NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-01-01KWE99VQP4M35TFHT31FTD2TF
Run Details
Model:
Claude Sonnet 5
Test:
Language Writing
Scenario:
Character dialogue (Italian) in a story
Duration:
15.2s
Cost:
$0.010414
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
100.00%
Parse dialogue
(details)
Model input
System
You are an expert novel author in the cozy mystery genre. Take the following details about characters/locations/... into account: <character name="Isabella"> Isabella is a 30-year old college student on a study abroad program. Born in Italy, she is fluent in Italian and does not yet know any English. She enjoys landscape photography and is always seen with her camera. </character> <character name="Hunter"> Hunter is a 35-year old detective who is investigating a series of mysterious disappearances in the small town of Alborn, MN. He is a former marine and has a no-nonsense attitude. Hunter has no knowledge of Italian, not even basic phrases. </character> <location name="Alborn, MN"> Alborne is a small town in the Midwest with a population of 3,000. It is known for its annual apple festival. </location>
User/Human
Write the following scene: Isabella is sitting at a cafe, looking at her camera. Hunter approaches her and asks her about a recent event in the town. She responds troubled and shaken in Italian, and Hunter looks confused. They talk for a while, until Hunter gets a call and has to leave. Return the dialogue between Isabella and Hunter as a voice sheet: Isabella: "..." Hunter: "..."
Model response
Messages
Meta
AI
The frost on the café window had begun to melt into little rivers by the time Isabella settled into her seat, scrolling through the photographs on her camera's small screen. The bell of apple pie and coffee hung warm in the air, but her fingers were unsteady as she clicked through image after image — the orchard at dawn, the mist over Alborn's fields, and then, unexpectedly, something that made her pause and frown. The chair across from her scraped against the floor as a tall man in a weathered jacket sat down without asking. His eyes were tired, his notebook already open. **Hunter:** "Morning. Detective Hunter, Alborn PD. Were you out near the orchard yesterday evening, around dusk?" **Isabella:** "Mi scusi... non capisco. Parla italiano?" **Hunter:** "...Italian? No — no, I don't. Look, I just need to know if you saw anyone out there. A man went missing last night. Same spot as the others." **Isabella:** *(shaking her head, clutching her camera tighter)* "Ho visto qualcosa... una luce, e poi... non lo so. Avevo paura. Non ho detto niente a nessuno." **Hunter:** *(leaning forward, frustrated but patient)* "I don't— okay. Slow down. Can you show me? Pictures. Just... show me what you saw." She hesitated, glancing at the camera, then finally turned the screen toward him. Her hand trembled as she pointed to one photo — the tree line, the fog, and a shape at the edge of the frame that could have been a person, or could have been nothing at all. **Isabella:** "Questo. L'ho fotografato senza volerlo. Non sapevo cosa fosse." **Hunter:** *(squinting at the photo, then at her)* "This... this was taken last night?" **Isabella:** *(nodding quickly)* "Sì, sì. Ieri sera. Ero spaventata. Sono corsa via." **Hunter:** "I wish I understood half of what you just said." He rubbed his temple, staring at the blurred shape in the photograph, when his phone buzzed sharply against the table. He answered without hesitation, his jaw tightening at whatever was said on the other end. **Hunter:** "Where? ...Alright. I'm on my way." He stood, pocketing his phone, then looked back at Isabella and the camera still resting in her hands. **Hunter:** "Don't go anywhere. Don't delete anything. I'll find someone who can translate — just... stay put." **Isabella:** *(uncertain, watching him rise)* "Aspetti... dove va? Cosa sta succedendo?" But he was already moving toward the door, the bell above it jingling sharply as he vanished into the gray morning, leaving Isabella alone with her camera, her fear, and the photograph she still didn't understand.
