RISE Humanities Data Benchmark, 0.6.1

Search Test Runs

 

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.

Search Results
Show compact results Refine Search New Search
Download JSON Download CSV (Downloads are limited to 250 results.)

Your search for Benchmark 'company_lists__true' with Search Hidden 'False' returned 360 results, showing page 32 of 36.
Result 311 of 360

Test T0361 at 2026-01-24

book-page information-extraction printed 20 en, de list company

genai gemini-2.5-pro · temp 0.5 · dataclass ListPage

Response vs ground truth

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

Precision46.3%
Recall47.7%
True positives31
False positives36
False negatives34
F1 score47.0%
Total fields94

{"page_id":"24","entries":[{"entry_id":"24-1","company_name":"A. Boreux","location":"null"},{"entry_id":"24-2","company_name":"Brunnenverwaltung Eptingen","location":"Eptingen"},{"entry_id":"24-3","company_name":"Singer & Buchenhorner A.-G.","location":"null"},{"entry_id":"24-4","company_name":"Alf. Dürr, J. H. Neukomm's Nachf.","location":"null"},{"entry_id":"24-5","company_name":"Ausstattungsmagazine Ed. Senft","location":"null"},{"entry_id":"24-6","company_name":"Basler Möbelfabrik A.-G. vorm. Hermann Wagner & Cie.","location":"null"},{"entry_id":"24-7","company_name":"Adolf Bürgin","location":"null"},{"entry_id":"24-8","company_name":"Bussinger & Cie.","location":"null"},{"entry_id":"24-9","company_name":"Fränkel & Voellmy","location":"null"},{"entry_id":"24-10","company_name":"H. Hartmann","location":"null"},{"entry_id":"24-11","company_name":"Kunsthandlung Rath","location":"null"},{"entry_id":"24-12","company_name":"M. Russ","location":"null"},{"entry_id":"24-13","company_name":"Alf. Schray (Kleinmöbel)","location":"null"},{"entry_id":"24-14","company_name":"Wolf & Glatz","location":"null"},{"entry_id":"24-15","company_name":"Gebr. Antonietti","location":"null"},{"entry_id":"24-16","company_name":"A.-G. Bächtold & Cie.","location":"null"},{"entry_id":"24-17","company_name":"Maschinenfabrik Burckhardt A.-G.","location":"null"},{"entry_id":"24-18","company_name":"G. Meidinger & Cie.","location":"null"},{"entry_id":"24-19","company_name":"A.-G. für Motorlastwagen Soller","location":"Soller"},{"entry_id":"24-20","company_name":"Hug & Co.","location":"null"},{"entry_id":"24-21","company_name":"Schweiz. Geigenbaugesellschaft","location":"Liestal"},{"entry_id":"24-22","company_name":"Schweizerisches Musikhaus Bannwart & Cie.","location":"null"},{"entry_id":"24-23","company_name":"Henri Grunauer","location":"null"},{"entry_id":"24-24","company_name":"Hans Ritter-Soder","location":"null"},{"entry_id":"24-25","company_name":"Alb. Singeisen-Halder","location":"null"},{"entry_id":"24-26","company_name":"Ch. H. Pfister & Co.","location":"null"},{"entry_id":"24-27","company_name":"E. Müry & Cie.","location":"null"},{"entry_id":"24-28","company_name":"Affentranger, Haas & Plattner","location":"Niederdorf"},{"entry_id":"24-29","company_name":"Schweizerische Nähmaschinenfabrik A.-G.","location":"null"},{"entry_id":"24-30","company_name":"G. P. Richter","location":"null"},{"entry_id":"24-31","company_name":"E. H. Schacke","location":"null"}]}

Scoring

F1 micro51.2%
F1 macro50.9%
Micro precision51.1%
Micro recall51.2%
Instances15
True positives508
False positives486
False negatives484

Speed

Model time, all inputs406.6 s
Mean per input27.11 s
Slowest input64.12 s
Inputs timed15

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 tokens9.9K
Output tokens16.8K
Total tokens26.7K
Input cost$0.0123
Output cost$0.168
Total cost$0.5927
Reasoning cost usd$0.4124
Total reasoning tokens41.2K

Priced from 2026-01-23 · Input $/M $1.25 · Output $/M $10.00

Cite: Hindermann, Marti, Alberto, et al., (2026). RISE-UNIBAS/humanities_data_benchmark, 10.5281/zenodo.21975827
Result 312 of 360

Test T0360 at 2026-01-24

book-page information-extraction printed 20 en, de list company

genai gemini-2.5-flash · temp 0.5 · dataclass ListPage

Response vs ground truth

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

Precision48.5%
Recall49.2%
True positives32
False positives34
False negatives33
F1 score49.0%
Total fields94

