Run: 2026-02-16-01KHKA9T1CBQXAASGT2TGVXMBH

Run Details

Model:
GPT-5
Duration:
1m 39s
Cost:
$0.054530
Provider:
OpenAI

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="Selvi"> Selvi is a 30-year old college student on a study abroad program. Born in India, she is fluent in Hindi 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 Hindi, 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: Selvi 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 Hindi, and Hunter looks confused. They talk for a while, until Hunter gets a call and has to leave. Return the dialogue between Selvi and Hunter as a voice sheet: Selvi: "..." Hunter: "..."

Model response

AI
Hunter: "Afternoon. I'm Detective Hunter with Alborn PD. Mind if I ask you a few questions about last night?" Selvi: "माफ़ कीजिए, मैं अंग्रेज़ी नहीं बोलती। मैं सेल्वी हूँ।" Hunter: "Right. Okay. Do you speak English? English?" Selvi: "नहीं... अंग्रेज़ी नहीं। मैं बस तस्वीरें ले रही थी।" Hunter: "Photos? Camera? You were taking photos?" Selvi: "हाँ, कैमरा... तस्वीरें। कल रात भी।" Hunter: "Good. Can I see? Show me? Photos?" Selvi: "ये देखिए, सर।" Hunter: "Okay... This looks like the orchard road. The festival grounds?" Selvi: "सेब का बाग... हाँ। सड़क के किनारे। धुंध थी।" Hunter: "Fog. Got it. Time? When?" Selvi: "लगभग नौ बजे... फिर अचानक चीख सुनाई दी।" Hunter: "Scream? Someone screamed?" Selvi: "हाँ, चीख... बहुत तेज़। मैं डर गई।" Hunter: "You saw anyone? A face? A vehicle?" Selvi: "छाया जैसा... एक आदमी... और छोटे टायर के निशान। जैसे ट्रॉली।" Hunter: "Small tracks... a cart. Any truck? License plate?" Selvi: "नहीं दिखा... बस अंधेरा और धुंध। यह निशान देखिए।" Hunter: "Yeah, I see the tracks. Where exactly? By the barn? By the road?" Selvi: "बाग के किनारे, पुराने लाल खलिहान के पास। पुल नहीं... पगडंडी।" Hunter: "Old red barn. Got it. What time did the scream stop?" Selvi: "कुछ ही पलों में... फिर सब चुप। मैंने कॉल करने की कोशिश की, लेकिन फोन बंद हो गया।" Hunter: "Your phone died. Anyone else there? Anyone with you?" Selvi: "नहीं। मैं अकेली थी। मैं बस पढ़ाई के लिए यहाँ आई हूँ... तस्वीरें लेती हूँ।" Hunter: "Okay. Can you send these photos to me? Email? Text?" Selvi: "मुझे समझ नहीं आया... पर मैं कैमरा संभाल कर रखूँगी। कृपया।" Hunter: "Keep it safe. Don't delete. I'll find someone who can translate." Selvi: "मैं सच बोल रही हूँ... मैंने कुछ बुरा देखा।" Hunter: "I believe you. You're safe." Hunter: "Hunter." Hunter: "Yeah. Copy. On my way." Hunter: "I have to go. Thank you. Keep your camera with you." Selvi: "कृपया... कोई मेरी बात समझाए।" Hunter: "I'll send someone who speaks Hindi. Stay here if you can." Selvi: "ठीक है... मैं यहीं रहूँगी।" Hunter: "Thank you, Selvi." Selvi: "धन्यवाद।"
created_at"2026-02-16T13:31:48.6649+00:00" 2/16/2026, 1:31:48 PM
model"openai/gpt-5-2025-08-07"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency11121
moderation_latency(null)
generation_time98408
tokens_prompt315
tokens_completion2363
native_tokens_prompt272
native_tokens_completion5419
native_tokens_completion_images0
native_tokens_reasoning4736
native_tokens_cached0
num_media_prompt(null)
num_input_audio_prompt(null)
num_media_completion0
num_search_results(null)
origin"https://ncbench.com/"
is_byokfalse
finish_reason"stop"
native_finish_reason"completed"
usage0.05453
router(null)
provider_responses
0
id"resp_086e9dc81875b6660169931be16e44819596c93df0bd2e69ff"
status200
is_byokfalse
latency180
endpoint_id"7c2f859a-7890-4e8e-b1de-1cd1c0a800b4"
provider_name"OpenAI"
model_permaslug"openai/gpt-5-2025-08-07"
api_type"completions"
id"gen-1771248609-puEfw5p7mBNPQZACRnl8"
upstream_id"resp_086e9dc81875b6660169931be16e44819596c93df0bd2e69ff"
total_cost0.05453
cache_discount(null)
upstream_inference_cost0
provider_name"OpenAI"

Evaluation details

Result Evaluator Details Meta Data
100.00% Parse dialogue n/a
dialogue
0
name"Hunter"
dialogue"Afternoon. I'm Detective Hunter with Alborn PD. Mind if I ask you a few questions about last night?"
