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 177 results, showing page 16 of 18.
Result 151 of 177

Test T0300 at 2026-01-25

manuscript transcription handwritten 15 de prose

openrouter qwen/qwen3-vl-8b-thinking · temp 0.0 · dataclass Document

Response vs ground truth

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

Fuzzy score86.6%
CER ↓16.1%

{"folios":[{"folio":"3","text":"In s ein pferit die mir vnd\
 minen knyhten uder hulfend\
 say so was mency kiny wcy\
 same day wir machten\
 and vickend die knyhtge oub\
 vnd vil in vntz an say anv\
 vnd die pferit vntz an die\
 pater vnd was ze mot ein groffe\
 nebel ez win kum vntz kryge\
 vnd also mit grosser arbait kome\
 wir ze mittem tag zu pant\
 hmpoffel vff say berg so\
 so fach ich die bucker so gav\
 vnd terry wopay in pom\
 die vur stur e dlu gecley band\
 so raine minceb vatterb plicuy\
 wopay sog in sem smey","addition1":"","addition2":"","addition3":""}]}

Scoring
Speed

Model time, all inputs9.4 s
Mean per input9.42 s
Slowest input9.42 s
Inputs timed1

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

Priced from 2026-01-23 · Input $/M $0.18 · Output $/M $2.10

Result 152 of 177

Test T0302 at 2026-01-25

manuscript transcription handwritten 15 de prose

openrouter qwen/qwen3-vl-30b-a3b-instruct · temp 0.0 · dataclass Document

Response vs ground truth

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

Fuzzy score91.0%
CER ↓9.3%

{"folios":[{"folio":"3","text":"Und ein pferit Die wir vnd
 minen Enchsten vber Gultend
 Sen So was menen den Weg
 Same Den wir machend
 vnd vichend Die Enchge Duk
 vnd vil in vnt an Den anb
 vnd Sie pferit vnt an Die
 petel vnd was ze mol ein groffe
 nebel & wir kum oepauffend
 vnd als mit groffer arbeit kome
 wir ze mittem tag zu Pont
 Ein toffel vff Den berg So
 So sach ich Die bucher So gar
 vil gerny Wopen in Pone
 Die in stur So gm gebey hand
 So find mincb vattero Plegen
 Wopen set in dem emen","addition1":"","addition2":"","addition3":""}]}

Scoring

Fuzzy score62.1%
CER ↓40.0%

Speed

Model time, all inputs49.4 s
Mean per input4.12 s
Slowest input5.68 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 tokens39.3K
Output tokens2.5K
Total tokens41.9K
Input cost$0.0051
Output cost$0.0013
Total cost$0.0064

Priced from 2026-01-23 · Input $/M $0.15 · Output $/M $0.60

Result 153 of 177

Test T0505 at 2026-01-25

manuscript transcription handwritten 15 de prose

genai gemini-3-flash-preview · temp 0.0 · dataclass Document

Response vs ground truth

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

Fuzzy score96.3%
CER ↓2.9%

{"folios":[{"folio":"3","text":"vnd ein pferit die mir vnd
minen knechten vber hulfend
den do was meinen kein weg
denne den wir machtend
vnd vichend 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 gepassend
vnd als mit grosser arbeit kōme
wir ze mittem tag zu sant
cristoffel vff den berg do
do sach ich die kilchen do gar
vil herren wopen in stene
die ir stür darzu geben hand
do stund mines vatters seligen
wopen ouch in dem einen","addition1":"","addition2":"","addition3":""}]}

Scoring

Fuzzy score75.2%
CER ↓25.0%

Speed

Model time, all inputs1495.0 s
Mean per input124.59 s
Slowest input325.71 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 tokens19.1K
Output tokens2.8K
Total tokens22K
Input cost$0.0096
Output cost$0.0085
Total cost$0.8804
Reasoning cost usd$0.8623
Total reasoning tokens287.4K

Priced from 2026-01-23 · Input $/M $0.50 · Output $/M $3.00

Result 154 of 177

Test T0516 at 2026-01-24

manuscript transcription handwritten 15 de prose

anthropic claude-opus-4-5-20251101 · temp 0.0 · dataclass Document

Response vs ground truth

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

Fuzzy score97.5%
CER ↓1.3%

{"folios":[{"folio":"3","text":"vnd ein pferit die mir vnd
minen knechten vber hulffend
den do was menen 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 gesachend
vnd als mit grosser arbeit kame
wir ze mittem tag zuͦ sant
kristoffel vff den berg do
do sach ich die buͦcher do gar
vil herren wopen jn stond
die ir stur do hin geben hand
do stuͦnd mines vatters seligen
wopen och in dem einen","addition1":"","addition2":"","addition3":""}]}