{"page_id":"{page_id}","entries":[{"entry_id":"entry_1","company_name":"A. Boreux","location":""},{"entry_id":"entry_2","company_name":"Brunnenverwaltung Eptingen","location":"Eptingen"},{"entry_id":"entry_3","company_name":"Singer & Buchenhorner A.-G.","location":""},{"entry_id":"entry_4","company_name":"Alf. Dürr, J. H. Neukomm's Nachf.","location":""},{"entry_id":"entry_5","company_name":"Ausstattungsrnagazine Ed. Senft.","location":""},{"entry_id":"entry_6","company_name":"Basler Möbelfabrik A.-G. vorm. Hermann Wagner & Cie.","location":""},{"entry_id":"entry_7","company_name":"Adolf Bürgin.","location":""},{"entry_id":"entry_8","company_name":"Bussinger & Cie.","location":""},{"entry_id":"entry_9","company_name":"Fränkel & Voellmy.","location":""},{"entry_id":"entry_10","company_name":"H. Hartmann.","location":""},{"entry_id":"entry_11","company_name":"Kunsthandlung Rath.","location":""},{"entry_id":"entry_12","company_name":"M. Russ.","location":""},{"entry_id":"entry_13","company_name":"Alf. Schray","location":""},{"entry_id":"entry_14","company_name":"Wolf & Glatz.","location":""},{"entry_id":"entry_15","company_name":"Gebr. Antonietti.","location":""},{"entry_id":"entry_16","company_name":"A.-G. Bächtold & Cie.","location":""},{"entry_id":"entry_17","company_name":"Maschinenfabrik Burckhardt A.-G.","location":""},{"entry_id":"entry_18","company_name":"G. Meidinger & Cie.","location":""},{"entry_id":"entry_19","company_name":"A.-G. für Motorlastwagen Soller","location":""},{"entry_id":"entry_20","company_name":"Hug & Co.","location":""},{"entry_id":"entry_21","company_name":"Schweiz. Geigenbaugesellschaft","location":"Liestal"},{"entry_id":"entry_22","company_name":"Schweizerisches Musikhaus Bannwart & Cie.","location":""},{"entry_id":"entry_23","company_name":"Henri Grunauer.","location":""},{"entry_id":"entry_24","company_name":"Hans Ritter-Soder.","location":""},{"entry_id":"entry_25","company_name":"Alb. Singeisen-Halder.","location":""},{"entry_id":"entry_26","company_name":"Ch. H. Pfister & Co.","location":""},{"entry_id":"entry_27","company_name":"E. Müry & Cie.","location":""},{"entry_id":"entry_28","company_name":"Affentranger, Haas & Plattner.","location":"Niederdorf"},{"entry_id":"entry_29","company_name":"Schweizerische Nähmaschinenfabrik A.-G.","location":""},{"entry_id":"entry_30","company_name":"G. P. Richter","location":""},{"entry_id":"entry_31","company_name":"E. H. Schacke","location":""}]}

Scoring

F1 micro48.0%
F1 macro48.3%
Micro precision47.2%
Micro recall48.8%
Instances15
True positives484
False positives541
False negatives508

Speed

Model time, all inputs139.0 s
Mean per input9.27 s
Slowest input17.70 s
Inputs timed15

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 tokens4.3K
Output tokens12.3K
Total tokens16.5K
Input cost$0.0013
Output cost$0.0307
Total cost$0.0877
Reasoning cost usd$0.0557
Total reasoning tokens22.3K

Priced from 2026-01-23 · Input $/M $0.30 · Output $/M $2.50

Cite: Hindermann, Marti, Alberto, et al., (2026). RISE-UNIBAS/humanities_data_benchmark, 10.5281/zenodo.21975827
Result 313 of 360

Test T0359 at 2026-01-24

book-page information-extraction printed 20 en, de list company

genai gemini-2.5-flash · temp 0.5 · dataclass ListPage

Response vs ground truth

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

Precision47.7%
Recall47.7%
True positives31
False positives34
False negatives34
F1 score48.0%
Total fields94

{"page_id":"24","entries":[{"entry_id":"24-1","company_name":"A. Boreux","location":""},{"entry_id":"24-2","company_name":"Brunnenverwaltung Eptingen","location":""},{"entry_id":"24-3","company_name":"Singer & Buchenhorner A.-G.","location":""},{"entry_id":"24-4","company_name":"Alf. Dürr, J. H. Neukomm's Nachf.","location":""},{"entry_id":"24-5","company_name":"Ausstattungsmagazine Ed. Senft.","location":""},{"entry_id":"24-6","company_name":"Basler Möbelfabrik A.-G. vorm. Hermann Wagner & Cie.","location":""},{"entry_id":"24-7","company_name":"Adolf Bürgin.","location":""},{"entry_id":"24-8","company_name":"Bussinger & Cie.","location":""},{"entry_id":"24-9","company_name":"Fränkel & Voellmy.","location":""},{"entry_id":"24-10","company_name":"H. Hartmann.","location":""},{"entry_id":"24-11","company_name":"Kunsthandlung Rath.","location":""},{"entry_id":"24-12","company_name":"M. Russ.","location":""},{"entry_id":"24-13","company_name":"Alf. Schray (Kleinmöbel).","location":""},{"entry_id":"24-14","company_name":"Wolf & Glatz.","location":""},{"entry_id":"24-15","company_name":"Gebr. Antonietti.","location":""},{"entry_id":"24-16","company_name":"A.-G. Bächtold & Cie.","location":""},{"entry_id":"24-17","company_name":"Maschinenfabrik Burckhardt A.-G.","location":""},{"entry_id":"24-18","company_name":"G. Meidinger & Cie.","location":""},{"entry_id":"24-19","company_name":"A.-G. für Motorlastwagen Soller","location":""},{"entry_id":"24-20","company_name":"Hug & Co.","location":""},{"entry_id":"24-21","company_name":"Schweiz. Geigenbaugesellschaft","location":"Liestal"},{"entry_id":"24-22","company_name":"Schweizerisches Musikhaus Bannwart & Cie.","location":""},{"entry_id":"24-23","company_name":"Henri Grunauer.","location":""},{"entry_id":"24-24","company_name":"Hans Ritter-Soder.","location":""},{"entry_id":"24-25","company_name":"Alb. Singeisen-Halder.","location":""},{"entry_id":"24-26","company_name":"Ch. H. Pfister & Co.","location":""},{"entry_id":"24-27","company_name":"E. Müry & Cie.","location":""},{"entry_id":"24-28","company_name":"Affentranger, Haas & Plattner.","location":"Niederdorf"},{"entry_id":"24-29","company_name":"Schweizerische Nähmaschinenfabrik A.-G.","location":""},{"entry_id":"24-30","company_name":"G. P. Richter","location":""},{"entry_id":"24-31","company_name":"E. H. Schacke","location":""}]}