detectedLang"en"
heavyLang"en"
scores
en0.7973950795947902
tl0.6430392656807752
it0.5385629531970995
fr0.5345744680851064
ca0.4833948339483395
ro0.47761194029850745
pt0.4708994708994709
da0.4395516413130504
no0.43273905996758516
es0.39759036144578314
sv0.3848857644991213
nl0.358974358974359
cs0.3560257589696412
sq0.3383742911153119
hr0.31237721021611
de0.3089832181638697
hu0.3076162215628091
et0.29364278506559033
yo0.2857142857142857
sk0.2842535787321063
pl0.24812030075187969
sl0.23580786026200873
tr0.2273730684326711
ms0.2222222222222222
lt0.17159763313609466
is0.16467780429594273
az0.15966386554621848
lv0.15966386554621848
vi0.15966386554621848
be0.09090909090909091
eu0.09090909090909091
fi0.08256880733944955
uk0.08256880733944955
reliabletrue
passestrue
1
name"Selvi"
dialogue"माफ़ कीजिए, मैं अंग्रेज़ी नहीं बोलती। मैं सेल्वी हूँ।"
detectedLang"hi"
heavyLang"hi"
scores
hi0.8902942694889003
mr0.8833699231613611
reliabletrue
passestrue
2
name"Hunter"
dialogue"Right. Okay. Do you speak English? English?"
detectedLang"en"
heavyLang"en"
scores
en0.8051948051948052
tl0.6826516220028209
cs0.48394495412844035
hr0.460431654676259
no0.4094488188976378
pt0.4094488188976378
yo0.40318302387267907
da0.3935309973045822
de0.3935309973045822
pl0.3885869565217392
sk0.3697478991596639
sl0.34782608695652173
sq0.34210526315789475
vi0.33035714285714285
fr0.2474916387959866
ms0.24242424242424243
ro0.24242424242424243
sv0.24242424242424243
reliabletrue
passestrue
3
name"Selvi"
dialogue"नहीं... अंग्रेज़ी नहीं। मैं बस तस्वीरें ले रही थी।"
detectedLang"hi"
heavyLang"hi"
scores
hi0.884125144843569
mr0.8804185351270553
reliabletrue
passestrue
4
name"Hunter"
dialogue"Photos? Camera? You were taking photos?"
detectedLang"en"
heavyLang"en"
scores
en0.7874601487778958
tl0.6715927750410509
fr0.6219281663516069
nl0.5545657015590201
de0.5271867612293144
es0.47229551451187335
ca0.46380697050938335
it0.441340782122905
ro0.441340782122905
sv0.43342776203966005
pt0.4301994301994302
pl0.3464052287581699
no0.3006993006993007
tr0.3006993006993007
fi0.2857142857142857
lt0.2857142857142857
cs0.2805755395683453
hi0.2779783393501805
ms0.2647058823529412
et0.26199261992619927
is0.26199261992619927
lv0.26199261992619927
sk0.26199261992619927
sl0.26199261992619927
sq0.26199261992619927
reliabletrue
passestrue
5
name"Selvi"
dialogue"हाँ, कैमरा... तस्वीरें। कल रात भी।"
detectedLang"mr"
heavyLang"hi"
scores
mr0.8871331828442438
hi0.8859749144811858
reliabletrue
passestrue
6
name"Hunter"
dialogue"Good. Can I see? Show me? Photos?"
