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

Your search for Benchmark 'bibliographic_data__true' with Search Hidden 'False' returned 208 results, showing page 20 of 21.
Result 191 of 208

Test T0130 at 2025-09-30

book-page information-extraction printed 20 en list bibliographic

openai gpt-5-mini · temp 0.0 · dataclass Document

Response vs ground truth

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

Scoring

Fuzzy score67.8%

Speed

Model time, all inputs395.9 s
Mean per input79.17 s
Slowest input105.67 s
Inputs timed5

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 tokens7.4K
Output tokens28.2K
Total tokens35.7K
Input cost$0.0019
Output cost$0.0565
Total cost$0.0583

Priced from 2025-09-30 · Input $/M $0.25 · Output $/M $2.00

Cite: Hindermann, Marti, Alberto, et al., (2026). RISE-UNIBAS/humanities_data_benchmark, 10.5281/zenodo.21975827
Result 192 of 208

Test T0129 at 2025-09-30

book-page information-extraction printed 20 en list bibliographic

openai gpt-5 · temp 0.0 · dataclass Document

Response vs ground truth

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

Scoring

Fuzzy score67.3%

Speed

Model time, all inputs574.1 s
Mean per input114.82 s
Slowest input156.80 s
Inputs timed5

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 tokens6.5K
Output tokens33.2K
Total tokens39.7K
Input cost$0.0081
Output cost$0.3322
Total cost$0.3403

Priced from 2025-09-30 · 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 193 of 208

Test T0133 at 2025-09-30

book-page information-extraction printed 20 en list bibliographic

openai o3 · temp 0.0 · dataclass Document

Response vs ground truth

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

Scoring

Fuzzy score67.4%

Speed

Model time, all inputs542.3 s
Mean per input108.46 s
Slowest input135.22 s
Inputs timed5

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 tokens6.7K
Output tokens22.8K
Total tokens29.5K
Input cost$0.0135
Output cost$0.1823
Total cost$0.1958

Priced from 2025-09-30 · Input $/M $2.00 · Output $/M $8.00

Cite: Hindermann, Marti, Alberto, et al., (2026). RISE-UNIBAS/humanities_data_benchmark, 10.5281/zenodo.21975827
Result 194 of 208

Test T0130 at 2025-09-24

book-page information-extraction printed 20 en list bibliographic

openai gpt-5-mini · temp 0.0 · dataclass Document

Response vs ground truth

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

Scoring

Fuzzy score64.9%

Speed

Model time, all inputs445.1 s
Mean per input89.03 s
Slowest input103.89 s
Inputs timed5

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

No cost recorded for this run

Cite: Hindermann, Marti, Alberto, et al., (2026). RISE-UNIBAS/humanities_data_benchmark, 10.5281/zenodo.21975827
Result 195 of 208

Test T0141 at 2025-08-27

book-page information-extraction printed 20 en list bibliographic

openai gpt-4.1-nano · temp 0.0 · dataclass Document

Response vs ground truth

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

Scoring

Fuzzy score33.0%

Speed

Model time, all inputs67.0 s
Mean per input13.41 s
Slowest input18.81 s
Inputs timed5

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

No cost recorded for this run

Cite: Hindermann, Marti, Alberto, et al., (2026). RISE-UNIBAS/humanities_data_benchmark, 10.5281/zenodo.21975827
Result 196 of 208

Test T0140 at 2025-08-27

book-page information-extraction printed 20 en list bibliographic

openai gpt-4.1-mini · temp 0.0 · dataclass Document

Response vs ground truth

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

Scoring

Fuzzy score61.5%

Speed

Model time, all inputs179.2 s
Mean per input35.84 s
Slowest input50.02 s
Inputs timed5

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

No cost recorded for this run

Cite: Hindermann, Marti, Alberto, et al., (2026). RISE-UNIBAS/humanities_data_benchmark, 10.5281/zenodo.21975827
Result 197 of 208

Test T0139 at 2025-08-27

book-page information-extraction printed 20 en list bibliographic

openai gpt-4.1 · temp 0.0 · dataclass Document

Response vs ground truth

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

Scoring

Fuzzy score54.4%

Speed

Model time, all inputs304.5 s
Mean per input60.90 s
Slowest input80.18 s
Inputs timed5

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

No cost recorded for this run

Cite: Hindermann, Marti, Alberto, et al., (2026). RISE-UNIBAS/humanities_data_benchmark, 10.5281/zenodo.21975827
Result 198 of 208

Test T0133 at 2025-08-20

book-page information-extraction printed 20 en list bibliographic

openai o3 · temp 0.0 · dataclass Document

Response vs ground truth

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

Scoring

Fuzzy score64.6%

Speed

Model time, all inputs369.6 s
Mean per input73.92 s
Slowest input84.78 s
Inputs timed5

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

No cost recorded for this run

Cite: Hindermann, Marti, Alberto, et al., (2026). RISE-UNIBAS/humanities_data_benchmark, 10.5281/zenodo.21975827
Result 199 of 208

Test T0131 at 2025-08-14

book-page information-extraction printed 20 en list bibliographic

openai gpt-5-nano · temp 0.0 · dataclass Document

Response vs ground truth

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

Scoring

Fuzzy score33.0%

Speed

Model time, all inputs359.1 s
Mean per input71.82 s
Slowest input95.42 s
Inputs timed5

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

No cost recorded for this run

Cite: Hindermann, Marti, Alberto, et al., (2026). RISE-UNIBAS/humanities_data_benchmark, 10.5281/zenodo.21975827
Result 200 of 208

Test T0130 at 2025-08-14

book-page information-extraction printed 20 en list bibliographic

openai gpt-5-mini · temp 0.0 · dataclass Document

Response vs ground truth

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

Scoring

Fuzzy score63.8%

Speed

Model time, all inputs394.9 s
Mean per input78.98 s
Slowest input101.62 s
Inputs timed5

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

No cost recorded for this run

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