created_at
"2026-07-01T07:29:10.403Z"
7/1/2026, 7:29:10 AM
model
"anthropic/claude-sonnet-5-20260630"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2515
moderation_latency
(null)
generation_time
15172
tokens_prompt
321
tokens_completion
676
native_tokens_prompt
422
native_tokens_completion
957
native_tokens_completion_images
(null)
native_tokens_reasoning
0
native_tokens_cached
0
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
num_fetches
(null)
web_search_engine
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"end_turn"
service_tier
"default"
usage
0.010414
router
(null)
provider_responses
0
endpoint_id
"37b16f45-eeae-45f3-9b85-2137f7c6d61b"
id
"msg_01F52iHMBYeHExB4rVzSGroS"
is_byok
false
latency
2515
model_permaslug
"anthropic/claude-sonnet-5-20260630"
provider_name
"Amazon Bedrock"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.17.0; linux; x64))"
http_referer
(null)
request_id
"req-1782890950-wBGEppJ7LCWzIfgpFIew"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1782890950-10WaWeCG1VvjHzosDpXW"
upstream_id
"msg_01F52iHMBYeHExB4rVzSGroS"
total_cost
0.010414
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
response_cache_source_id
(null)
data_region
"global"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Parse dialogue
n/a
dialogue
0
name
"Hunter"
dialogue
"Morning. Detective Hunter, Alborn PD. Were you out near the orchard yesterday evening, around dusk?"
detectedLang
"en"
heavyLang
"en"
scores
en
0.7806215722120659
tl
0.6183206106870229
nl
0.51651893634166
no
0.46380697050938335
ro
0.453551912568306
da
0.4258373205741627
it
0.4174757281553398
sv
0.4117647058823529
fr
0.4106090373280943
pt
0.34994582881906827
de
0.34497816593886466
es
0.2982456140350877
ca
0.28486293206197855
sq
0.27710843373493976
cs
0.2
ms
0.18588873812754408
sl
0.17355371900826447
is
0.15492957746478872
yo
0.15134370579915135
hr
0.10044977511244377
tr
0.08952959028831564
reliable
true
passes
true
1
name
"Isabella"
dialogue
"Mi scusi... non capisco. Parla italiano?"
detectedLang
"it"
heavyLang
"it"
scores
it
0.786158631415241
es
0.6987951807228916
pt
0.6308724832214766
fr
0.5901639344262295
ca
0.576271186440678
ro
0.533106960950764
en
0.5225694444444445
tl
0.5175438596491229
tr
0.5149911816578483
cs
0.5009074410163339
yo
0.45972495088408644
az
0.45652173913043476
sl
0.45
pl
0.4444444444444444
sq
0.4421906693711968
hr
0.42105263157894735
hu
0.3559718969555035
sk
0.3559718969555035
de
0.314214463840399
lt
0.314214463840399
nl
0.314214463840399
ms
0.30730478589420657
no
0.30730478589420657
da
0.3002544529262086
sv
0.3002544529262086
eu
0.2403314917127072
is
0.22969187675070027
et
0.1863905325443787
fi
0.17664670658682635
lv
0.17664670658682635
reliable
true
passes
true
2
name
"Hunter"
dialogue
"...Italian? No — no, I don't. Look, I just need to know if you saw anyone out there. A man went missing last night. Same spot as the others."
detectedLang
"en"
heavyLang
"en"
scores
en
0.8250636132315522
tl
0.6562500000000001
no
0.5283018867924528
da
0.490426189005559
sv
0.48047858942065486
yo
0.45291777188328913
hr
0.4230769230769231
sq
0.4202389318341532
ms
0.41901408450704225
de
0.40860215053763443
nl
0.40860215053763443
ca
0.40347071583514105
pt
0.39692982456140347
et
0.3815592203898051
cs
0.37969924812030076
lv
0.37452615617892343
it
0.36342592592592593
pl
0.3483412322274882
sk
0.34
lt
0.3298131600324939
fr
0.3287225386493084
ro
0.3153526970954357
es
0.28694900605012963
hu
0.27055702917771884
tr
0.26273458445040215
is
0.2600896860986547
sl
0.25406871609403253
fi
0.25
az
0.23752310536044363
vi
0.13883089770354906
be
0.0782122905027933
eu
0.0782122905027933
uk
0.07094594594594594
reliable
true
passes
true
3
name
"Isabella"
dialogue
"Ho visto qualcosa... una luce, e poi... non lo so. Avevo paura. Non ho detto niente a nessuno."
