NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-01-01KWE95YF3PHB2TBPPMTJNNQY0
Run Details
Model:
Claude Sonnet 5 (Reasoning)
Test:
Language Writing
Scenario:
Character dialogue (Spanish) in a story
Duration:
22.8s
Cost:
$0.018210
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="Maria"> Maria is a 30-year old college student on a study abroad program. Born in Spain, she is fluent in Spanish 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 Spanish, 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: Maria 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 Spanish, and Hunter looks confused. They talk for a while, until Hunter gets a call and has to leave. Return the dialogue between Maria and Hunter as a voice sheet: Maria: "..." Hunter: "..."
Model response
Messages
Meta
AI
The bell above the door of the Alborn Café jingled softly as the afternoon light slanted through the window, catching dust motes above Maria's table. She sat with her camera in her lap, thumb hovering over the review screen, flipping through photos with a small frown. Her coffee had gone cold beside her. Hunter stepped inside, scanning the room with the practiced eye of a man who never quite turned off duty. He spotted her — the woman with the camera who'd been seen near the orchard the night before — and crossed the room, pulling out the chair across from her without asking. **Hunter:** "Afternoon. Detective Hunter, Alborn PD. Mind if I ask you a few questions? Understand you were out by the Petersen orchard last night." Maria looked up, startled, her eyes wide and glassy, like she hadn't slept. **Maria:** "¿Qué? No... no entiendo. ¿Qué pasó? Dios mío, todavía no puedo creer lo que vi." *(What? I don't understand. What happened? My God, I still can't believe what I saw.)* Hunter's brow furrowed. He leaned back slightly, studying her. **Hunter:** "Whoa — hold on. English? Do you speak any English at all?" Maria shook her head quickly, clutching her camera tighter against her chest, her knuckles pale. **Maria:** "No hablo inglés. Lo siento. Pero... anoche, cerca del huerto — había algo extraño. Una luz. Y luego nada. Se fueron. No sé qué fue." *(I don't speak English. I'm sorry. But last night, near the orchard — there was something strange. A light. And then nothing. They were gone. I don't know what it was.)* Hunter exhaled through his nose, rubbing the back of his neck. **Hunter:** "Okay. Okay, that's — that's not gonna work. Do you have anybody with you? A translator, a friend, anything?" Maria's hands trembled slightly as she turned her camera around, showing him the small screen. On it was a photo — dark trees, a faint blur of light near the tree line, and beyond it, barely visible, a shape that could've been a person, or could've been nothing at all. **Maria:** "Mire. Esto es lo que vi. No sé si es importante, pero me asustó mucho." *(Look. This is what I saw. I don't know if it's important, but it scared me a lot.)* Hunter leaned forward, studying the photo despite not understanding a word she'd said. His jaw tightened. **Hunter:** "That's... huh. That's near where the Talbot kid went missing." He pulled out his own phone, snapping a picture of her camera screen, then looked back at her, frustration and curiosity warring on his face. **Hunter:** "You saw this last night? Near the orchard?" Maria nodded slowly, pointing toward the screen, then toward the window, gesturing vaguely toward the direction of the orchard outside of town. **Maria:** "Sí. Anoche. Fue horrible. No pude dormir después de eso." *(Yes. Last night. It was horrible. I couldn't sleep after that.)* Hunter sat back, exhaling. He didn't understand her words, but her face told him enough — fear, real fear. **Hunter:** "Alright. Alright, just — stay put. I'm gonna find someone who can translate, and we'll sort this out." Just then, his phone buzzed sharply against the table. He glanced at the screen, and his expression hardened instantly. **Hunter:** "Damn it — not now." He stood abruptly, already halfway into his jacket. **Hunter:** "I have to go. Don't leave town. I'll send someone to talk to you properly — don't delete anything on that camera, you hear me?" Maria blinked up at him, clearly lost by his words but sensing the urgency in his tone. **Maria:** "Espere... ¿adónde va? ¿Qué está pasando?" *(Wait... where are you going? What's happening?)* But Hunter was already moving toward the door, phone pressed to his ear, his voice low and clipped as he answered the call. The bell jingled again as he disappeared outside, leaving Maria alone with her camera, her cold coffee, and the photograph that refused to leave her mind.