Scoring

Fuzzy score85.5%
CER ↓15.1%

Speed

Model time, all inputs137.5 s
Mean per input11.46 s
Slowest input23.84 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 tokens35.9K
Output tokens3.4K
Total tokens39.3K
Input cost$0.1795
Output cost$0.0849
Total cost$0.2644

Priced from 2026-01-23 · Input $/M $5.00 · Output $/M $25.00

Result 155 of 177

Test T0527 at 2026-01-24

manuscript transcription handwritten 15 de prose

anthropic claude-haiku-4-5-20251001 · temp 0.0 · dataclass Document

Response vs ground truth

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

Fuzzy score90.1%
CER ↓10.2%

{"folios":[{"folio":"3","text":"Vnd ein pferit die mir vnd
minen knechten vder gulland
den so was menig lang weg
Jmme der wir machten
vnd vielend die knecht dut
vnd vil in vmtz an der and
vnd die pferit vmz an die
stral vnd was ze mol ein groſſa
nebel dz wir kunig gefaſſend
vnd als mir groſſer arbeit bame
wir ze mittem tag ze fart
kinfaſſel vſ den berg do
do fach ich die brieder do gar
vil barney wagen zu ſtone
die in ſtir ed ſny gelieg hand
do fand mines vatters Rligen
wagen och in dem zineig","addition1":"","addition2":"","addition3":""}]}

Scoring

Fuzzy score63.2%
CER ↓39.7%

Speed

Model time, all inputs67.9 s
Mean per input5.66 s
Slowest input9.34 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 tokens35.9K
Output tokens3.6K
Total tokens39.5K
Input cost$0.0359
Output cost$0.0178
Total cost$0.0537

Priced from 2026-01-23 · Input $/M $1.00 · Output $/M $5.00

Result 156 of 177

Test T0271 at 2026-01-24

manuscript transcription handwritten 15 de prose

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

Response vs ground truth

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

Fuzzy score92.0%
CER ↓7.2%

{"folios":[{"folio":"3","text":"Vnd ein pferit Die mir vnd
minen knechten vber Rulfend
Sen So was menen kein weg
Sanne Das wir machtend
vnd ziehend Sie knecht Sind
vnd vil in vntz an Sen anb
vnd Sie pferit vntz an Die
pettel vnd was ze mol ein groſſe
nebel dz wir kum gepaſſend
vnd als mit groſſer arbeit kame
wir ze mittem tag zuo Sant
Einroſſel vff Sen berg So
So sach ich Die bucher Do gar
vil herren wopen zuo ſtont
Die in fuor edlen geben hand
So ſind mineb vattero Rligen
wopen ach in Sem emen","addition1":"","addition2":"","addition3":""}]}

Scoring

Fuzzy score62.4%
CER ↓40.4%

Speed

Model time, all inputs111.3 s
Mean per input9.27 s
Slowest input19.93 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 tokens9.3K
Output tokens2.9K
Total tokens12.2K
Input cost$0.0028
Output cost$0.0074
Total cost$0.0571
Reasoning cost usd$0.0469
Total reasoning tokens18.8K

Priced from 2026-01-23 · Input $/M $0.30 · Output $/M $2.50

Result 157 of 177

Test T0272 at 2026-01-24

manuscript transcription handwritten 15 de prose

genai gemini-2.5-pro · temp 0.0 · dataclass Document

Response vs ground truth

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

Fuzzy score95.8%
CER ↓3.5%

{"folios":[{"folio":"3","text":"vnd ein pferit die mir vnd
minen knechten vber hulffend
den So was menen kein weg
Sonne den wir machtend
vnd viehend die knecht die
vnd vil in vntz an den anß
vnd die pferit vntz an die
petel vnd was ze mol ein grosse
nebel dz wir kum gesachend
vnd als mit grosser arbeit kome
wir ze mittem tag zuo sant
kristoffel vff den berg do
do sach ich die buocher do gar
vil herren wopen jn stont
die ir fuor eltern geben hand
do fuond mines vatterß seligen
wopen ouch in dem enen","addition1":"","addition2":"","addition3":""}]}