detectedLang"en"
heavyLang"en"
scores
en0.8078770413064361
tl0.6389891696750902
et0.6212121212121212
ca0.588477366255144
sq0.5850622406639004
fr0.5771670190274841
pt0.550561797752809
no0.5412844036697247
nl0.5370370370370371
it0.4936708860759494
es0.47643979057591623
tr0.42363112391930835
lt0.41690962099125367
az0.4117647058823529
da0.41002949852507375
hr0.41002949852507375
sv0.40828402366863903
lv0.40119760479041916
pl0.38650306748466257
cs0.3442622950819672
ro0.3103448275862069
sl0.3055555555555556
yo0.30313588850174217
ms0.29577464788732394
hi0.2779783393501805
fi0.2727272727272727
sk0.2647058823529412
de0.26199261992619927
be0.25925925925925924
hu0.250936329588015
is0.23954372623574144
uk0.23954372623574144
vi0.23954372623574144
reliabletrue
passestrue
7
name"Selvi"
dialogue"ये देखिए, सर।"
detectedLang"hi"
heavyLang"hi"
scores
hi0.8872180451127819
mr0.8797113071371291
reliabletrue
passestrue
8
name"Hunter"
dialogue"Okay... This looks like the orchard road. The festival grounds?"
detectedLang"en"
heavyLang"en"
scores
en0.7906698564593302
tl0.7105045492142266
no0.5793269230769231
fr0.5575221238938053
nl0.49567723342939485
sv0.43910256410256415
da0.4308943089430894
ms0.4233937397034596
sq0.37275985663082434
ca0.37050359712230213
hr0.36479128856624315
pt0.36479128856624315
it0.3613138686131387
cs0.3482309124767225
sl0.3482309124767225
es0.3433395872420263
de0.29292929292929293
lt0.2647058823529412
et0.2584745762711864
az0.25213675213675213
ro0.25213675213675213
sk0.25213675213675213
yo0.23413566739606126
hu0.1606714628297362
fi0.15254237288135594
lv0.15254237288135594
pl0.15254237288135594
reliabletrue
passestrue
9
name"Selvi"
dialogue"सेब का बाग... हाँ। सड़क के किनारे। धुंध थी।"
detectedLang"hi"
heavyLang"hi"
scores
hi0.8925361469323955
mr0.8840151834668916
reliabletrue
passestrue
10
name"Hunter"
dialogue"Fog. Got it. Time? When?"
detectedLang"en"
heavyLang"en"
scores
en0.812874251497006
tl0.571917808219178
hu0.4834710743801653
lv0.4075829383886255
sq0.4075829383886255
hr0.40191387559808617
pt0.40191387559808617
yo0.37810945273631835
da0.375
no0.375
reliabletrue
passestrue
11
name"Selvi"
dialogue"लगभग नौ बजे... फिर अचानक चीख सुनाई दी।"
detectedLang"hi"
heavyLang"hi"
scores
hi0.8784440842787682
mr0.8700923787528868
reliabletrue
passestrue
12
name"Hunter"
dialogue"Scream? Someone screamed?"
detectedLang"en"
heavyLang"en"
scores
en0.7787610619469026
pt0.5426829268292682
ms0.42748091603053434
et0.39999999999999997
tl0.39999999999999997
es0.34210526315789475
reliabletrue
passestrue
13
name"Selvi"
dialogue"हाँ, चीख... बहुत तेज़। मैं डर गई।"
detectedLang"hi"
heavyLang"hi"
scores
hi0.8818432453721938
mr0.8719590268886044
reliabletrue
passestrue
14
name"Hunter"
dialogue"You saw anyone? A face? A vehicle?"