Scoring

F1 micro51.8%
F1 macro50.9%
Micro precision51.8%
Micro recall51.8%
Instances15
True positives514
False positives479
False negatives478

Speed

Model time, all inputs235.9 s
Mean per input15.73 s
Slowest input61.17 s
Inputs timed15

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 tokens9.9K
Output tokens13.8K
Total tokens23.7K
Input cost$0.003
Output cost$0.0346
Total cost$0.1289
Reasoning cost usd$0.0913
Total reasoning tokens36.5K

Priced from 2026-01-23 · Input $/M $0.30 · Output $/M $2.50

Cite: Hindermann, Marti, Alberto, et al., (2026). RISE-UNIBAS/humanities_data_benchmark, 10.5281/zenodo.21975827
Result 314 of 360

Test T0380 at 2026-01-24

book-page information-extraction printed 20 en, de list company

anthropic claude-sonnet-4-5-20250929 · temp 0.5 · dataclass ListPage

Response vs ground truth

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

Precision33.0%
Recall47.7%
True positives31
False positives63
False negatives34
F1 score39.0%
Total fields94

{"page_id":"24","entries":[{"entry_id":"1","company_name":"A. Boreux","location":"<UNKNOWN>"},{"entry_id":"2","company_name":"Brunnenverwaltung Eptingen","location":"<UNKNOWN>"},{"entry_id":"3","company_name":"Singer & Buchenhorner A.-G.","location":"<UNKNOWN>"},{"entry_id":"4","company_name":"Alf. Dürr, J. H. Neukomm's Nachf.","location":"<UNKNOWN>"},{"entry_id":"5","company_name":"Ausstattungsmagazine Ed. Senft","location":"<UNKNOWN>"},{"entry_id":"6","company_name":"Basler Möbelfabrik A.-G. vorm. Hermann Wagner & Cie.","location":"<UNKNOWN>"},{"entry_id":"7","company_name":"Adolf Bürgin","location":"<UNKNOWN>"},{"entry_id":"8","company_name":"Bussinger & Cie.","location":"<UNKNOWN>"},{"entry_id":"9","company_name":"Fränkel & Voellmy","location":"<UNKNOWN>"},{"entry_id":"10","company_name":"H. Hartmann","location":"<UNKNOWN>"},{"entry_id":"11","company_name":"Kunsthandlung Rath","location":"<UNKNOWN>"},{"entry_id":"12","company_name":"M. Russ","location":"<UNKNOWN>"},{"entry_id":"13","company_name":"Alf. Schray","location":"<UNKNOWN>"},{"entry_id":"14","company_name":"Wolf & Glatz","location":"<UNKNOWN>"},{"entry_id":"15","company_name":"Gebr. Antonietti","location":"<UNKNOWN>"},{"entry_id":"16","company_name":"A.-G. Bächtold & Cie.","location":"<UNKNOWN>"},{"entry_id":"17","company_name":"Maschinenfabrik Burckhardt A.-G.","location":"<UNKNOWN>"},{"entry_id":"18","company_name":"G. Meidinger & Cie.","location":"<UNKNOWN>"},{"entry_id":"19","company_name":"A.-G. für Motorlastwagen Soller","location":"<UNKNOWN>"},{"entry_id":"20","company_name":"Hug & Co.","location":"Schweiz"},{"entry_id":"21","company_name":"Geigenbaugesellschaft Liestal","location":"<UNKNOWN>"},{"entry_id":"22","company_name":"Schweizerisches Musikhaus Bannwart & Cie.","location":"<UNKNOWN>"},{"entry_id":"23","company_name":"Henri Grunauer","location":"<UNKNOWN>"},{"entry_id":"24","company_name":"Hans Ritter-Soder","location":"<UNKNOWN>"},{"entry_id":"25","company_name":"Alb. Singeisen-Halder","location":"<UNKNOWN>"},{"entry_id":"26","company_name":"Ch. H. Pfister & Co.","location":"<UNKNOWN>"},{"entry_id":"27","company_name":"E. Müry & Cie.","location":"<UNKNOWN>"},{"entry_id":"28","company_name":"Allentranger, Haas & Plattner","location":"Niederdorf"},{"entry_id":"29","company_name":"Schweizerische Nähmaschinfabrik A.-G.","location":"<UNKNOWN>"},{"entry_id":"30","company_name":"G. P. Richter","location":"<UNKNOWN>"},{"entry_id":"31","company_name":"E. H. Schacke","location":"<UNKNOWN>"}]}

Scoring

F1 micro38.9%
F1 macro38.4%
Micro precision37.9%
Micro recall39.8%
Instances15
True positives395
False positives646
False negatives597

Speed

Model time, all inputs257.3 s
Mean per input17.15 s
Slowest input28.16 s
Inputs timed15

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 tokens35.8K
Output tokens16.7K
Total tokens52.5K
Input cost$0.1074
Output cost$0.2501
Total cost$0.3576

Priced from 2026-01-23 · Input $/M $3.00 · Output $/M $15.00

Cite: Hindermann, Marti, Alberto, et al., (2026). RISE-UNIBAS/humanities_data_benchmark, 10.5281/zenodo.21975827
Result 315 of 360