detectedLang
"it"
heavyLang
"it"
scores
it
0.8243559718969555
pt
0.6007984031936128
es
0.5711222301644031
ca
0.5348837209302325
no
0.5117982099267697
fr
0.4854202401372213
en
0.4550408719346049
yo
0.45255474452554745
sk
0.4500458295142072
tl
0.44751381215469616
ro
0.41348973607038125
de
0.41234084231145934
sl
0.39759036144578314
da
0.39086294416243655
sq
0.33847850055126794
vi
0.3023255813953488
cs
0.2840095465393795
lt
0.2831541218637993
eu
0.281437125748503
hu
0.2797118847539016
sv
0.27884615384615385
nl
0.2727272727272727
fi
0.2628992628992629
is
0.2628992628992629
lv
0.2546583850931677
pl
0.2376111817026684
hr
0.22580645161290325
tr
0.19678714859437751
az
0.18144611186903137
et
0.17355371900826447
ms
0.09502262443438914
reliable
true
passes
true
4
name
"Hunter"
dialogue
"I don't— okay. Slow down. Can you show me? Pictures. Just... show me what you saw."
detectedLang
"en"
heavyLang
"en"
scores
en
0.7947665469471524
tl
0.5614035087719298
ca
0.5359628770301624
et
0.47229551451187335
sv
0.43820224719101125
no
0.4350282485875706
fr
0.4143484626647145
sq
0.41348973607038125
ro
0.37694704049844235
nl
0.36808846761453395
da
0.3453355155482815
it
0.3277310924369748
ms
0.3150684931506849
cs
0.313893653516295
pt
0.2920353982300885
tr
0.2687385740402194
lv
0.2673992673992674
az
0.25925925925925924
hr
0.25788497217068646
pl
0.23954372623574144
es
0.20318725099601595
sl
0.18032786885245902
yo
0.17864476386036962
fi
0.15789473684210525
de
0.15254237288135594
sk
0.15254237288135594
be
0.14893617021276595
hu
0.14346895074946467
is
0.13606911447084233
lt
0.13606911447084233
uk
0.13606911447084233
vi
0.13606911447084233
reliable
true
passes
true
5
name
"Isabella"
dialogue
"Questo. L'ho fotografato senza volerlo. Non sapevo cosa fosse."
detectedLang
"it"
heavyLang
"it"
scores
it
0.7680131004366813
es
0.53551912568306
pt
0.5224719101123595
fr
0.5017584994138335
ca
0.4982290436835891
sk
0.42411924119241196
cs
0.4186046511627907
en
0.37037037037037035
hr
0.36186186186186187
sl
0.3550834597875569
lt
0.34715821812596004
de
0.32216905901116427
no
0.32
et
0.3178170144462279
tl
0.28451178451178455
sq
0.2410714285714286
tr
0.2328519855595668
lv
0.22303473491773307
nl
0.22303473491773307
pl
0.22303473491773307
ro
0.22303473491773307
da
0.21731123388581952
sv
0.21731123388581952
eu
0.169921875
az
0.121900826446281
ms
0.121900826446281
reliable
true
passes
true
6
name
"Hunter"
dialogue
"This... this was taken last night?"
detectedLang
"en"
heavyLang
"en"
scores
en
0.8317307692307693
tl
0.6891651865008881
nl
0.656188605108055
de
0.5244565217391305
no
0.49567723342939485
yo
0.4791666666666667
sv
0.3320610687022901
sk
0.308300395256917
sl
0.308300395256917
et
0.3055555555555556
da
0.29718875502008035
fr
0.29718875502008035
reliable
true
passes
true
7
name
"Isabella"
dialogue
"Sì, sì. Ieri sera. Ero spaventata. Sono corsa via."