detectedLang"en"
heavyLang"en"
scores
en0.8106060606060606
ro0.6219281663516069
ca0.6183206106870229
fr0.6023856858846919
tl0.574468085106383
pt0.5203836930455635
cs0.5121951219512195
ms0.4490358126721763
hu0.43820224719101125
es0.39759036144578314
sk0.3939393939393939
it0.38461538461538464
yo0.3730407523510972
hr0.358974358974359
pl0.3442622950819672
sl0.3103448275862069
lt0.2907801418439716
tr0.2779783393501805
is0.2727272727272727
da0.2647058823529412
sq0.2647058823529412
az0.25925925925925924
eu0.25925925925925924
lv0.25925925925925924
nl0.25925925925925924
no0.25925925925925924
vi0.25925925925925924
de0.250936329588015
et0.23954372623574144
fi0.23954372623574144
sv0.23954372623574144
reliabletrue
passestrue
15
name"Selvi"
dialogue"छाया जैसा... एक आदमी... और छोटे टायर के निशान। जैसे ट्रॉली।"
detectedLang"hi"
heavyLang"hi"
scores
hi0.8868508813720819
mr0.8799595653272682
reliabletrue
passestrue
16
name"Hunter"
dialogue"Small tracks... a cart. Any truck? License plate?"
detectedLang"en"
heavyLang"en"
scores
en0.7856200527704486
ca0.6575342465753424
it0.5631720430107527
fr0.5602165087956699
no0.5376955903271692
ro0.5357142857142857
tl0.5343839541547278
pt0.5220588235294118
es0.5192307692307693
sk0.4628099173553719
hr0.4347826086956522
de0.41546762589928055
nl0.3890977443609023
cs0.385633270321361
sq0.38446969696969696
pl0.33537832310838445
hu0.32432432432432434
sl0.3143459915611814
da0.30406852248394006
lt0.30257510729613735
sv0.3010752688172043
tr0.29501084598698485
lv0.2903930131004367
et0.27293064876957496
ms0.27293064876957496
yo0.268018018018018
is0.1875
az0.17721518987341772
eu0.17721518987341772
vi0.17721518987341772
fi0.16237113402061853
reliabletrue
passestrue
17
name"Selvi"
dialogue"नहीं दिखा... बस अंधेरा और धुंध। यह निशान देखिए।"
detectedLang"hi"
heavyLang"hi"
scores
hi0.88314344142565
mr0.8680303530188057
reliabletrue
passestrue
18
name"Hunter"
dialogue"Yeah, I see the tracks. Where exactly? By the barn? By the road?"
detectedLang"en"
heavyLang"en"
scores
en0.8067776456599287
da0.5454545454545454
no0.5060790273556232
sv0.49455676516329705
sq0.4715447154471545
tl0.4619205298013245
pl0.42882249560632685
ca0.42781690140845074
cs0.4206773618538324
et0.417562724014337
sk0.3902439024390244
yo0.3737957610789981
it0.37137330754352027
ro0.34077079107505076
fr0.3229166666666667
is0.3010752688172043
hr0.2995689655172413
nl0.20537897310513448
de0.1935483870967742
es0.1935483870967742
ms0.1935483870967742
be0.17721518987341772
tr0.17721518987341772
hu0.1709183673469388
az0.16237113402061853
lt0.16237113402061853
lv0.16237113402061853
uk0.16237113402061853
vi0.16237113402061853
reliabletrue
passestrue
19
name"Selvi"
dialogue"बाग के किनारे, पुराने लाल खलिहान के पास। पुल नहीं... पगडंडी।"
detectedLang"hi"
heavyLang"hi"
scores
hi0.8861505491561746
mr0.8845736013036394
reliabletrue
passestrue
20
name"Hunter"
dialogue"Old red barn. Got it. What time did the scream stop?"
