Run: 2026-07-25-01KYCYJDHBBY6T46YEKZS29HMV

Run Details

Model:
Thinking Machines Inkling
Test:
Language Writing
Scenario:
Character dialogue (German) in a story
Duration:
35.6s
Cost:
$0.001177
Provider:
DeepInfra

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

Model response

AI
Melanie: "Sie... Sie verschwinden einfach. Ich habe die Fotos gemacht... die Lichter im Wald. Ich zittere... es tut mir leid, mein Englisch... nichts. Nichts." Hunter: "Whoa, slow down. I don't— I don't understand a word of that. German, right? I'm Detective Hunter. I'm asking about the disappearances in Alborn." Melanie: "Die Leute... weg. Angst. Ich habe Angst." Hunter: "Yeah, you're shaking. I can see that. Look, I need to know what you saw near the orchard. Can you... can you show me? On your camera?" Melanie: "Die Kamera... ja. Bilder... von gestern Nacht. Schwarz... alles schwarz." Hunter: "Your camera. Okay. Maybe the pictures tell me something you can't. We can figure this out, just... stay right here." Melanie: "Bitte... nicht alleine lassen. Die Dunkelheit..." Hunter: "I won't— Hunter here. Yeah, I'm on my way out. No, she doesn't speak a lick of English, but she's terrified. I'll update you at the station. Copy that." Hunter: "I've got to take this. Don't move. We'll talk through the photos when I get back."<|end_message|>
created_at"2026-07-25T15:33:45.651Z" 7/25/2026, 3:33:45 PM
model"thinkingmachines/inkling-20260715"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency819
moderation_latency(null)
generation_time35521
tokens_prompt306
tokens_completion267
native_tokens_prompt279
native_tokens_completion261
native_tokens_completion_images(null)
native_tokens_reasoning0
native_tokens_cached192
num_media_prompt(null)
num_input_audio_prompt(null)
num_media_completion0
num_search_results(null)
num_fetches(null)
web_search_engine(null)
origin"https://ncbench.com/"
is_byokfalse
finish_reason"stop"
native_finish_reason"stop"
service_tier(null)
usage0.00117669
router(null)
provider_responses
0
endpoint_id"d6b9d68e-115a-49d7-81cd-1ad1c6942b0e"
id"chatcmpl-R78i89SUZ9dTE4BpOrsfPpYM"
is_byokfalse
latency54
model_permaslug"thinkingmachines/inkling-20260715"
provider_name"DeepInfra"
status200
user_agent"langchainjs-openai/1.0.0 ((node/v24.18.0; linux; x64))"
http_referer(null)
request_id"req-1784993625-3XLuE51LWuiBGvPadvtX"
session_id(null)
preset_id(null)
api_type"completions"
id"gen-1784993625-h5So2iF48onVU4NwCoko"
upstream_id"chatcmpl-R78i89SUZ9dTE4BpOrsfPpYM"
total_cost0.00117669
cache_discount0.00015936
upstream_inference_cost0
provider_name"DeepInfra"
response_cache_source_id(null)
data_region"global"

