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 21 of 21.
Result 201 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
Result 202 of 208

Test T0129 at 2025-08-14

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 score62.7%

Speed

Model time, all inputs764.6 s
Mean per input152.91 s
Slowest input230.22 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

No cost recorded for this run

Cite: Hindermann, Marti, Alberto, et al., (2026). RISE-UNIBAS/humanities_data_benchmark, 10.5281/zenodo.21975827
Result 203 of 208

Test T0027 at 2025-04-08

book-page information-extraction printed 20 en list bibliographic

openai gpt-4o-mini · temp 0.0 · dataclass Document

Response vs ground truth

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

Scoring

Fuzzy score53.9%

Speed

Model time, all inputs179.6 s
Mean per input35.92 s
Slowest input51.05 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 204 of 208

Test T0007 at 2025-04-08

book-page information-extraction printed 20 en list bibliographic

openai gpt-4o · temp 0.0 · dataclass Document

Response vs ground truth

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

Scoring

Fuzzy score52.0%

Speed

Model time, all inputs260.5 s
Mean per input52.11 s
Slowest input69.14 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 205 of 208

Test T0007 at 2025-04-01

book-page information-extraction printed 20 en list bibliographic

openai gpt-4o · temp 0.0 · dataclass Document

Response vs ground truth

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

Scoring

Fuzzy score61.3%

Speed

Model time, all inputs95.8 s
Mean per input47.89 s
Slowest input53.53 s
Inputs timed2

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 206 of 208

Test T0007 at 2025-03-05

book-page information-extraction printed 20 en list bibliographic

openai gpt-4o · temp 0.0 · dataclass Document

Response vs ground truth

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

Scoring

Fuzzy score71.4%

Speed

Model time, all inputs46.0 s
Mean per input23.00 s
Slowest input26.83 s
Inputs timed2

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 207 of 208

Test T0007 at 2025-03-04

book-page information-extraction printed 20 en list bibliographic

openai gpt-4o · temp 0.0 · dataclass Document

Response vs ground truth

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

Scoring

Fuzzy score60.7%

Speed

Model time, all inputs43.6 s
Mean per input21.79 s
Slowest input24.01 s
Inputs timed2

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 208 of 208

Test T0007 at 2025-03-02

book-page information-extraction printed 20 en list bibliographic

openai gpt-4o · temp 0.0 · dataclass Document

Response vs ground truth

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

Scoring

Fuzzy score61.0%

Speed

Model time, all inputs49.1 s
Mean per input24.55 s
Slowest input32.13 s
Inputs timed2

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