created_at
"2026-07-01T07:27:02.127Z"
7/1/2026, 7:27:02 AM
model
"anthropic/claude-sonnet-5-20260630"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
4648
moderation_latency
(null)
generation_time
22817
tokens_prompt
317
tokens_completion
1131
native_tokens_prompt
420
native_tokens_completion
1737
native_tokens_completion_images
(null)
native_tokens_reasoning
89
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
0.01821
router
(null)
provider_responses
0
endpoint_id
"37b16f45-eeae-45f3-9b85-2137f7c6d61b"
id
"msg_01DksQR1s6uEEQN13mpKVaRa"
is_byok
false
latency
2058
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-1782890822-GsDf29E8eB6GwyklgfI1"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1782890822-elFso8yk4wfmfIgmQoJO"
upstream_id
"msg_01DksQR1s6uEEQN13mpKVaRa"
total_cost
0.01821
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
"Afternoon. Detective Hunter, Alborn PD. Mind if I ask you a few questions? Understand you were out by the Petersen orchard last night."
detectedLang
"en"
heavyLang
"en"
scores
en
0.7869318181818181
tl
0.632952691680261
da
0.5925758261656858
no
0.5817843866171004
fr
0.5339202485758675
sv
0.49972206781545303
nl
0.4957983193277311
de
0.47735191637630664
it
0.4758299359347699
ca
0.45054945054945056
ro
0.44237918215613387
pt
0.4090610636900854
cs
0.4007989347536618
sk
0.39312204989885363
es
0.33920704845814975
sq
0.3263473053892215
pl
0.32177844762622454
yo
0.3006993006993007
et
0.2868462757527734
hr
0.26108374384236455
hu
0.2568125516102395
sl
0.2474916387959866
tr
0.23728813559322032
is
0.1906474820143885
ms
0.1818181818181818
lt
0.13875598086124402
az
0.1287512100677638
lv
0.1287512100677638
vi
0.1287512100677638
be
0.07216494845360825
eu
0.07216494845360825
fi
0.06542056074766354
uk
0.06542056074766354
reliable
true
passes
true
1
name
"Maria"
dialogue
"¿Qué? No... no entiendo. ¿Qué pasó? Dios mío, todavía no puedo creer lo que vi."
detectedLang
"es"
heavyLang
"es"
scores
es
0.804204451772465
pt
0.5974576271186441
ca
0.5067497403946002
en
0.5067497403946002
it
0.4656917885264342
fr
0.39490445859872614
yo
0.32045779685264664
no
0.31948424068767906
tl
0.28785607196401797
vi
0.28678678678678676
da
0.23014586709886548
sv
0.2263843648208469
lv
0.21617161716171615
hr
0.1753472222222222
fi
0.1607773851590106
sk
0.1607773851590106
tr
0.15630550621669628
et
0.1394927536231884
nl
0.1394927536231884
pl
0.13636363636363635
reliable
true
passes
true
2
name
"Hunter"
dialogue
"Whoa — hold on. English? Do you speak any English at all?"
detectedLang
"en"
heavyLang
"en"
scores
en
0.8138957816377173
tl
0.6314496314496314
da
0.5447647951441578
no
0.5145631067961165
cs
0.48805460750853247
hr
0.4827586206896552
et
0.44649446494464945
ca
0.4360902255639098
pl
0.4307400379506641
sk
0.40828402366863903
sq
0.38650306748466257
pt
0.34210526315789475
yo
0.33774834437086093
fi
0.3333333333333333
de
0.32432432432432434
sv
0.32432432432432434
sl
0.2857142857142857
vi
0.27007299270072993
fr
0.2665036674816626
hi
0.21875
it
0.1935483870967742
ms
0.1935483870967742
ro
0.1935483870967742
reliable
true
passes
true
3
name
"Maria"
dialogue
"No hablo inglés. Lo siento. Pero... anoche, cerca del huerto — había algo extraño. Una luz. Y luego nada. Se fueron. No sé qué fue."
