_voix": "699",
      "signature_present": false,
      "signature": ""
    },
    {
      "number": "3",
      "name": "Monsieur MASSON Daniel",
      "address": "Villa la Cava, av. de la Cava 06 -
FRANCE CANNES",
      "actions_o": "10",
      "actions_p": "",
      "no_de_voix": "10",
      "signature_present": false,
      "signature": ""
    },
    {
      "number": "4",
      "name": "COMPAGNIE CENTRALE SICLI",
      "address": "2/4 rue Blaise Pascal
93 - LE BLANC-MESNIL FRANCE",
      "actions_o": "168",
      "actions_p": "822",
      "no_de_voix": "990",
      "signature_present": false,
      "signature": ""
    },
    {
      "number": "5",
      "name": "SOCIETE DES MINES DE L'AURIERAS",
      "address": "11 bis rue Balzac PARIS 8e
FRANCE",
      "actions_o": "45",
      "actions_p": "355",
      "no_de_voix": "400",
      "signature_present": false,
      "signature": ""
    },
    {
      "number": "6",
      "name": "SOCIETE DE RECHERCHES MINIERES FRAN-CAISES",
      "address": "11 bis rue Balzac PARIS 8e
FRANCE",
      "actions_o": "10",
      "actions_p": "",
      "no_de_voix": "10",
      "signature_present": false,
      "signature": ""
    },
    {
      "number": "7",
      "name": "Monsieur PANI Antonio",
      "address": "SESSA (Tessin)
SUISSE",
      "actions_o": "10",
      "actions_p": "",
      "no_de_voix": "10",
      "signature_present": false,
      "signature": ""
    }
  ],
  "total_actions": {
    "total_o": "",
    "total_p": "",
    "total_voix": ""
  }
}

Scoring

Fuzzy score75.1%

Speed

Model time, all inputs509.7 s

Mean per input56.64 s

Slowest input75.38 s

Inputs timed9

Summed model time, not elapsed: requests run in parallel and the worker count is not recorded, so the run finished sooner than this.

Costs / Pricing

Input tokens41.1K

Output tokens8.2K

Total tokens49.3K

Input cost$0.0493

Output cost$0.0329

Total cost$0.0822

Priced from 2026-08-18 · Input $/M $1.20 · Output $/M $4.00

Cite: Hindermann, Marti, Alberto, et al., (2026). RISE-UNIBAS/humanities_data_benchmark, 10.5281/zenodo.21975827

Result 9 of 99

Test T1598 at 2026-08-18

minutes information-extraction typed, handwritten 20 it, fr, de table person, location

genai gemini-3.7-flash · temp 0.0 · dataclass MinutesPage

Response vs ground truth

One model response from this run. The per-input comparison needs JavaScript.

Fuzzy score100.0%

{"document":"Se_18_Assemblées_3_Bilanz1968_2_page_9","page_number":9,"entries":[{"number":"1","name":"Monsieur BREHAM Alain","address":"45 bd Charcot - NEUILLY-S/SEINE (92)
FRANCE","actions_o":"179","actions_p":"520","no_de_voix":"699","signature_present":false,"signature":""},{"number":"2","name":"Monsieur BREHAM Marc","address":"la Tuilerie - ST NOM LA BRETECHE
FRANCE","actions_o":"179","actions_p":"520","no_de_voix":"699","signature_present":false,"signature":""},{"number":"3","name":"Monsieur MASSON Daniel","address":"Villa la Cava, av. de la Cava 06 -
FRANCE CANNES","actions_o":"10","actions_p":"","no_de_voix":"10","signature_present":false,"signature":""},{"number":"4","name":"COMPAGNIE CENTRALE SICLI","address":"2/4 rue Blaise Pascal
93 - LE BLANC-MESNIL FRANCE","actions_o":"168","actions_p":"822","no_de_voix":"990","signature_present":false,"signature":""},{"number":"5","name":"SOCIETE DES MINES DE L'AURIERAS","address":"11 bis rue Balzac PARIS 8e
FRANCE","actions_o":"45","actions_p":"355","no_de_voix":"400","signature_present":false,"signature":""},{"number":"6","name":"SOCIETE DE RECHERCHES MINIERES FRAN-
CAISES","address":"11 bis rue Balzac PARIS 8e
FRANCE","actions_o":"10","actions_p":"","no_de_voix":"10","signature_present":false,"signature":""},{"number":"7","name":"Monsieur PANI Antonio","address":"SESSA (Tessin)
SUISSE","actions_o":"10","actions_p":"","no_de_voix":"10","signature_present":false,"signature":""}],"total_actions":{"total_o":"","total_p":"","total_voix":""}}

Scoring

Fuzzy score93.7%

Speed

Model time, all inputs68.6 s

Mean per input7.62 s

Slowest input20.00 s

Inputs timed9

Summed model time, not elapsed: requests run in parallel and the worker count is not recorded, so the run finished sooner than this.

