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 51 of 187

Test T1425 at 2026-09-16

index-card information-extraction typed, printed, handwritten 20, 19 de, fr, en, la, el, fi, sv, pl index bibliographic

genai gemini-3.6-flash · temp 0.0 · dataclass Document

Response vs ground truth

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

Precision25.0%

Recall33.3%

True positives1

False positives3

False negatives2

F1 score29.0%

Total fields12

{"type":{"type":"Reference"},"author":{"last_name":"Montaghemi","first_name":"Nourhomadeh"},"publication":{"title":"Sonnenbichler - Montaghemi, Nourhomadeh","year":"","place":"","pages":"","publisher":"","format":"","editor":null},"library_reference":{"shelfmark":"","subjects":""}}

Scoring

F1 micro88.1%

F1 macro87.0%

Micro precision86.3%

Micro recall89.9%

Instances263

True positives2,170

False positives344

False negatives245

Speed

Model time, all inputs2070.2 s

Mean per input7.87 s

Slowest input16.43 s

Inputs timed263

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 tokens406.2K

Output tokens40.5K

Total tokens446.8K

Input cost$0.3047

Output cost$0.152

Total cost$1.67

Reasoning cost usd$1.22

Total reasoning tokens324.6K

Priced from 2026-09-16 · 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 52 of 187

Test T1605 at 2026-09-16

index-card information-extraction typed, printed, handwritten 20, 19 de, fr, en, la, el, fi, sv, pl index bibliographic

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

Response vs ground truth

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

Precision33.3%

Recall33.3%

True positives1

False positives2

False negatives2

F1 score33.0%

Total fields12

{"type":{"type":"Reference"},"author":{"last_name":"Montaghemi","first_name":"Nourhomadeh"},"publication":{"title":"","year":"","place":null,"pages":null,"publisher":null,"format":null,"editor":null},"library_reference":{"shelfmark":null,"subjects":null}}

Scoring

F1 micro91.6%

F1 macro90.8%

Micro precision90.5%

Micro recall92.7%

Instances263

True positives2,239

False positives234

False negatives176

Speed

Model time, all inputs10404.0 s

Mean per input39.56 s

Slowest input108.22 s

Inputs timed263

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 tokens636.2K

Output tokens32.7K

Total tokens668.9K

Input cost$1.27

Output cost$0.1962

Total cost$5.15

Reasoning cost usd$3.68

Total reasoning tokens614.1K

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

Result 53 of 187

Test T0657 at 2026-09-16

index-card information-extraction typed, printed, handwritten 20, 19 de, fr, en, la, el, fi, sv, pl index bibliographic

openai gpt-5.4-2026-03-05 · temp 0.0 · dataclass Document

Response vs ground truth

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

Precision25.0%

Recall33.3%

True positives1

False positives3

False negatives2

F1 score29.0%

Total fields12

{"type":{"type":"Reference"},"author":{"last_name":"Montaghemi","first_name":"Nourhomadeh"},"publication":{"title":"","year":"","place":"","pages":"","publisher":"","format":"","editor":null},"library_reference":{"shelfmark":"","subjects":"Sonnenbichler - Montaghemi, Nourhomadeh"}}

Scoring

F1 micro83.9%

F1 macro83.2%

Micro precision81.4%

Micro recall86.5%

Instances263

True positives2,090

False positives476

False negatives325

Speed

Model time, all inputs948.1 s

Mean per input3.60 s

Slowest input67.23 s

Inputs timed263

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 tokens444.1K

Output tokens40.2K

Total tokens484.3K

Input cost$1.11

Output cost$0.6027

Total cost$1.71

Priced from 2026-09-16 · Input $/M $2.50 · Output $/M $15.00

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

Result 54 of 187

Test T1365 at 2026-09-16

index-card information-extraction typed, printed, handwritten 20, 19 de, fr, en, la, el, fi, sv, pl index bibliographic

openai gpt-5.6-terra · temp 0.0 · dataclass Document

Response vs ground truth

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

Precision25.0%

Recall33.3%

True positives1

False positives3

False negatives2

F1 score29.0%

Total fields12

{"type":{"type":"Reference"},"author":{"last_name":"Montaghemi","first_name":"Nourhomadeh"},"publication":{"title":"Sonnenbichler-Montaghemi, Nourhomadeh","year":"","place":"","pages":"","publisher":"","format":"","editor":null},"library_reference":{"shelfmark":"","subjects":""}}