detectedLang"en"
heavyLang"en"
scores
en0.8203592814371257
tl0.6453900709219859
da0.5121951219512195
no0.46714031971580816
yo0.37888198757763975
sv0.375
sq0.35344827586206895
hr0.3464052287581699
lv0.2227979274611399
es0.21875
nl0.21875
pt0.21875
fr0.20634920634920634
ms0.20634920634920634
is0.20424403183023873
sl0.2
reliabletrue
passestrue
21
name"Selvi"
dialogue"कुछ ही पलों में... फिर सब चुप। मैंने कॉल करने की कोशिश की, लेकिन फोन बंद हो गया।"
detectedLang"hi"
heavyLang"hi"
scores
hi0.8881431767337807
mr0.8811838410023763
reliabletrue
passestrue
22
name"Hunter"
dialogue"Your phone died. Anyone else there? Anyone with you?"
detectedLang"en"
heavyLang"en"
scores
en0.8276942355889725
tl0.609375
de0.4791666666666667
ms0.36194895591647336
vi0.32598039215686275
fr0.233983286908078
cs0.22096317280453256
sq0.22096317280453256
da0.21428571428571427
nl0.21428571428571427
reliabletrue
passestrue
23
name"Selvi"
dialogue"नहीं। मैं अकेली थी। मैं बस पढ़ाई के लिए यहाँ आई हूँ... तस्वीरें लेती हूँ।"
detectedLang"hi"
heavyLang"hi"
scores
hi0.8821912428823876
mr0.8720682302771855
reliabletrue
passestrue
24
name"Hunter"
dialogue"Okay. Can you send these photos to me? Email? Text?"
detectedLang"en"
heavyLang"en"
scores
en0.8013447432762836
tl0.5729303547963206
cs0.5276162790697675
sq0.4992295839753467
fr0.45652173913043476
ca0.41016333938294003
sl0.39138576779026213
no0.38095238095238093
lv0.3725868725868726
lt0.36149312377210213
es0.358974358974359
it0.3564356435643564
ms0.34343434343434337
pt0.34077079107505076
nl0.3229166666666667
tr0.3200836820083682
yo0.29653679653679654
pl0.2934782608695652
sk0.28884026258205686
hr0.2630385487528345
da0.24242424242424243
eu0.23349056603773585
et0.2261904761904762
az0.19154228855721395
hi0.19154228855721395
fi0.1875
de0.1792929292929293
reliabletrue
passestrue
25
name"Selvi"
dialogue"मुझे समझ नहीं आया... पर मैं कैमरा संभाल कर रखूँगी। कृपया।"
detectedLang"hi"
heavyLang"hi"
scores
hi0.8822445218103625
mr0.8765564620008587
reliabletrue
passestrue
26
name"Hunter"
dialogue"Keep it safe. Don't delete. I'll find someone who can translate."
detectedLang"en"
heavyLang"en"
scores
en0.803921568627451
ro0.43582510578279265
no0.4261119081779053
pt0.3730407523510972
da0.36507936507936506
sq0.36
es0.35691318327974275
ca0.35379644588045234
tr0.34959349593495936
tl0.3485342019543974
it0.33884297520661155
lv0.2766726943942134
hr0.25650557620817843
az0.2537313432835821
et0.250936329588015
sl0.250936329588015
nl0.24528301886792453
sv0.23954372623574144
vi0.18032786885245902
hu0.17355371900826447
fr0.16666666666666666
yo0.15966386554621848
pl0.14893617021276595
de0.14346895074946467
eu0.14346895074946467
lt0.14346895074946467
sk0.13606911447084233
cs0.12854030501089325
ms0.12854030501089325
reliabletrue
passestrue
27
name"Selvi"
dialogue"मैं सच बोल रही हूँ... मैंने कुछ बुरा देखा।"
detectedLang"hi"
heavyLang"hi"
scores
hi0.8920752389762565
mr0.8870967741935484
reliabletrue
passestrue
28
name"Hunter"
dialogue"I believe you. You're safe."