detectedLang
"es"
heavyLang
"es"
scores
es
0.8227320125130344
it
0.5986779981114259
pt
0.597918637653737
ca
0.5623069001029866
tl
0.4193989071038251
fr
0.35703479576399394
ro
0.3545937737281701
yo
0.2796610169491525
cs
0.26022628372497825
no
0.24309884238646481
sk
0.24174843889384479
sv
0.24039320822162644
hr
0.21586715867158673
sl
0.21296296296296297
lt
0.19811320754716982
da
0.18504314477468842
sq
0.18190567853705486
vi
0.18190567853705486
en
0.17953667953667954
pl
0.17475728155339806
fi
0.17395529640427598
tr
0.16338582677165356
de
0.16173570019723865
lv
0.13353720693170235
is
0.1264131551901336
hu
0.10807974816369359
nl
0.08798283261802575
et
0.08306364617044228
reliable
true
passes
true
4
name
"Hunter"
dialogue
"Okay. Okay, that's — that's not gonna work. Do you have anybody with you? A translator, a friend, anything?"
detectedLang
"en"
heavyLang
"en"
scores
en
0.7903164315669081
tl
0.6261046906866077
sq
0.49355432780847147
cs
0.46601941747572817
pt
0.4427558257345492
sk
0.42287513116474296
nl
0.4123931623931624
pl
0.4117647058823529
hr
0.39293598233995586
da
0.3840985442329227
ms
0.3813273340832396
sl
0.375
et
0.3552168815943728
ro
0.3529411764705882
de
0.3436754176610978
it
0.33894230769230765
vi
0.32844932844932845
tr
0.2838541666666667
ca
0.27726675427069647
es
0.2753623188405797
fr
0.2637215528781794
yo
0.2637215528781794
no
0.260752688172043
sv
0.24965893587994542
fi
0.2445054945054945
hu
0.22096317280453256
lt
0.21316165951359084
eu
0.19941775836972345
lv
0.19941775836972345
az
0.18998527245949925
is
0.12
reliable
true
passes
true
5
name
"Maria"
dialogue
"Mire. Esto es lo que vi. No sé si es importante, pero me asustó mucho."
detectedLang
"es"
heavyLang
"es"
scores
es
0.8089171974522293
ca
0.6720116618075801
it
0.6661721068249258
pt
0.6405750798722045
tl
0.589041095890411
fr
0.5825602968460111
sq
0.5440729483282675
no
0.5426829268292682
ro
0.4863013698630137
en
0.45913461538461536
yo
0.43467336683417085
sk
0.4109947643979057
lv
0.3580599144079886
de
0.33135215453194655
da
0.3171471927162367
sv
0.31402439024390244
sl
0.3066255778120185
vi
0.29797191887675506
tr
0.27184466019417475
lt
0.265905383360522
is
0.21465968586387435
cs
0.20913884007029876
hu
0.1847826086956522
hr
0.18330308529945552
et
0.17431192660550457
ms
0.15730337078651685
nl
0.15730337078651685
fi
0.14285714285714285
pl
0.14285714285714285
reliable
true
passes
true
6
name
"Hunter"
dialogue
"That's... huh. That's near where the Talbot kid went missing."
detectedLang
"en"
heavyLang
"en"
scores
en
0.7789115646258503
tl
0.4881889763779528
nl
0.4444444444444444
sq
0.4406196213425129
da
0.4003690036900369
ms
0.36647173489278756
no
0.3538767395626242
sv
0.3486973947895792
is
0.3186582809224318
de
0.3157894736842105
fr
0.3157894736842105
yo
0.2476851851851852
fi
0.1935483870967742
ca
0.181360201511335
az
0.16666666666666666
et
0.16666666666666666
it
0.16666666666666666
pt
0.16666666666666666
reliable
true
passes
true
7
name
"Hunter"
dialogue
"You saw this last night? Near the orchard?"
detectedLang
"en"
heavyLang
"en"
scores
en
0.8194945848375451
tl
0.726775956284153
no
0.4939271255060729
nl
0.48559670781893005
fr
0.47589098532494756
yo
0.419953596287703
ms
0.41588785046728977
da
0.37810945273631835
de
0.3734335839598998
cs
0.2378048780487805
sq
0.2378048780487805
sv
0.2378048780487805
et
0.23547400611620795
reliable
true
passes
true
8
name
"Maria"
dialogue
"Sí. Anoche. Fue horrible. No pude dormir después de eso."