Scoring

F1 micro76.8%

F1 macro76.2%

Micro precision75.9%

Micro recall77.8%

Instances263

True positives1,878

False positives597

False negatives537

Speed

Model time, all inputs7343.0 s

Mean per input27.92 s

Slowest input802.34 s

Inputs timed263

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 tokens444.1K

Output tokens172.7K

Total tokens616.8K

Input cost$0.8883

Output cost$2.07

Total cost$2.96

Priced from 2026-09-16 · Input $/M $2.00 · Output $/M $12.00

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

Result 55 of 187

Test T1770 at 2026-09-16

index-card information-extraction typed, printed, handwritten 20, 19 de, fr, en, la, el, fi, sv, pl index bibliographic

deepseek deepseek-flash · temp 0.0 · dataclass Document

Response vs ground truth

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

Precision25.0%

Recall33.3%

True positives1

False positives3

False negatives2

F1 score29.0%

Total fields12

{"type":{"type":"Reference"},"author":{"last_name":"Montaghemi","first_name":"Nourhomadeh"},"publication":{"title":"Sonnenbichler - Montaghemi, Nourhomadeh","year":"","place":"","pages":"","publisher":"","format":"","editor":null},"library_reference":{"shelfmark":"","subjects":""}}

Scoring

F1 micro86.7%

F1 macro85.9%

Micro precision84.7%

Micro recall88.9%

Instances263

True positives2,146

False positives388

False negatives269

Speed

Model time, all inputs2144.0 s

Mean per input8.15 s

Slowest input41.99 s

Inputs timed263

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 tokens425.6K

Output tokens391.4K

Total tokens817K

Input cost$0.1277

Output cost$0.4697

Total cost$0.5974

Priced from 2026-09-16 · Input $/M $0.30 · Output $/M $1.20

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

Result 56 of 187

Test T1455 at 2026-09-16

index-card information-extraction typed, printed, handwritten 20, 19 de, fr, en, la, el, fi, sv, pl index bibliographic

x-ai grok-4.5 · temp 0.0 · dataclass Document

Response vs ground truth

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

Precision33.3%

Recall33.3%

True positives1

False positives2

False negatives2

F1 score33.0%

Total fields12

{"type":{"type":"Reference"},"author":{"last_name":"Montaghemi","first_name":"Nourhomadeh"},"publication":{"title":"","year":"","place":"","pages":"","publisher":"","format":"","editor":""},"library_reference":{"shelfmark":"","subjects":""}}

Scoring

F1 micro91.1%

F1 macro90.3%

Micro precision90.1%

Micro recall92.1%

Instances263

True positives2,224

False positives244

False negatives191

Speed

Model time, all inputs5475.3 s

Mean per input20.82 s

Slowest input70.78 s

Inputs timed263

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 tokens598.9K

Output tokens37.2K

Total tokens636.1K

Input cost$1.20

Output cost$0.2232

Total cost$3.22

Reasoning cost usd$1.80

Total reasoning tokens300.2K

Priced from 2026-09-16 · Input $/M $2.00 · Output $/M $6.00

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

Result 57 of 187

Test T1169 at 2026-09-16

index-card information-extraction typed, printed, handwritten 20, 19 de, fr, en, la, el, fi, sv, pl index bibliographic

genai gemini-3.1-flash-lite · temp 0.0 · dataclass Document

Response vs ground truth

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

Precision25.0%

Recall33.3%

True positives1

False positives3

False negatives2

F1 score29.0%

Total fields12

{"type":{"type":"Reference"},"author":{"last_name":"Montaghemi","first_name":"Nourhomadeh"},"publication":{"title":"Sonnenbichler - Montaghemi, Nourhomadeh","year":"","place":"","pages":"","publisher":"","format":"","editor":null},"library_reference":{"shelfmark":"","subjects":""}}