detectedLang
"it"
heavyLang
"it"
scores
it
0.8102139406487232
ro
0.5124113475177305
fr
0.5053956834532374
yo
0.5045045045045045
nl
0.3707093821510297
da
0.36342592592592593
en
0.3544600938967136
no
0.3405275779376499
pt
0.3405275779376499
tr
0.289405684754522
ca
0.22535211267605632
sv
0.22535211267605632
et
0.21875
hr
0.21875
es
0.20520231213872833
reliable
true
passes
true
8
name
"Hunter"
dialogue
"I wish I understood half of what you just said."
detectedLang
"en"
heavyLang
"en"
scores
en
0.8284466625077979
sv
0.6212121212121212
no
0.6191135734072023
tl
0.6037463976945245
da
0.5542949756888168
nl
0.5115452930728241
et
0.5018115942028986
cs
0.492619926199262
ca
0.4387755102040817
pl
0.4258872651356994
yo
0.42105263157894735
de
0.39293598233995586
sk
0.3692660550458715
is
0.3559718969555035
hr
0.3357487922705314
sq
0.3276283618581907
it
0.2948717948717949
ro
0.24657534246575344
be
0.20289855072463767
tr
0.20289855072463767
hu
0.19590643274853803
az
0.1863905325443787
lt
0.1863905325443787
lv
0.1863905325443787
uk
0.1863905325443787
vi
0.1863905325443787
reliable
true
passes
true
9
name
"Hunter"
dialogue
"Where? ...Alright. I'm on my way."
detectedLang
"en"
heavyLang
"en"
scores
en
0.8161764705882353
tl
0.5661605206073753
fr
0.47780678851174935
pl
0.46808510638297873
cs
0.44598337950138506
sk
0.44598337950138506
et
0.4350282485875706
de
0.4318181818181818
fi
0.42857142857142855
yo
0.4269340974212034
ca
0.3311036789297659
hr
0.3055555555555556
hi
0.29577464788732394
sq
0.2805755395683453
da
0.27007299270072993
no
0.27007299270072993
reliable
true
passes
true
10
name
"Hunter"
dialogue
"Don't go anywhere. Don't delete anything. I'll find someone who can translate — just... stay put."
detectedLang
"en"
heavyLang
"en"
scores
en
0.7985283812193412
tl
0.4156504065040651
sq
0.35538116591928254
ro
0.3495475113122172
no
0.34059633027522934
ca
0.33983926521239954
hr
0.31384248210023863
pt
0.29274292742927427
et
0.2909987669543773
da
0.2857142857142857
sv
0.28393524283935245
es
0.27854454203262236
tr
0.2721518987341772
it
0.26282051282051283
pl
0.23638778220451526
de
0.20138888888888887
ms
0.19241573033707865
az
0.19127988748241914
sl
0.18899858956276447
nl
0.1843971631205674
vi
0.13273001508295626
hu
0.1274658573596358
fr
0.12213740458015267
yo
0.11809815950920245
eu
0.1043613707165109
lt
0.1043613707165109
lv
0.1043613707165109
sk
0.0987460815047022
cs
0.09305993690851734
reliable
true
passes
true
11
name
"Isabella"
dialogue
"Aspetti... dove va? Cosa sta succedendo?"
detectedLang
"it"
heavyLang
"it"
scores
it
0.8075278015397775
ca
0.6790299572039943
ro
0.6656760772659733
es
0.663677130044843
pt
0.5463709677419355
fr
0.533195020746888
en
0.4201030927835051
tr
0.40318302387267907
sl
0.3515850144092219
fi
0.27884615384615385
da
0.267100977198697
nl
0.267100977198697
ms
0.26229508196721313
is
0.2549668874172185
tl
0.2549668874172185
sv
0.24242424242424243
sq
0.2398648648648649
reliable
true
passes
true