detectedLang"en"
heavyLang"en"
scores
en0.8097826086956521
sq0.5478036175710594
tr0.5257452574525745
cs0.5111731843575419
tl0.4664634146341463
no0.453125
da0.44267515923566875
hr0.44267515923566875
ca0.44089456869009586
sv0.44089456869009586
ms0.42434210526315785
pl0.4186046511627907
it0.396551724137931
nl0.3613138686131387
ro0.33962264150943394
yo0.3320610687022901
sk0.29149797570850206
be0.2857142857142857
hu0.2768595041322314
az0.2647058823529412
et0.2647058823529412
is0.2647058823529412
lt0.2647058823529412
lv0.2647058823529412
uk0.2647058823529412
vi0.2647058823529412
reliabletrue
passestrue
29
name"Hunter"
dialogue"Hunter."
detectedLang"en"
heavyLang"de"
scores
en0.7797356828193832
de0.6376811594202898
da0.6212121212121212
no0.609375
fr0.5901639344262295
sv0.5833333333333334
tl0.5726495726495726
it0.5575221238938053
nl0.5575221238938053
pt0.5575221238938053
ca0.5412844036697247
ms0.5412844036697247
ro0.5412844036697247
sl0.5412844036697247
sq0.5412844036697247
tr0.5412844036697247
reliablefalse
passestrue
30
name"Hunter"
dialogue"Yeah. Copy. On my way."
detectedLang"en"
heavyLang"en"
scores
en0.7544204322200393
pl0.584717607973422
cs0.5629370629370629
sk0.5629370629370629
tl0.5614035087719298
et0.5519713261648745
fi0.5454545454545454
fr0.4658119658119659
ca0.44196428571428575
hr0.4131455399061033
hi0.40191387559808617
yo0.375
reliabletrue
passestrue
31
name"Hunter"
dialogue"I have to go. Thank you. Keep your camera with you."
detectedLang"en"
heavyLang"en"
scores
en0.8172959805115714
tl0.6453900709219859
da0.5652173913043478
pl0.5515695067264574
cs0.511400651465798
yo0.5008319467554077
it0.47643979057591623
hr0.4594594594594595
no0.45848375451263534
ro0.45255474452554745
ca0.4444444444444444
ms0.4318181818181818
sv0.4230769230769231
vi0.4094488188976378
sk0.40476190476190477
lv0.3814432989690722
lt0.3576017130620985
sq0.3087557603686636
sl0.28741092636579574
es0.24812030075187969
fr0.20212765957446807
nl0.20212765957446807
de0.1935483870967742
be0.1891891891891892
tr0.1891891891891892
hu0.18256130790190736
az0.17355371900826447
et0.17355371900826447
is0.17355371900826447
uk0.17355371900826447
reliabletrue
passestrue
32
name"Selvi"
dialogue"कृपया... कोई मेरी बात समझाए।"
detectedLang"hi"
heavyLang"hi"
scores
hi0.8867497168742922
mr0.8727735368956743
reliabletrue
passestrue
33
name"Hunter"
dialogue"I'll send someone who speaks Hindi. Stay here if you can."
detectedLang"en"
heavyLang"en"
scores
en0.7919143876337693
tl0.5828367103694875
et0.3996569468267582
sq0.3482309124767225
it0.22566371681415928
sv0.2222222222222222
is0.21875
cs0.1822429906542056
es0.1822429906542056
hi0.1822429906542056
pt0.1822429906542056
az0.18032786885245902
ca0.18032786885245902
tr0.18032786885245902
reliabletrue
passestrue
34
name"Selvi"
dialogue"ठीक है... मैं यहीं रहूँगी।"
detectedLang"hi"
heavyLang"hi"
scores
hi0.8893805309734514
mr0.8823836905384214
reliabletrue
passestrue
35
name"Hunter"
dialogue"Thank you, Selvi."
detectedLang"en"
heavyLang"en"
scores
en0.7384937238493724
vi0.5370370370370371
da0.47257383966244726
fi0.46808510638297873
no0.42660550458715596
cs0.3842364532019704
tl0.3842364532019704
ca0.3811881188118812
reliabletrue
passestrue
36
name"Selvi"
dialogue"धन्यवाद।"
detectedLang"mr"
heavyLang"hi"
scores
mr0.868559411146162
hi0.8657357679914071
reliabletrue
passestrue