Scoring

Fuzzy score67.7%
CER ↓33.5%

Speed

Model time, all inputs273.0 s
Mean per input22.75 s
Slowest input40.89 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 tokens9.3K
Output tokens2.8K
Total tokens12.1K
Input cost$0.0116
Output cost$0.0284
Total cost$0.3197
Reasoning cost usd$0.2798
Total reasoning tokens28K

Priced from 2026-01-23 · Input $/M $1.25 · Output $/M $10.00

Result 158 of 177

Test T0293 at 2026-01-24

manuscript transcription handwritten 15 de prose

anthropic claude-sonnet-4-5-20250929 · temp 0.0 · dataclass Document

Response vs ground truth

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

Fuzzy score44.0%
CER ↓56.1%

{"folios":[{"folio":"","text":"Vnd ein pfarꝛit die mir vnd
minen knechtẽ oder hulffend
zũ do was menen kan weg
danne den wir machtend
vnd inellent die knecht dut
mit vil in vntz an den arb
vnd die pfarit vntz an die
fatel vnd was ze mol ein grosse
nebel dz wir kam gesachend
vnd als mit grosser arbeit kame
wir ze mittem tag zu sant
kirstoffel vff den berg do
do sach ich die bucher do gar
zil herren woren zu stont
die in stür delhin gelien hand
do stůnd mines vatters sligen
wappen och in dem emein","addition1":"","addition2":"","addition3":""}]}

Scoring

Fuzzy score25.7%
CER ↓74.3%

Speed

Model time, all inputs143.7 s
Mean per input11.97 s
Slowest input19.32 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 tokens35.9K
Output tokens3.7K
Total tokens39.6K
Input cost$0.1077
Output cost$0.056
Total cost$0.1637

Priced from 2026-01-23 · Input $/M $3.00 · Output $/M $15.00

Result 159 of 177

Test T0409 at 2025-11-25

manuscript transcription handwritten 15 de prose

openai gpt-5.1-2025-11-13 · temp 0.0 · dataclass Document

Response vs ground truth

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

Fuzzy score90.5%
CER ↓10.5%

{"folios":[{"folio":"3","text":"vnd ein pferit die mir mit
minen knechten vber flußend
san so was minen knecht weg
same das mir machten
und vieland die knecht vnd
und vil in vngemeyn arb
vnd die pferit vntz an die
stetl vnd was ze mol ein groszer
nebel dz wir kun geſahen
vnd als mit grosser arbait kamen
wir ze mitten tag zu sant
kristoffel vff den berg do
zo sach ich die buͤrger do gar
vil herren wappen zu roſſe
vnd in iren gehurn getzey hant
zo fuͤnd minen vatter vlagen
woppey och in dem eweg","addition1":"","addition2":"","addition3":""}]}

Scoring

Fuzzy score65.3%
CER ↓37.6%

Speed

Model time, all inputs82.8 s
Mean per input6.90 s
Slowest input11.03 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 tokens18.8K
Output tokens2.5K
Total tokens21.3K
Input cost$0.0235
Output cost$0.0248
Total cost$0.0484

Priced from 2025-11-24 · Input $/M $1.25 · Output $/M $10.00

Result 160 of 177

Test T0271 at 2025-11-24

manuscript transcription handwritten 15 de prose

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

Response vs ground truth

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

Fuzzy score92.5%
CER ↓7.2%

{"folios":[{"folio":"3","text":"Vnd ein pferit Die mir vnd
minen knechten vßß Kulfend
den So was menny kein weg
denne dan wir machend
vnd zichend die knecht dich
vnd vil in vntz an den anb
vnd die pferit vntz an die
potel vnd waß ze mol ein groffe
nebel dz wir kum gepassent
vnd als mit groffer arbeit kome
wir ze mittem tag zu sant
kristoffel vff den berg Do
do sach ich die bůcher Do sar
vil Gerren wapen in pone
Die in sinr edlen geben hand
Do fund mincs vatterß flüßen
wappen ach in sinem wappñ","addition1":"","addition2":"","addition3":""}]}

Scoring

Fuzzy score64.5%
CER ↓39.9%

Speed

Model time, all inputs181.9 s
Mean per input15.16 s
Slowest input27.71 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 tokens9.3K
Output tokens3.1K
Total tokens12.4K
Input cost$0.0028
Output cost$0.0077
Total cost$0.0902
Reasoning cost usd$0.0797
Total reasoning tokens31.9K

Priced from 2025-11-24 · Input $/M $0.30 · Output $/M $2.50