Costs / Pricing

Input tokens10.8K

Output tokens9.1K

Total tokens20K

Input cost$0.0081

Output cost$0.0342

Total cost$0.0423

Priced from 2026-08-18 · Input $/M $0.75 · Output $/M $3.75

Cite: Hindermann, Marti, Alberto, et al., (2026). RISE-UNIBAS/humanities_data_benchmark, 10.5281/zenodo.21975827

Result 10 of 99

Test T1613 at 2026-08-18

minutes information-extraction typed, handwritten 20 it, fr, de table person, location

x-ai grok-4.6 · temp 0.0 · dataclass MinutesPage

Response vs ground truth

One model response from this run. The per-input comparison needs JavaScript.

Fuzzy score100.0%

{"document":"Se_18_Assemblées_3_Bilanz1968_2_page_9","page_number":9,"entries":[{"number":"1","name":"Monsieur BREHAM Alain","address":"45 bd Charcot - NEUILLY-S/SEINE (92)
FRANCE","actions_o":"179","actions_p":"520","no_de_voix":"699","signature_present":false,"signature":""},{"number":"2","name":"Monsieur BREHAM Marc","address":"la Tuilerie - ST NOM LA BRETECHE
FRANCE","actions_o":"179","actions_p":"520","no_de_voix":"699","signature_present":false,"signature":""},{"number":"3","name":"Monsieur MASSON Daniel","address":"Villa la Cava, av. de la Cava 06 -
FRANCE CANNES","actions_o":"10","actions_p":"","no_de_voix":"10","signature_present":false,"signature":""},{"number":"4","name":"COMPAGNIE CENTRALE SICLI","address":"2/4 rue Blaise Pascal
93 - LE BLANC-MESNIL FRANCE","actions_o":"168","actions_p":"822","no_de_voix":"990","signature_present":false,"signature":""},{"number":"5","name":"SOCIETE DES MINES DE L'AURIERAS","address":"11 bis rue Balzac PARIS 8e
FRANCE","actions_o":"45","actions_p":"355","no_de_voix":"400","signature_present":false,"signature":""},{"number":"6","name":"SOCIETE DE RECHERCHES MINIERES FRAN-
CAISES","address":"11 bis rue Balzac PARIS 8e
FRANCE","actions_o":"10","actions_p":"","no_de_voix":"10","signature_present":false,"signature":""},{"number":"7","name":"Monsieur PANI Antonio","address":"SESSA (Tessin)
SUISSE","actions_o":"10","actions_p":"","no_de_voix":"10","signature_present":false,"signature":""}],"total_actions":{"total_o":"","total_p":"","total_voix":""}}

Scoring

Fuzzy score92.2%

Speed

Model time, all inputs796.8 s

Mean per input88.53 s

Slowest input174.20 s

Inputs timed9

Summed model time, not elapsed: requests run in parallel and the worker count is not recorded, so the run finished sooner than this.

Costs / Pricing

Input tokens28.5K

Output tokens7.5K

Total tokens36.1K

Input cost$0.057

Output cost$0.0452

Total cost$0.1022

Priced from 2026-08-18 · Input $/M $2.00 · Output $/M $6.00

Cite: Hindermann, Marti, Alberto, et al., (2026). RISE-UNIBAS/humanities_data_benchmark, 10.5281/zenodo.21975827

Search Test Runs

Search Results
Show compact results Refine Search New Search

Download JSON Download CSV

Test T1748 at 2026-09-09

Test T1718 at 2026-09-08

Test T1763 at 2026-09-08

Test T1703 at 2026-09-08

Test T1733 at 2026-09-08

Test T1673 at 2026-09-04

Test T1658 at 2026-09-03

Test T1643 at 2026-08-18

Test T1598 at 2026-08-18

Test T1613 at 2026-08-18

Search Test Runs

Search Results Show compact results Refine Search New Search Download Download JSON Download CSV

Test T1748 at 2026-09-09

Test T1718 at 2026-09-08

Test T1763 at 2026-09-08

Test T1703 at 2026-09-08

Test T1733 at 2026-09-08

Test T1673 at 2026-09-04

Test T1658 at 2026-09-03

Test T1643 at 2026-08-18

Test T1598 at 2026-08-18

Test T1613 at 2026-08-18

Search Results
Show compact results Refine Search New Search

Download JSON Download CSV