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 13 of 18.
Result 121 of 178

Test T0898 at 2026-04-21

manuscript transcription handwritten 15 de prose

openrouter qwen/qwen3.6-plus-04-02 · temp 0.0 · dataclass Document

Response vs ground truth

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

Fuzzy score61.8%
CER ↓38.8%

{"folios":[{"folio":"73","text":"It zu dem ersten min her graff albrecht vo
nberg
It her ludwig lantgraf von liechtenberg
It graff ott von hemmenberg
It graff Bernhart von Regenstein
It graff gottfrid von hohenloch
It graff gebhart von Mansfeld
It graff ludwig von Arenburg
It her Gottfrid von Stoff
It her hans von tungern
It Jerg Bappanhein
It her Ruprecht vom stein wz vorhin Ritter
It hug vom Rotenhan
It Jerg von waldenfels
It hilprand von thungen
It Jerg von Elicben
It henyn quast","addition1":"bedpanckin","addition2":"","addition3":""}]}

Scoring

Fuzzy score65.3%
CER ↓35.5%

Speed

Model time, all inputs655.6 s
Mean per input72.84 s
Slowest input122.63 s
Inputs timed9

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 tokens29.7K
Output tokens49.8K
Total tokens79.6K
Input cost$0.0097
Output cost$0.0972
Total cost$0.1069

Priced from 2026-04-21 · Input $/M $0.325 · Output $/M $1.95

Result 122 of 178

Test T0549 at 2026-03-31

manuscript transcription handwritten 15 de prose

mistral ministral-14b-2512 · temp 0.0 · dataclass Document

Response vs ground truth

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

Fuzzy score0.0%
CER ↓100.0%

{"folios":[]}

Scoring

Fuzzy score2.4%
CER ↓100.0%

Speed

Model time, all inputs1353.5 s
Mean per input112.79 s
Slowest input271.66 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 tokens9K
Output tokens1.2K
Total tokens10.2K
Input cost$0.0018
Output cost$0.0002
Total cost$0.002

Priced from 2026-03-02 · Input $/M $0.20 · Output $/M $0.20

Result 123 of 178

Test T0285 at 2026-03-31

manuscript transcription handwritten 15 de prose

genai gemini-2.5-flash-lite · temp 0.0 · dataclass Document

Response vs ground truth

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

Fuzzy score89.6%
CER ↓9.8%

{"folios":[{"folio":"3","text":"vnd ein pferit Die mir vnd
minen energen vber Gulsend
Sen So was manen Ein weg
Semme Den wir machtend
 vnd vietend Die Energt Siet
vnd vil in vntz an Sen vnd
vnd Sie pferit vntz an Die
petel vnd was ze mol ein groffe
nebel So wir kum gepaüend
vnd als mit groffer arbeit kome
wir ze mittem tag zu Sant
Ein roffel vff Say bexy So
So sach ich Die bücher So jar
vil Gerrey wopay ju Stone
Die in für Edlyn geben Hand
So pünd mineb vatterb Rügen
wopay act in Sem emenj","addition1":"","addition2":"","addition3":""}]}

Scoring

Fuzzy score60.1%
CER ↓41.3%

Speed

Model time, all inputs45.7 s
Mean per input4.16 s
Slowest input5.66 s
Inputs timed11

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 tokens8.5K
Output tokens2.8K
Total tokens11.2K
Input cost$0.0008
Output cost$0.0011
Total cost$0.002

Priced from 2026-03-02 · Input $/M $0.10 · Output $/M $0.40

Result 124 of 178

Test T0885 at 2026-03-25

manuscript transcription handwritten 15 de prose

alibaba qwen3.5-flash-2026-02-23 · temp 0.0 · dataclass Document

Response vs ground truth

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

Fuzzy score93.5%
CER ↓6.2%

{"folios":[{"folio":"3","text":"vnd ein pferit die wir vnd
minen knechten oder Hulffend
sen do was meinen kün weg
deme den wir machten vnd
vielend die knecht tot
vnd vil in vnz an den and
vnd die pferit vnz an die
pettel vnd was ze mol ein grofse
nebel dz wir kum erpaffend
vnd als mit groffer arbeit kome
wir ze mittem tag zu Pant
krapffel vff den berg do
so sach ich die bücher so gar
vil herren wopen zu stone
die ir für den gun geben hand
do stund mines vatters pflegen
wopen och in dem zineg","addition1":null,"addition2":null,"addition3":null}]}