Test T0364 at 2026-01-24

book-page information-extraction printed 20 en, de list company

genai gemini-2.5-flash-lite · temp 0.5 · dataclass ListPage

Response vs ground truth

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

Precision13.0%
Recall20.0%
True positives13
False positives87
False negatives52
F1 score16.0%
Total fields100

{"page_id":"{page_id}","entries":[{"entry_id":"Mikroskopie und Zubehör","company_name":"A. Boreux","location":"N/A"},{"entry_id":"Mineralwasser","company_name":"Brunnenverwaltung Eptingen","location":"N/A"},{"entry_id":"Mineralwasser","company_name":"Singer & Buchenhorner A.-G.","location":"N/A"},{"entry_id":"Mineralwasser","company_name":"Alf. Dürr, J. H. Neukomm's Nachf. (künstliches)","location":"N/A"},{"entry_id":"Möbel, hölzerne","company_name":"Ausstattungsmagazine Ed. Senft","location":"N/A"},{"entry_id":"Möbel, hölzerne","company_name":"Basler Möbelfabrik A.-G. vorm. Hermann Wagner & Cie.","location":"N/A"},{"entry_id":"Möbel, hölzerne","company_name":"Adolf Bürgin","location":"N/A"},{"entry_id":"Möbel, hölzerne","company_name":"Bussinger & Cie.","location":"N/A"},{"entry_id":"Möbel, hölzerne","company_name":"Fränkel & Voellmy","location":"N/A"},{"entry_id":"Möbel, hölzerne","company_name":"H. Hartmann","location":"N/A"},{"entry_id":"Möbel, hölzerne","company_name":"Kunsthandlung Rath","location":"N/A"},{"entry_id":"Möbel, hölzerne","company_name":"M. Russ","location":"N/A"},{"entry_id":"Möbel, hölzerne","company_name":"Alf. Schray (Kleinmöbel)","location":"N/A"},{"entry_id":"Möbel, hölzerne","company_name":"Wolf & Glatz","location":"N/A"},{"entry_id":"Mosaik- und Terrazzo-Böden","company_name":"Gebr. Antonietti","location":"N/A"},{"entry_id":"Motoren","company_name":"A.-G. Bächtold & Cie. (Benzinmotoren, Dieselmotoren, Gasmotoren, Rohölmotoren, Sauggasmotoren, Schiffsmotoren)","location":"N/A"},{"entry_id":"Motoren","company_name":"Maschinenfabrik Burckhardt A.-G. (Druckluftmotoren für Laboratorien)","location":"N/A"},{"entry_id":"Motoren","company_name":"G. Meidinger & Cie. (für Webstuhlantrieb, Centrifugalantrieb, fahrbare Motoren mit Zahnradbetrieb, Automobilmotoren)","location":"N/A"},{"entry_id":"Motoren","company_name":"s. Elektromotoren","location":"N/A"},{"entry_id":"Motorlastwagen","company_name":"A.-G. für Motorlastwagen Soller (auch Reparaturstücke)","location":"N/A"},{"entry_id":"Musikinstrumente","company_name":"Hug & Co. (Blechblasinstrumente)","location":"Schweiz"},{"entry_id":"Musikinstrumente","company_name":"Schweiz. Geigenbaugesellschaft Liestal (Geigen, Celli, Bässe, Bögen, Gitarren, Zithern)","location":"N/A"},{"entry_id":"Musikinstrumente","company_name":"Schweizerisches Musikhaus Bannwart & Cie. (Mundharmonikas, Ziehharmonikas, Zungenmusikinstrumente, Blechblasinstrumente)","location":"N/A"},{"entry_id":"Musterkarten für chemische Fabriken, Färbereien etc.","company_name":"Henri Grunauer","location":"N/A"},{"entry_id":"Musterkarten für chemische Fabriken, Färbereien etc.","company_name":"Hans Ritter-Soder","location":"N/A"},{"entry_id":"Musterkarten für chemische Fabriken, Färbereien etc.","company_name":"Alb. Singeisen-Halder","location":"N/A"},{"entry_id":"Magnesiacement","company_name":"Ch. H. Pfister & Co.","location":"N/A"},{"entry_id":"Nähfaden","company_name":"E. Müry & Cie.","location":"N/A"},{"entry_id":"Nähmaschinen","company_name":"Affentranger, Haas & Plattner","location":"Niederdorf"},{"entry_id":"Nähmaschinen","company_name":"Schweizerische Nähmaschinenfabrik A.-G. (für Hand-, Fuss- und elektrischen Betrieb, Fabriktische für Kraftbetrieb)","location":"N/A"},{"entry_id":"Nähseide","company_name":"s. Floretseide","location":"N/A"},{"entry_id":"Nährsalzpräparate","company_name":"G. P. Richter (Nährsalze «Gerstyl», Nährsalz - Bananencacao, Nährsalz - Hafercacao, Nährsalz - Kaffee)","location":"N/A"},{"entry_id":"Nährsalzpräparate","company_name":"E. H. Schacke (Nährsalz-Cacao, Nährsalz-Kaffee)","location":"N/A"}]}

Scoring

F1 micro37.6%
F1 macro39.0%
Micro precision36.0%
Micro recall39.3%
Instances15
True positives390
False positives693
False negatives602

Speed

Model time, all inputs62.3 s
Mean per input4.15 s
Slowest input9.21 s
Inputs timed15

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 tokens4.3K
Output tokens17.7K
Total tokens21.9K
Input cost$0.0004
Output cost$0.0071
Total cost$0.0075
Reasoning cost usd$0.00
Total reasoning tokens2