Scoring

F1 micro88.7%

F1 macro87.9%

Micro precision85.5%

Micro recall92.0%

Instances263

True positives2,223

False positives377

False negatives192

Speed

Model time, all inputs357.9 s

Mean per input1.36 s

Slowest input2.83 s

Inputs timed263

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 tokens406.2K

Output tokens47.9K

Total tokens454.2K

Input cost$0.1016

Output cost$0.0719

Total cost$0.1734

Priced from 2026-09-16 · Input $/M $0.25 · Output $/M $1.50

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

Result 58 of 187

Test T1440 at 2026-09-16

index-card information-extraction typed, printed, handwritten 20, 19 de, fr, en, la, el, fi, sv, pl index bibliographic

genai gemini-3.5-flash-lite · temp 0.0 · dataclass Document

Response vs ground truth

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

Precision25.0%

Recall33.3%

True positives1

False positives3

False negatives2

F1 score29.0%

Total fields12

{"type":{"type":"Reference"},"author":{"last_name":"Montaghemi","first_name":"Nourhomadeh"},"publication":{"title":"s. Sonnenbichler - Montaghemi, Nourhomadeh","year":"","place":null,"pages":null,"publisher":null,"format":null,"editor":null},"library_reference":{"shelfmark":null,"subjects":null}}

Scoring

F1 micro87.4%

F1 macro86.7%

Micro precision84.5%

Micro recall90.6%

Instances263

True positives2,187

False positives402

False negatives228

Speed

Model time, all inputs339.9 s

Mean per input1.29 s

Slowest input2.80 s

Inputs timed263

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 tokens406.2K

Output tokens49.3K

Total tokens455.5K

Input cost$0.1219

Output cost$0.1232

Total cost$0.2451

Priced from 2026-09-16 · 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 59 of 187

Test T1650 at 2026-09-16

index-card information-extraction typed, printed, handwritten 20, 19 de, fr, en, la, el, fi, sv, pl index bibliographic

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

Response vs ground truth

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

Precision33.3%

Recall33.3%

True positives1

False positives2

False negatives2

F1 score33.0%

Total fields12

{"type":{"type":"Reference"},"author":{"last_name":"Montaghemi","first_name":"Nourhomadeh"},"publication":{"title":"","year":"","place":"","pages":"","publisher":"","format":"","editor":null},"library_reference":{"shelfmark":"","subjects":""}}

Scoring

F1 micro90.6%

F1 macro89.8%

Micro precision89.1%

Micro recall92.1%

Instances263

True positives2,225

False positives271

False negatives190

Speed

Model time, all inputs1470.8 s

Mean per input5.59 s

Slowest input54.37 s

Inputs timed263

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 tokens406.2K

Output tokens48.4K

Total tokens454.7K

Input cost$0.3047

Output cost$0.1816

Total cost$1.59

Reasoning cost usd$1.10

Total reasoning tokens293.7K

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 60 of 187

Test T1055 at 2026-09-16

index-card information-extraction typed, printed, handwritten 20, 19 de, fr, en, la, el, fi, sv, pl index bibliographic

genai gemini-3.5-flash · temp 0.0 · dataclass Document

Response vs ground truth

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

Precision25.0%

Recall33.3%

True positives1

False positives3

False negatives2

F1 score29.0%

Total fields12

{"type":{"type":"Reference"},"author":{"last_name":"Montaghemi","first_name":"Nourhomadeh"},"publication":{"title":"Sonnenbichler - Montaghemi, Nourhomadeh","year":"","place":null,"pages":null,"publisher":null,"format":null,"editor":null},"library_reference":{"shelfmark":null,"subjects":null}}

Scoring

F1 micro86.9%

F1 macro85.9%

Micro precision84.0%

Micro recall90.1%

Instances263

True positives2,175

False positives413

False negatives240

Speed

Model time, all inputs1713.1 s

Mean per input6.51 s

Slowest input10.45 s

Inputs timed263

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 tokens406.2K

Output tokens49.9K

Total tokens456.1K

Input cost$0.6094

Output cost$0.4489

Total cost$4.04

Reasoning cost usd$2.98

Total reasoning tokens331.3K

Priced from 2026-09-16 · Input $/M $1.50 · Output $/M $9.00

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 T1425 at 2026-09-16

Test T1605 at 2026-09-16

Test T0657 at 2026-09-16

Test T1365 at 2026-09-16

Test T1770 at 2026-09-16

Test T1455 at 2026-09-16

Test T1169 at 2026-09-16

Test T1440 at 2026-09-16

Test T1650 at 2026-09-16

Test T1055 at 2026-09-16

Search Test Runs

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

Test T1425 at 2026-09-16

Test T1605 at 2026-09-16

Test T0657 at 2026-09-16

Test T1365 at 2026-09-16

Test T1770 at 2026-09-16

Test T1455 at 2026-09-16

Test T1169 at 2026-09-16

Test T1440 at 2026-09-16

Test T1650 at 2026-09-16

Test T1055 at 2026-09-16

Search Results
Show compact results Refine Search New Search

Download JSON Download CSV