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.

Loading module...

Search Results

Your search for Benchmark 'medieval_manuscripts__true' with Search Hidden 'False' returned 178 results, showing page 1 of 18.
Result 1 of 178

Test T1891 at 2026-10-14

manuscript transcription handwritten 15 de prose

genai gemini-4-argon · temp 0.0 · dataclass Document

Response vs ground truth

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

Fuzzy score98.2%
CER ↓0.6%

{"folios":[{"folio":"3","text":"Vnd ein pferit die mir vnd
minen knechten über hulfend
den do was nienan kein weg
denne den wir machtend
vnd vielend die knecht dik
vnd vil in vntz an den ars
vnd die pferit vntz an die
settel vnd was ze mol ein grosser
nebel dz wir kum gesachend
vnd also mit grosser arbeit komē
wir ze mittem tag zuo sant
kristoffel vff den berg do
do sach ich die buocher do gar
vil herren wopen jn stond
die ir stür do hin geben hand
do stuond mines vatters seligen
wopen och in dem einen","addition1":"","addition2":"","addition3":""}]}

Scoring

Fuzzy score88.3%
CER ↓11.6%

Speed

Model time, all inputs117.8 s
Mean per input9.82 s
Slowest input26.14 s
Inputs timed12

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 tokens22.9K
Output tokens2.9K
Total tokens25.8K
Input cost$0.0458
Output cost$0.0288
Total cost$0.0819
Reasoning cost usd$0.0073
Total reasoning tokens731

Priced from 2026-10-14 · Input $/M $2.00 · Output $/M $10.00

Result 2 of 178

Test T1801 at 2026-09-29

manuscript transcription handwritten 15 de prose

scicore Qwen3.8-Flash-Next-FP8 · temp 0.0 · dataclass Document

Response vs ground truth

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

Fuzzy score93.6%
CER ↓6.0%

{"folios":[{"folio":"3","text":"Vnd ein pferit die wir vnd
minen knechten vber hulfend
sen do waß minen vater weg
demme den wir machtend
vnd richend die knecht vß
vnd vil in vntz an den arb
vnd die pferit vnz an die
pettel vnd waß ze mol ein grosser
nebel dz wir kaum gepaffend
vnd als mit grosser arbeit kame
wir ze mitten tag zu sant
ein pffel vff den berg do
do sach ich die burcher do gar
vil herren wapen zu stone
die ir für vß im gebey gant
do stund mines vatters flugen
wapen och in dem einen","addition1":"","addition2":"","addition3":""}]}

Scoring

Fuzzy score77.8%
CER ↓23.1%

Speed

Model time, all inputs1094.8 s
Mean per input91.24 s
Slowest input231.16 s
Inputs timed12

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 tokens40.8K
Output tokens93K
Total tokens133.8K
Input cost$0.00
Output cost$0.00
Total cost$0.00

Priced from 2026-09-27 · Input $/M $0.00 · Output $/M $0.00

Result 3 of 178

Test T1876 at 2026-09-29

manuscript transcription handwritten 15 de prose

anthropic claude-sonnet-5-5 · temp 0.0 · dataclass Document

Response vs ground truth

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

Fuzzy score96.6%
CER ↓2.2%

{"folios":[{"folio":"3","text":"Vnd ein pferit Die mir vnd
minen knechten ober hulfend
den Do was menan kein weg
senne den wir machtend
vnd viehend Die knecht dick
vnd vil in vntz an den ars
vnd die pferit vntz an die
settel vnd was ze mol ein grosser
nebel dz wir kum gefarend
vnd als mit grosser arbeit kome
wir ze mittem tag zuͦ sant
kristoffel vff den berg do
Do sach ich die bucher do gar
vil herren wopen ju stone
Die iv stiur de hin geben hand
Do stund mines vatters seligen
wopen ach in dem einen","addition1":"","addition2":"","addition3":""}]}

Scoring

Fuzzy score84.4%
CER ↓14.8%

Speed

Model time, all inputs61.6 s
Mean per input5.14 s
Slowest input7.15 s
Inputs timed12

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 tokens60.7K
Output tokens4.3K
Total tokens65K
Input cost$0.1213
Output cost$0.0433
Total cost$0.1646