Scoring

Fuzzy score70.5%
CER ↓32.0%

Speed

Model time, all inputs102.8 s
Mean per input8.57 s
Slowest input12.50 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 tokens39.4K
Output tokens2.8K
Total tokens42.2K
Input cost$0.0039
Output cost$0.0011
Total cost$0.0051

Priced from 2026-03-24 · Input $/M $0.10 · Output $/M $0.40

Result 125 of 178

Test T0872 at 2026-03-25

manuscript transcription handwritten 15 de prose

alibaba qwen3.5-397b-a17b · temp 0.0 · dataclass Document

Response vs ground truth

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

Fuzzy score93.5%
CER ↓6.0%

{"folios":[{"folio":"3","text":"Vnd ein pferit die mir vnd
minen knechten vber ſtulfend
ſey do was menſen lang weg
deme das wir machtend
vnd vielend die knechte dick
vnd vil in vntz an den arb
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 mittent tag zu Sant
kriſtoffel vff den berg do
do ſach ich die buͤcher do gar
vil herren wapey in ſtone
die ir ſtůr ſelben geſchey hand
do ſtůnd mines vatters pflugey
wapey och in dem einen","addition1":"","addition2":"","addition3":""}]}

Scoring

Fuzzy score70.7%
CER ↓32.6%

Speed

Model time, all inputs148.8 s
Mean per input12.40 s
Slowest input14.89 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 tokens39.4K
Output tokens3.1K
Total tokens42.5K
Input cost$0.0236
Output cost$0.0113
Total cost$0.0349

Priced from 2026-03-24 · Input $/M $0.60 · Output $/M $3.60

Result 126 of 178

Test T0859 at 2026-03-25

manuscript transcription handwritten 15 de prose

alibaba qwen3.5-122b-a10b · temp 0.0 · dataclass Document

Response vs ground truth

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

Fuzzy score94.1%
CER ↓5.7%

{"folios":[{"folio":"3","text":"Und ein pferit die mir vnd
minen knechten wider gulfend
sey So was menen kain weg
deme den wir machtend
und vieliend die knetgt sich
vnd vil in vntz an den arb
vnd die pferit vntz an die
pettel vnd was ze mol ein grosse
nebel dz wir kum gepatend
vnd als mit grosser arbait kome
wir ze mittern tag zu Sant
kristoffel vff den berg do
Do sach ich die bücher do gar
vil herrey wopen zu ston
die ir fürer selbim gebey hand
do sind mines vatters pflegen
wopen och in dem einen","addition1":"","addition2":"","addition3":""}]}

Scoring

Fuzzy score71.9%
CER ↓29.4%

Speed

Model time, all inputs118.9 s
Mean per input9.91 s
Slowest input12.05 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 tokens39.4K
Output tokens2.7K
Total tokens42.1K
Input cost$0.0158
Output cost$0.0088
Total cost$0.0245

Priced from 2026-03-24 · Input $/M $0.40 · Output $/M $3.20

Result 127 of 178

Test T0846 at 2026-03-25

manuscript transcription handwritten 15 de prose

alibaba qwen3.5-27b · temp 0.0 · dataclass Document

Response vs ground truth

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

Fuzzy score93.8%
CER ↓5.8%

{"folios":[{"folio":"3","text":"vnd ein pferit die mir vnd
minen knechten wider gultend
san so was menan lang weg
deme dan wir machgend
vnd vieliend die knchte durb
vnd vil im vntz an den arb
vnd die pferit vntz an die
fettel vnd was ze mol ein grosser
nebel dz wir kum gepatsend
vnd als mit grosser arbeit kame
wir ze mittrem tag zu Sant
bristoffel uff den berg do
do sach ich die burger do gar
vil herren wopen im ston
die ir stirr ez hnn geben hand
do stand minneb vatterb klugen
wopen och in dem einen","addition1":"","addition2":"","addition3":""}]}

Scoring

Fuzzy score72.7%
CER ↓31.4%

Speed

Model time, all inputs244.5 s
Mean per input20.38 s
Slowest input26.50 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 tokens39.4K
Output tokens3K
Total tokens42.4K
Input cost$0.0118
Output cost$0.0072
Total cost$0.0191