Priced from 2026-01-23 · Input $/M $0.10 · Output $/M $0.40

Cite: Hindermann, Marti, Alberto, et al., (2026). RISE-UNIBAS/humanities_data_benchmark, 10.5281/zenodo.21975827
Result 316 of 360

Test T0530 at 2026-01-24

book-page information-extraction printed 20 en, de list company

anthropic claude-haiku-4-5-20251001 · temp 0.5 · dataclass ListPage

Response vs ground truth

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

Precision1.1%
Recall1.5%
True positives1
False positives90
False negatives64
F1 score1.0%
Total fields94

{"page_id":"{page_id}","entries":[{"entry_id":"1","company_name":"A. Boreux","location":"Unknown"},{"entry_id":"2","company_name":"Brunnenverwaltung Eptingen Singer & Buchhorner A.-G.","location":"Eptingen"},{"entry_id":"3","company_name":"Alf. Dürr, J. H. Neukomm's Nachf. (künstliches)","location":"Unknown"},{"entry_id":"4","company_name":"Basler Möbelfabrik A.G.","location":"Basel"},{"entry_id":"5","company_name":"Hermann Wagner & Cie.","location":"Unknown"},{"entry_id":"6","company_name":"Adolf Bürgin","location":"Unknown"},{"entry_id":"7","company_name":"Bussinger & Cie.","location":"Unknown"},{"entry_id":"8","company_name":"Fränkel & Voellmy","location":"Unknown"},{"entry_id":"9","company_name":"H. Hartmann","location":"Unknown"},{"entry_id":"10","company_name":"Kunsthandlung Rath","location":"Unknown"},{"entry_id":"11","company_name":"M. Russ","location":"Unknown"},{"entry_id":"12","company_name":"Alf. Schray (Kleinmöbel)","location":"Unknown"},{"entry_id":"13","company_name":"Wolf & Glatz","location":"Unknown"},{"entry_id":"14","company_name":"Gebr. Antonietti","location":"Unknown"},{"entry_id":"15","company_name":"A.-G. Bächtold & Cie.","location":"Unknown"},{"entry_id":"16","company_name":"Maschinenfabrik Burckhardt A.-G.","location":"Unknown"},{"entry_id":"17","company_name":"G. Meidinger & Cie.","location":"Unknown"},{"entry_id":"18","company_name":"A.-G. für Motorlastwagen Soller","location":"Soller"},{"entry_id":"19","company_name":"Hug & Co. (Blechblasinstrumente)","location":"Switzerland"},{"entry_id":"20","company_name":"Geigenbaugesellschaft Liestal","location":"Liestal"},{"entry_id":"21","company_name":"Schweizerisches Musikhaus Bannwart & Cie.","location":"Switzerland"},{"entry_id":"22","company_name":"Henri Grunauer","location":"Unknown"},{"entry_id":"23","company_name":"Hans Ritter-Soder","location":"Unknown"},{"entry_id":"24","company_name":"Alb. Singeisen-Halder","location":"Unknown"},{"entry_id":"25","company_name":"Ch. H. Pfsler & Co.","location":"Unknown"},{"entry_id":"26","company_name":"E. Müry & Cie.","location":"Unknown"},{"entry_id":"27","company_name":"Affentranger, Haas & Plattner","location":"Niederdorf"},{"entry_id":"28","company_name":"Schweizerische Nähmaschinenfabrik A.-G.","location":"Switzerland"},{"entry_id":"29","company_name":"G. P. Richter","location":"Unknown"},{"entry_id":"30","company_name":"E. H. Schacke","location":"Unknown"}]}

Scoring

F1 micro40.6%
F1 macro41.2%
Micro precision39.8%
Micro recall41.3%
Instances15
True positives410
False positives619
False negatives582

Speed

Model time, all inputs118.2 s
Mean per input7.88 s
Slowest input14.23 s
Inputs timed15

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 tokens35.8K
Output tokens16.2K
Total tokens52K
Input cost$0.0358
Output cost$0.081
Total cost$0.1168

Priced from 2026-01-23 · Input $/M $1.00 · Output $/M $5.00

Cite: Hindermann, Marti, Alberto, et al., (2026). RISE-UNIBAS/humanities_data_benchmark, 10.5281/zenodo.21975827
Result 317 of 360

Test T0379 at 2026-01-24

book-page information-extraction printed 20 en, de list company

anthropic claude-sonnet-4-5-20250929 · temp 0.5 · dataclass ListPage

Response vs ground truth

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

Precision37.5%
Recall36.9%
True positives24
False positives40
False negatives41
F1 score37.0%
Total fields94