Priced from 2026-09-28 · Input $/M $2.00 · Output $/M $10.00

Result 4 of 178

Test T1816 at 2026-09-29

manuscript transcription handwritten 15 de prose

anthropic claude-opus-5-5 · temp 0.0 · dataclass Document

Response vs ground truth

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

Fuzzy score98.0%
CER ↓1.1%

{"folios":[{"folio":"3","text":"Vnd ein pferit die mir vnd
minen knechten vber hulfend
den do was menan kein weg
denne den wir machtend
vnd viellend die knecht dick
vnd vil in vntz an den ars
vnd die pferit vntz an die
settel vnd was ze mol ein grosser
nebel dz wir kum gesachend
vnd als mit grosser arbeit kame
wir ze mittem tag zuo sant
kristoffel vff den berg do
do sach ich die buecher do gar
vil herren wopen jn stone
die ir stur dohin geben hand
do stuond mines vatters seligen
wopen och in dem einen","addition1":"","addition2":"","addition3":""}]}

Scoring

Fuzzy score83.3%
CER ↓15.8%

Speed

Model time, all inputs88.9 s
Mean per input7.41 s
Slowest input10.84 s
Inputs timed12

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 tokens60.7K
Output tokens5.2K
Total tokens65.9K
Input cost$0.2426
Output cost$0.1049
Total cost$0.3475

Priced from 2026-09-27 · Input $/M $4.00 · Output $/M $20.00

Result 5 of 178

Test T1681 at 2026-09-29

manuscript transcription handwritten 15 de prose

anthropic claude-fable-5-1 · temp 0.0 · dataclass Document

Response vs ground truth

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

Fuzzy score98.0%
CER ↓0.9%

{"folios":[{"folio":"3","text":"vnd ein pferit die mir vnd
minen knechten vber hulfend
den do was menan kein weg
denne den wir machtend
vnd vielend die knecht dick
vnd vil in vntz an den ars
vnd die pferit vntz an die
settel vnd was ze mol ein grosser
nebel dz wir kum gesachend
vnd als mit grosser arbeit kame
wir ze mittem tag zuo sant
kristoffel vff den berg do
do sach ich die buecher do gar
vil herren wopen in stene
die ir stur do hin geben hand
do stuond mines vatters seligen
wopen och in dem einen","addition1":"","addition2":"","addition3":""}]}

Scoring

Fuzzy score83.5%
CER ↓15.9%

Speed

Model time, all inputs273.6 s
Mean per input22.80 s
Slowest input41.59 s
Inputs timed12

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 tokens60.7K
Output tokens16.1K
Total tokens76.8K
Input cost$0.6066
Output cost$0.8072
Total cost$1.41

Priced from 2026-09-08 · Input $/M $10.00 · Output $/M $50.00

Result 6 of 178

Test T1876 at 2026-09-28

manuscript transcription handwritten 15 de prose

anthropic claude-sonnet-5-5 · temp 0.0 · dataclass Document

Response vs ground truth

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

Fuzzy score96.4%
CER ↓2.9%

{
  "folios": [
    {
      "folio": "3",
      "text": "Vnd ein pferit die mir vnd
minen knechten vber hulffend
den do was menglich kein weg
denne den wir machtend
vnd viehend die knecht dick
vnd vil in vntz an den ars
vnd die pferit vntz an die
settel vnd was ze mol ein grosser
nebel dz wir kum gepatend
vnd alſo mit grosser arbeit kome
wir ze mittem tag zuͦ sant
kristoffel vff den berg do
do sach ich die bůcher do gar
vil herren wapen ju stone
die in stur delhin geben hand
do stund mines vatters seligen
wapen ach in dem einen",
      "addition1": "",
      "addition2": "",
      "addition3": ""
    }
  ]
}

Scoring

Fuzzy score85.3%
CER ↓14.1%

Speed

Model time, all inputs56.7 s
Mean per input4.73 s
Slowest input6.42 s
Inputs timed12

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 tokens52.6K
Output tokens4.1K
Total tokens56.7K
Input cost$0.1052
Output cost$0.0411
Total cost$0.1463

Priced from 2026-09-28 · Input $/M $2.00 · Output $/M $10.00

Result 7 of 178

Test T1846 at 2026-09-27

manuscript transcription handwritten 15 de prose

openai gpt-6-luna · temp 0.0 · dataclass Document

Response vs ground truth

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

Fuzzy score87.3%
CER ↓14.9%

{"folios":[{"folio":"3","text":"Und ein pferit die mir mit
meinen knechten vber helfend
Sey Do waß mennlich sin weg
dann den mir machend
und vil in vnsern an den ort
und die pferit vns an die
statt und wir ze not ein grosse
nebel das wir kum gesehen
und also mit grosser arbeit komen
wir ze mittem tag zu Sant
Basel uff ein berg do
do hettend die burger do gar
vil herren wappen in ...
die ... ... hand
So ... mines vatters pflegen
wappen uff in dem ...","addition1":"","addition2":"","addition3":""}]}