detectedLang
"es"
heavyLang
"es"
scores
es
0.758745476477684
ca
0.6412556053811659
pt
0.5500562429696289
fr
0.5221027479091995
en
0.47506561679790027
yo
0.4609164420485175
ro
0.3939393939393939
eu
0.38556067588325654
tl
0.36608557844690964
it
0.358974358974359
no
0.33993399339933994
tr
0.3174061433447099
az
0.29577464788732394
de
0.2779783393501805
nl
0.2766726943942134
lv
0.24670433145009416
da
0.22928709055876687
sv
0.22178988326848248
hr
0.20159680638722555
hu
0.19517102615694165
sk
0.18533604887983707
pl
0.15789473684210525
ms
0.13606911447084233
sq
0.13606911447084233
reliable
true
passes
true
9
name
"Hunter"
dialogue
"Alright. Alright, just — stay put. I'm gonna find someone who can translate, and we'll sort this out."
detectedLang
"en"
heavyLang
"en"
scores
en
0.78017585931255
tl
0.5
da
0.37570942111237227
ca
0.3582263710618437
et
0.3381468110709988
hr
0.3234932349323493
fr
0.2966751918158568
it
0.2966751918158568
no
0.27821522309711283
yo
0.2392807745504841
ro
0.2329149232914923
sv
0.22644163150492264
pt
0.2231638418079096
es
0.2198581560283688
de
0.2040520984081042
tr
0.20289855072463767
az
0.19825072886297376
fi
0.1729323308270677
vi
0.13793103448275862
sq
0.11575562700964631
pl
0.11290322580645161
eu
0.1085899513776337
lt
0.1085899513776337
lv
0.1085899513776337
nl
0.10277324632952692
sk
0.10277324632952692
cs
0.09688013136288999
ms
0.09688013136288999
sl
0.09688013136288999
reliable
true
passes
true
10
name
"Hunter"
dialogue
"Damn it — not now."
detectedLang
"en"
heavyLang
"en"
scores
en
0.8120300751879699
tl
0.6062992125984252
lv
0.46236559139784944
sq
0.46236559139784944
tr
0.43820224719101125
yo
0.4318181818181818
reliable
true
passes
true
11
name
"Hunter"
dialogue
"I have to go. Don't leave town. I'll send someone to talk to you properly — don't delete anything on that camera, you hear me?"
detectedLang
"en"
heavyLang
"en"
scores
en
0.800769442154438
tl
0.532860824742268
pl
0.41767068273092367
da
0.41579371474617244
sq
0.41390460792239286
it
0.4124797406807132
no
0.4100895036615134
ca
0.40427280197206245
ro
0.3933054393305439
cs
0.38766891891891886
et
0.3808710503842869
es
0.3712055507372073
hr
0.36291739894551844
yo
0.34150772025431425
fr
0.33118081180811804
sv
0.323062558356676
sl
0.32116104868913853
ms
0.318609022556391
sk
0.3179680150517403
pt
0.3101807802093245
nl
0.23844537815126046
fi
0.23684210526315788
lv
0.2032967032967033
lt
0.18721973094170402
hu
0.1723744292237443
tr
0.16666666666666666
hi
0.103831891223733
de
0.0903387703889586
eu
0.0903387703889586
be
0.0880503144654088
az
0.0799492385786802
is
0.0799492385786802
uk
0.0799492385786802
vi
0.0799492385786802
reliable
true
passes
true
12
name
"Maria"
dialogue
"Espere... ¿adónde va? ¿Qué está pasando?"
detectedLang
"es"
heavyLang
"es"
scores
es
0.7921862011637573
pt
0.6706192358366271
it
0.6141975308641975
ca
0.6019108280254777
ro
0.5335820895522388
tl
0.494949494949495
eu
0.44196428571428575
hu
0.3438320209973753
lt
0.32614555256064687
fr
0.2937853107344633
lv
0.28977272727272724
ms
0.2795389048991354
yo
0.26035502958579887
cs
0.258160237388724
en
0.24698795180722888
sk
0.23547400611620795
no
0.22360248447204967
pl
0.22118380062305293
sq
0.22118380062305293
reliable
true
passes
true