{"page_id": "24", "entries": [{"entry_id": "24-1", "company_name": "A. Boreux", "location": null}, {"entry_id": "24-2", "company_name": "Brunnenverwaltung Eptingen", "location": null}, {"entry_id": "24-3", "company_name": "Singer & Buchenhorner A.-G.", "location": null}, {"entry_id": "24-4", "company_name": "Alf. D\u00fcrr, J. H. Neukomm's Nachf.", "location": null}, {"entry_id": "24-5", "company_name": "Ausstattungsmagazine Ed. Senft", "location": null}, {"entry_id": "24-6", "company_name": "Basler M\u00f6belfabrik A.-G. vorm. Hermann Wagner & Cie.", "location": null}, {"entry_id": "24-7", "company_name": "Adolf B\u00fcrgin", "location": null}, {"entry_id": "24-8", "company_name": "Bussinger & Cie.", "location": null}, {"entry_id": "24-9", "company_name": "Fr\u00e4nkel & Voellmy", "location": null}, {"entry_id": "24-10", "company_name": "H. Hartmann", "location": null}, {"entry_id": "24-11", "company_name": "Kunsthandlung Rath", "location": null}, {"entry_id": "24-12", "company_name": "M. Russ", "location": null}, {"entry_id": "24-13", "company_name": "Alf. Schray (Kleinm\u00f6bel)", "location": null}, {"entry_id": "24-14", "company_name": "Wolf & Glatz", "location": null}, {"entry_id": "24-15", "company_name": "Gebr. Antonietti", "location": null}, {"entry_id": "24-16", "company_name": "A.-G. B\u00e4chtold & Cie.", "location": null}, {"entry_id": "24-17", "company_name": "Maschinenfabrik Burckhardt A.-G.", "location": null}, {"entry_id": "24-18", "company_name": "G. Meidinger & Cie.", "location": null}, {"entry_id": "24-19", "company_name": "A.-G. f\u00fcr Motorlastwagen Soller", "location": null}, {"entry_id": "24-20", "company_name": "Hug & Co. (Blechblasinstrumente)", "location": null}, {"entry_id": "24-21", "company_name": "Schweiz. Geigenbaugesellschaft Liestal (Geigen, Celli, B\u00e4sse, B\u00f6-gen, Gitarren, Zithern)", "location": null}, {"entry_id": "24-22", "company_name": "Schweizerisches Musikhaus Bannwart & Cie. (Mundharmonikas, Ziehharmonikas, Zungenmusik-instrumente, Blechblasinstrumente)", "location": null}, {"entry_id": "24-23", "company_name": "Henri Grunauer", "location": null}, {"entry_id": "24-24", "company_name": "Hans Ritter-Soder", "location": null}, {"entry_id": "24-25", "company_name": "Alb. Singeisen-Halder", "location": null}, {"entry_id": "24-26", "company_name": "Ch. H. Pfister & Co.", "location": null}, {"entry_id": "24-27", "company_name": "E. M\u00fcry & Cie.", "location": null}, {"entry_id": "24-28", "company_name": "Allentranger, Haas & Plattner, Niederdorf (Schrauben und kleine Bestandteile f\u00fcr N\u00e4hmaschinen)", "location": "Niederdorf"}, {"entry_id": "24-29", "company_name": "Schweizerische N\u00e4hmaschinenfabrik A.-G. (f\u00fcr Hand-, Fuss- und elektrischen Betrieb, Fabrikitische f\u00fcr Kraftbetrieb)", "location": null}, {"entry_id": "24-30", "company_name": "G. P. Richter (N\u00e4hrsalze \u00abGerstyl\u00bb, N\u00e4hrsalz - Bananencacao, N\u00e4hrsalz - Hafercacao, N\u00e4hrsalz - Kaffee)", "location": null}, {"entry_id": "24-31", "company_name": "E. H. Schacke (N\u00e4hrsalz-Cacao, N\u00e4hrsalz-Kaffee)", "location": null}]}

Scoring

F1 micro40.2%
F1 macro38.9%
Micro precision40.9%
Micro recall39.6%
Instances15
True positives393
False positives568
False negatives599

Speed

Model time, all inputs263.3 s
Mean per input17.55 s
Slowest input28.89 s
Inputs timed15

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 tokens41.6K
Output tokens17.4K
Total tokens59K
Input cost$0.1248
Output cost$0.2611
Total cost$0.3859

Priced from 2026-01-23 · Input $/M $3.00 · Output $/M $15.00

Cite: Hindermann, Marti, Alberto, et al., (2026). RISE-UNIBAS/humanities_data_benchmark, 10.5281/zenodo.21975827
Result 318 of 360

Test T0529 at 2026-01-24

book-page information-extraction printed 20 en, de list company

anthropic claude-haiku-4-5-20251001 · temp 0.5 · dataclass ListPage

Response vs ground truth

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

Precision42.4%
Recall43.1%
True positives28
False positives38
False negatives37
F1 score43.0%
Total fields94

{"page_id": "24", "entries": [{"entry_id": "24-1", "company_name": "A. Boreux", "location": null}, {"entry_id": "24-2", "company_name": "Brunnenverwaltung Eptingen", "location": null}, {"entry_id": "24-3", "company_name": "Singer & Buchehorner A.-G.", "location": null}, {"entry_id": "24-4", "company_name": "Alf. D\u00fcrr, J. H. Neukomm's Nachf. (k\u00fcnstliches)", "location": null}, {"entry_id": "24-5", "company_name": "Ausstattungsmagazine Ed. Senft", "location": null}, {"entry_id": "24-6", "company_name": "Basler M\u00f6belfabrik A.-G. vorm. Hermann Wagner & Cie.", "location": null}, {"entry_id": "24-7", "company_name": "Adolf B\u00fcrgin", "location": null}, {"entry_id": "24-8", "company_name": "Bussinger & Cie.", "location": null}, {"entry_id": "24-9", "company_name": "Fr\u00e4nkel & Voellmy", "location": null}, {"entry_id": "24-10", "company_name": "H. Hartmann", "location": null}, {"entry_id": "24-11", "company_name": "Kunsthandlung Rath", "location": null}, {"entry_id": "24-12", "company_name": "M. Russ", "location": null}, {"entry_id": "24-13", "company_name": "Alf. Schray (Kleinm\u00f6bel)", "location": null}, {"entry_id": "24-14", "company_name": "Wolf & Glatz", "location": null}, {"entry_id": "24-15", "company_name": "Gebr. Antonietti", "location": null}, {"entry_id": "24-16", "company_name": "A.-G. B\u00e4chtold & Cie.", "location": null}, {"entry_id": "24-17", "company_name": "Maschinenfabrik Burckhardt A.-G.", "location": null}, {"entry_id": "24-18", "company_name": "G. Meidinger & Cie.", "location": null}, {"entry_id": "24-19", "company_name": "A.-G. f\u00fcr Motorlastwagen Soller", "location": null}, {"entry_id": "24-20", "company_name": "Hug & Co. (Blechblasinstrumente)", "location": "Schweiz"}, {"entry_id": "24-21", "company_name": "Geigenbaugesellschaft Liestal", "location": "Geigen, Celli, B\u00e4sse, B\u00f6gen, Gitarren, Zithern"}, {"entry_id": "24-22", "company_name": "Schweizerisches Musikhaus Bannwart & Cie.", "location": null}, {"entry_id": "24-23", "company_name": "Henri Grunauer", "location": null}, {"entry_id": "24-24", "company_name": "Hans Ritter-Soder", "location": null}, {"entry_id": "24-25", "company_name": "Alb. Singeisen-Halder", "location": null}, {"entry_id": "24-26", "company_name": "Ch. H. Pfsler & Co.", "location": null}, {"entry_id": "24-27", "company_name": "E. M\u00fcry & Cie.", "location": null}, {"entry_id": "24-28", "company_name": "Affentranger, Haas & Plattner", "location": "Niederdorf"}, {"entry_id": "24-29", "company_name": "Schweizerische N\u00e4hmaschinenfabrik A.-G.", "location": null}, {"entry_id": "24-30", "company_name": "G. P. Richter", "location": null}, {"entry_id": "24-31", "company_name": "E. H. Schacke", "location": null}]}