Priced from 2026-03-24 · Input $/M $0.30 · Output $/M $2.40

Result 128 of 178

Test T0833 at 2026-03-25

manuscript transcription handwritten 15 de prose

alibaba qwen3.5-35b-a3b · temp 0.0 · dataclass Document

Response vs ground truth

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

Fuzzy score93.5%
CER ↓6.6%

{"folios":[{"folio":"3","text":"Vnd ein pferit die wir vnd
minen knechten oder Hulffend
sen do was meinen kün weg
deme den wir machten vnd
vnd vieliend die knecht sich
vnd vil in vnz an den and
vnd die pferit vnz an die
pettel vnd was ze mol ein grofse
nebel dz wir kum gepaffend
vnd als mit groffer arbeit kamc
wir ze mitttem tag zu Pant
krapffel vff den berg do
do sach ich die bücher so gar
vil herren wappen zu stone
die ir stirz daz hin geben hand
do stund meines vatters pflegen
wappen och in dem zineg","addition1":null,"addition2":null,"addition3":null}]}

Scoring

Fuzzy score66.3%
CER ↓35.9%

Speed

Model time, all inputs112.6 s
Mean per input9.38 s
Slowest input11.52 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 tokens39.4K
Output tokens2.8K
Total tokens42.2K
Input cost$0.0099
Output cost$0.0055
Total cost$0.0154

Priced from 2026-03-24 · Input $/M $0.25 · Output $/M $2.00

Result 129 of 178

Test T0820 at 2026-03-24

manuscript transcription handwritten 15 de prose

alibaba qwen3.5-plus · temp 0.0 · dataclass Document

Response vs ground truth

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

Fuzzy score95.4%
CER ↓4.2%

{"folios":[{"folio":"3","text":"Vnd ein pferit die mir vnd
minen knehten vber Hulfend
sey do was menen lang weg
deme das wir machtend
vnd vielend die knehte dick
vnd vil in vntz an den arb
vnd die pferit vntz an die
pettel vnd was ze mol ein grosser
nebel dz wir kum gepathend
vnd als mit grosser arbeit kame
wir ze mittem tag zu sant
kristoffel vff den berg do
do sach ich die bucher do gar
vil herren wopen zu stone
die ir stur helm gebey hand
do stund mines vatters plugen
wopen och in dem einen","addition1":"","addition2":"","addition3":""}]}

Scoring

Fuzzy score72.0%
CER ↓30.4%

Speed

Model time, all inputs165.1 s
Mean per input13.76 s
Slowest input19.83 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 tokens39.4K
Output tokens3K
Total tokens42.4K
Input cost$0.0158
Output cost$0.0073
Total cost$0.023

Priced from 2026-03-24 · Input $/M $0.40 · Output $/M $2.40

Result 130 of 178

Test T0724 at 2026-03-23

manuscript transcription handwritten 15 de prose

x-ai grok-4.20-0309-reasoning · temp 0.0 · dataclass Document

Response vs ground truth

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

Fuzzy score88.9%
CER ↓11.8%

{"folios":[{"folio":"3","text":"vnd ein pfaff die mir vnd
minen frowen vber Rinfand
So was minen dem weg
Sume den wir machten
vnd stekent die knecht gut
vnd vil in vngeligen arb
vnd sie pfaff vng my die
pfaff vnd was ze mal ein grosser
nebel by vns kum geuallen
vnd als mir grosser arbeit kam
wir ze mittem tag ze sant
barthol vff dem berg So
So sach ich die burger So gar
vil herin wapen in front
die in mir dohin geleit hand
So sind mines vatters seligen
wapen och in dem sinen","addition1":"","addition2":"","addition3":""}]}

Scoring

Fuzzy score53.3%
CER ↓51.2%

Speed

Model time, all inputs2882.3 s
Mean per input240.19 s
Slowest input1264.57 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 tokens11.6K
Output tokens2.2K
Total tokens13.8K
Input cost$0.0233
Output cost$0.013
Total cost$0.3122
Reasoning cost usd$0.2759
Total reasoning tokens46K

Priced from 2026-03-22 · Input $/M $2.00 · Output $/M $6.00