Scoring

Fuzzy score57.0%
CER ↓52.0%

Speed

Model time, all inputs248.0 s
Mean per input20.67 s
Slowest input26.90 s
Inputs timed12

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 tokens47.5K
Output tokens25K
Total tokens72.5K
Input cost$0.0048
Output cost$0.0125
Total cost$0.0172

Priced from 2026-09-27 · Input $/M $0.10 · Output $/M $0.50

Result 8 of 178

Test T1831 at 2026-09-27

manuscript transcription handwritten 15 de prose

openai gpt-6-sol · temp 0.0 · dataclass Document

Response vs ground truth

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

Fuzzy score95.5%
CER ↓4.0%

{"folios":[{"folio":"3","text":"vnd ein pfferit die wir vnd
minen knechten wider hulfend
Den Do was menen kein weg
Danne den wir muechtend
vnd vielend die knecht dik
vnd vil in vns an den ars
vnd die pfferit vns an die
setel vnd was ze mol ein grosser
nebel dz wir kum gesachend
vnd als mit grosser arbeit kame
wir ze mittem tag zu sant
kristoffel uff dem berg Do
Do het ich die buecher Do gar
vil herren woppen zu stond
Die ir sinr do hin getan hand
Do stünd mines vatters seligen
woppen och in dem einen","addition1":"","addition2":"","addition3":""}]}

Scoring

Fuzzy score76.1%
CER ↓25.5%

Speed

Model time, all inputs248.7 s
Mean per input20.72 s
Slowest input26.52 s
Inputs timed12

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 tokens47.5K
Output tokens16.5K
Total tokens64K
Input cost$0.0951
Output cost$0.1648
Total cost$0.2599

Priced from 2026-09-27 · Input $/M $2.00 · Output $/M $10.00

Result 9 of 178

Test T1816 at 2026-09-27

manuscript transcription handwritten 15 de prose

anthropic claude-opus-5-5 · temp 0.0 · dataclass Document

Response vs ground truth

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

Fuzzy score98.2%
CER ↓0.7%

```json
{
  "folios": [
    {
      "folio": "3",
      "text": "Vnd ein pferit die mir vnd
minen knechten vber hulfend
den do was nienan kein weg
denne den wir machtend
vnd vielend die knecht dick
vnd vil in vntz an den ars
vnd die pferit vntz an die
settel vnd was ze mol ein grosser
nebel dz wir kum gesachend
vnd als mit grosser arbeit kame
wir ze mittem tag zuo sant
kristoffel vff den berg do
do sach ich die buecher do gar
vil herren wopen jn stone
die ir stür dehin geben hand
do stuond mines vatters seligen
wopen och in dem einen",
      "addition1": "",
      "addition2": "",
      "addition3": ""
    }
  ]
}
```

Scoring

Fuzzy score83.5%
CER ↓16.0%

Speed

Model time, all inputs118.3 s
Mean per input9.86 s
Slowest input16.30 s
Inputs timed12

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 tokens52.6K
Output tokens7.5K
Total tokens60.1K
Input cost$0.2104
Output cost$0.1491
Total cost$0.3595

Priced from 2026-09-27 · Input $/M $4.00 · Output $/M $20.00

Result 10 of 178

Test T1861 at 2026-09-27

manuscript transcription handwritten 15 de prose

x-ai grok-4.7 · temp 0.0 · dataclass Document

Response vs ground truth

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

Fuzzy score97.0%
CER ↓2.1%

{"folios":[{"folio":"3","text":"Vnd ein pferit die wir vnd
minen knechten vber Rulsend
den do was nieman kein weg
denne den wir machtend
vnd vielend die knecht dick
vnd vil in vntz an den arm
vnd die pferit vntz an die
kettel vnd was ze mol ein grosser
nebel dz wir kum gesehen
vnd also mit grosser arbeit kame
wir ze mittem tag zuo sant
cristoffel vff den berg do
do sach ich die bucher do gar
vil herren wapen in stein
die ir stir do hin geben hand
do stund mines vatters seligen
wapen och in dem einen","addition1":"","addition2":"","addition3":""}]}

Scoring

Fuzzy score79.8%
CER ↓20.7%

Speed

Model time, all inputs5280.8 s
Mean per input440.07 s
Slowest input550.38 s
Inputs timed12

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 tokens52.9K
Output tokens2.6K
Total tokens55.6K
Input cost$0.1059
Output cost$0.0157
Total cost$2.79
Reasoning cost usd$2.67
Total reasoning tokens444.2K

Priced from 2026-09-27 · Input $/M $2.00 · Output $/M $6.00