Scoring

F1 micro48.7%
F1 macro49.1%
Micro precision48.7%
Micro recall48.7%
Instances15
True positives483
False positives509
False negatives509

Speed

Model time, all inputs119.1 s
Mean per input7.94 s
Slowest input13.90 s
Inputs timed15

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 tokens41.6K
Output tokens17.3K
Total tokens58.9K
Input cost$0.0416
Output cost$0.0865
Total cost$0.1281

Priced from 2026-01-23 · Input $/M $1.00 · Output $/M $5.00

Cite: Hindermann, Marti, Alberto, et al., (2026). RISE-UNIBAS/humanities_data_benchmark, 10.5281/zenodo.21975827
Result 319 of 360

Test T0518 at 2026-01-24

book-page information-extraction printed 20 en, de list company

anthropic claude-opus-4-5-20251101 · temp 0.5 · dataclass ListPage

Response vs ground truth

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

Precision1.6%
Recall1.5%
True positives1
False positives62
False negatives64
F1 score2.0%
Total fields94

{"page_id": "24", "entries": [{"entry_id": "24-1", "company_name": "A. Boreux", "location": null}, {"entry_id": "24-2", "company_name": "Brunnenverwaltung Eptingen Singer & Buchenhorner A.-G.", "location": null}, {"entry_id": "24-3", "company_name": "Alf. D\u00fcrr, J. H. Neukomm's Nachf.", "location": null}, {"entry_id": "24-4", "company_name": "Ausstattungsmagazine Ed. Senft.", "location": null}, {"entry_id": "24-5", "company_name": "Basler M\u00f6belfabrik A.-G. vorm. Hermann Wagner & Cie.", "location": null}, {"entry_id": "24-6", "company_name": "Adolf B\u00fcrgin", "location": null}, {"entry_id": "24-7", "company_name": "Bussinger & Cie.", "location": null}, {"entry_id": "24-8", "company_name": "Fr\u00e4nkel & Voellmy", "location": null}, {"entry_id": "24-9", "company_name": "H. Hartmann", "location": null}, {"entry_id": "24-10", "company_name": "Kunsthandlung Rath", "location": null}, {"entry_id": "24-11", "company_name": "M. Russ", "location": null}, {"entry_id": "24-12", "company_name": "Alf. Schray (Kleinm\u00f6bel)", "location": null}, {"entry_id": "24-13", "company_name": "Wolf & Glatz", "location": null}, {"entry_id": "24-14", "company_name": "Gebr. Antonietti", "location": null}, {"entry_id": "24-15", "company_name": "A.-G. B\u00e4chtold & Cie.", "location": null}, {"entry_id": "24-16", "company_name": "Maschinenfabrik Burckhardt A.-G.", "location": null}, {"entry_id": "24-17", "company_name": "G. Meidinger & Cie.", "location": null}, {"entry_id": "24-18", "company_name": "A.-G. f\u00fcr Motorlastwagen Soller", "location": null}, {"entry_id": "24-19", "company_name": "Hug & Co.", "location": null}, {"entry_id": "24-20", "company_name": "Schweiz. Geigenbaugesellschaft", "location": "Liestal"}, {"entry_id": "24-21", "company_name": "Schweizerisches Musikhaus Bannwart & Cie.", "location": null}, {"entry_id": "24-22", "company_name": "Henri Grunauer", "location": null}, {"entry_id": "24-23", "company_name": "Hans Ritter-Soder", "location": null}, {"entry_id": "24-24", "company_name": "Alb. Singeisen-Halder", "location": null}, {"entry_id": "24-25", "company_name": "Ch. H. Pfister & Co.", "location": null}, {"entry_id": "24-26", "company_name": "E. M\u00fcry & Cie.", "location": null}, {"entry_id": "24-27", "company_name": "Affentranger, Haas & Plattner", "location": "Niederdorf"}, {"entry_id": "24-28", "company_name": "Schweizerische N\u00e4hmaschinenfabrik A.-G.", "location": null}, {"entry_id": "24-29", "company_name": "G. P. Richter", "location": null}, {"entry_id": "24-30", "company_name": "E. H. Schacke", "location": null}]}

Scoring

F1 micro54.0%
F1 macro53.8%
Micro precision54.2%
Micro recall53.8%
Instances15
True positives534
False positives451
False negatives458

Speed

Model time, all inputs201.9 s
Mean per input13.46 s
Slowest input22.78 s
Inputs timed15

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 tokens41.6K
Output tokens13.3K
Total tokens54.9K
Input cost$0.208
Output cost$0.3316
Total cost$0.5396

Priced from 2026-01-23 · Input $/M $5.00 · Output $/M $25.00

Cite: Hindermann, Marti, Alberto, et al., (2026). RISE-UNIBAS/humanities_data_benchmark, 10.5281/zenodo.21975827
Result 320 of 360

Test T0363 at 2026-01-24

book-page information-extraction printed 20 en, de list company

genai gemini-2.5-flash-lite · temp 0.5 · dataclass ListPage

Response vs ground truth

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

Precision1.4%
Recall1.5%
True positives1
False positives68
False negatives64
F1 score1.0%
Total fields94

{"page_id":"24","entries":[{"entry_id":"24-1","company_name":"Mikroskopie und Zubehör (Deckgläser, Objektträger, Cartonnage).","location":"A. Boreux."},{"entry_id":"24-2","company_name":"Mineralwasser.","location":"Brunnenverwaltung Eptingen"},{"entry_id":"24-3","company_name":"Singer & Buchenhorner A.-G.","location":"Alf. Dürr, J. H. Neukomm's Nachf. (künstliches)."},{"entry_id":"24-4","company_name":"Möbel, hölzerne.","location":"Ausstattungsmagazine Ed. Senft."},{"entry_id":"24-5","company_name":"Basler Möbelfabrik A.-G. vorm. Hermann Wagner & Cie.","location":"Adolf Bürgin."},{"entry_id":"24-6","company_name":"Bussinger & Cie.","location":"Fränkel & Voellmy."},{"entry_id":"24-7","company_name":"H. Hartmann.","location":"Kunsthandlung Rath."},{"entry_id":"24-8","company_name":"M. Russ.","location":"Alf. Schray (Kleinmöbel)."},{"entry_id":"24-9","company_name":"Wolf & Glatz.","location":"Mosaik- und Terrazzo-Böden."},{"entry_id":"24-10","company_name":"Gebr. Antonietti.","location":"Motoren."},{"entry_id":"24-11","company_name":"A.-G. Bächtold & Cie. (Benzinmotoren, Dieselmotoren, Gasmotoren, Rohölmotoren, Sauggasmotoren, Schiffsmotoren).","location":"Maschinenfabrik Burckhardt A.-G. (Druckluftmotoren für Laboratorien)."},{"entry_id":"24-12","company_name":"G. Meidinger & Cie. (für Webstuhlantrieb, Centrifugenantrieb, fahrbare Motoren mit Zahnradbetrieb, Automobilmotoren).","location":"s. Elektromotoren."},{"entry_id":"24-13","company_name":"Motorlastwagen.","location":"A.-G. für Motorlastwagen Soller (auch Reparaturstücke)."},{"entry_id":"24-14","company_name":"Musikinstrumente.","location":"Hug & Co. (Blechblasinstrumente)."},{"entry_id":"24-15","company_name":"Schweiz. Geigenbaugesellschaft Liestal (Geigen, Celli, Bässe, Bögen, Gitarren, Zithern).","location":"Schweizerisches Musikhaus Bannwart & Cie. (Mundharmonikas, Ziehharmonikas, Zungenmusikinstrumente, Blechblasinstrumente)."},{"entry_id":"24-16","company_name":"Musterkarten für chemische Fabriken, Färbereien etc.","location":"Henri Grunauer."},{"entry_id":"24-17","company_name":"Hans Ritter-Soder.","location":"Alb. Singeisen-Halder."},{"entry_id":"24-18","company_name":"Magnesiacement.","location":"Ch. H. Pfister & Co."},{"entry_id":"24-19","company_name":"Nähfaden.","location":"E. Müry & Cie."},{"entry_id":"24-20","company_name":"Nähmaschinen.","location":"Affenträger, Haas & Plattner, Nieder- dorf (Schrauben und kleine Bestandteile für Nähmaschinen)."},{"entry_id":"24-21","company_name":"Schweizerische Nähmaschinenfabrik A.-G. (für Hand-, Fuss- und elektrischen Betrieb, Fabriktische für Kraftbetrieb).","location":"Nähseide, s. Flortseide."},{"entry_id":"24-22","company_name":"Nährsalzpräparate.","location":"G. P. Richter (Nährsalze «Gerstyl», Nährsalz - Bananencacao, Nährsalz - Hafercacao, Nährsalz - Kaffee)."},{"entry_id":"24-23","company_name":"E. H. Schacke (Nährsalz-Cacao, Nährsalz-Kaffee).","location":"null"}]}

Scoring

F1 micro32.7%
F1 macro33.6%
Micro precision33.7%
Micro recall31.8%
Instances15
True positives315
False positives620
False negatives677

Speed

Model time, all inputs60.7 s
Mean per input4.05 s
Slowest input7.94 s
Inputs timed15

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 tokens9.9K
Output tokens17.3K
Total tokens27.2K
Input cost$0.001
Output cost$0.0069
Total cost$0.0079
Reasoning cost usd$0.00
Total reasoning tokens4

Priced from 2026-01-23 · Input $/M $0.10 · Output $/M $0.40

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