Evaluation details

Result Evaluator Details Meta Data
100.00% Parse dialogue n/a
dialogue
0
name"Melanie"
dialogue"Sie... Sie verschwinden einfach. Ich habe die Fotos gemacht... die Lichter im Wald. Ich zittere... es tut mir leid, mein Englisch... nichts. Nichts."
detectedLang"de"
heavyLang"de"
scores
de0.8156795281395921
nl0.6717724288840263
es0.36601859678782755
no0.3397887323943662
pl0.33862433862433866
ro0.3237150586113616
da0.3206521739130435
hr0.31255728689275897
ca0.3119266055045872
lt0.293119698397738
en0.29245283018867924
sk0.2809204218600192
sv0.28023032629558536
hu0.2704280155642024
tr0.258893280632411
lv0.25298804780876494
it0.23857868020304565
pt0.21548117154811713
sq0.21218487394957983
is0.19957310565635006
cs0.18211559432933477
sl0.16943521594684383
ms0.16666666666666666
fr0.1601343784994401
az0.1359447004608295
yo0.10501193317422433
eu0.09638554216867469
et0.07749077490774908
reliabletrue
passestrue
1
name"Hunter"
dialogue"Whoa, slow down. I don't— I don't understand a word of that. German, right? I'm Detective Hunter. I'm asking about the disappearances in Alborn."
detectedLang"en"
heavyLang"en"
scores
en0.7973885637100405
tl0.6196111580726965
nl0.5370370370370371
no0.5310057321521626
fr0.504950495049505
ro0.5046780407264722
de0.49748743718592964
sv0.49295774647887325
da0.47976878612716767
it0.46871310507674147
ca0.4538834951456311
pt0.4019933554817276
yo0.3951612903225807
sq0.35988620199146515
es0.34258582907231555
ms0.3298585256887565
cs0.30394431554524365
pl0.30394431554524365
is0.29245283018867924
sl0.2913385826771654
hr0.26108374384236455
sk0.24433249370277077
az0.2417860151642797
tr0.23469387755102045
hu0.1985752448797863
lv0.18699186991869918
lt0.13875598086124402
vi0.1287512100677638
et0.12280701754385964
be0.07216494845360825
eu0.07216494845360825
fi0.06542056074766354
uk0.06542056074766354
reliabletrue
passestrue
2
name"Melanie"
dialogue"Die Leute... weg. Angst. Ich habe Angst."
detectedLang"de"
heavyLang"de"
scores
de0.8366013071895425
nl0.6965098634294385
sk0.38271604938271603
pl0.36507936507936506
ca0.3333333333333333
yo0.3055555555555556
da0.2779783393501805
no0.2779783393501805
reliabletrue
passestrue
3
name"Hunter"
dialogue"Yeah, you're shaking. I can see that. Look, I need to know what you saw near the orchard. Can you... can you show me? On your camera?"
detectedLang"en"
heavyLang"en"
scores
en0.8118123914302258
tl0.6257915947035118
et0.48859166011014943
no0.4804156674660272
fr0.4347826086956522
nl0.4337979094076655
ca0.3902439024390244
ms0.3879472693032015
yo0.38446969696969696
cs0.37439846005774785
sv0.36211972522080466
sq0.3564356435643564
it0.35194416749750745
pl0.34673366834170855
hr0.34541792547834843
da0.3305870236869207
sk0.30032292787944026
ro0.27616926503340755
pt0.26636568848758463
de0.2588369441277081
fi0.2571428571428571
sl0.24330616996507565
es0.236192714453584
lv0.2215568862275449
lt0.20440636474908203
tr0.18444165621079048
az0.17721518987341772
is0.1709183673469388
hi0.11444141689373298
be0.09722222222222222
hu0.09344490934449094
uk0.08835904628330996
vi0.08835904628330996
reliabletrue
passestrue
4
name"Melanie"
dialogue"Die Kamera... ja. Bilder... von gestern Nacht. Schwarz... alles schwarz."
detectedLang"de"
heavyLang"de"
scores
de0.8199711953912625
nl0.6968472109943411
sv0.6161719549641761
no0.5791245791245792
da0.5443499392466585
ca0.5123537061118335
et0.4769874476987448
it0.4588744588744588
fr0.438622754491018
es0.4085173501577287
en0.39710610932475876
sk0.38016528925619836
fi0.37290969899665555
tl0.3686868686868687
tr0.3119266055045872
yo0.3029739776951673
is0.2964352720450282
cs0.29111531190926276
sl0.28435114503816794
ro0.27606177606177607
ms0.2732558139534884
az0.2454728370221328
lv0.23469387755102045
eu0.21548117154811713
pt0.19527896995708155
pl0.1758241758241758
hr0.17035398230088497
sq0.16666666666666666
ru0.1648106904231626
reliabletrue
passestrue
5
name"Hunter"
dialogue"Your camera. Okay. Maybe the pictures tell me something you can't. We can figure this out, just... stay right here."
detectedLang"en"
heavyLang"en"
scores
en0.8101597276774025
tl0.5992260917634052
fr0.4757772957339118
ca0.40960912052117265
ro0.3866328257191201
nl0.3808710503842869
sq0.3572695035460993
no0.3561278863232682
ms0.34977578475336324
es0.32432432432432434
sv0.3153918791312559
it0.2974806201550388
et0.28921568627450983
da0.28781925343811393
de0.28359683794466406
pt0.24479166666666666
yo0.1997792494481236
pl0.12439613526570048
sl0.1082410824108241
lv0.10272277227722773
cs0.09713574097135741
az0.09600997506234414
tr0.09600997506234414
fi0.09375000000000001
reliabletrue
passestrue
6
name"Melanie"
dialogue"Bitte... nicht alleine lassen. Die Dunkelheit..."
detectedLang"de"
heavyLang"de"
scores
de0.8357064622124862
nl0.7014925373134329
no0.5994659546061415
et0.4906621392190153
da0.4800693240901213
sv0.39999999999999997
fr0.38016528925619836
it0.35344827586206895
cs0.25
yo0.22680412371134018
en0.1891891891891892
fi0.1891891891891892
tl0.1891891891891892
reliabletrue
passestrue
7
name"Hunter"
dialogue"I won't— Hunter here. Yeah, I'm on my way out. No, she doesn't speak a lick of English, but she's terrified. I'll update you at the station. Copy that."
detectedLang"en"
heavyLang"en"
scores
en0.7978855721393034
tl0.6161417322834645
no0.5149253731343284
da0.4706840390879479
fr0.45953436807095344
de0.4223933649289099
ro0.40909090909090906
sv0.40548780487804875
yo0.4025735294117647
ca0.3981481481481482
it0.39553626782393053
pl0.3825205826472451
sq0.3729903536977492
hr0.3709677419354838
nl0.36357702349869453
cs0.3560105680317041
sk0.344758064516129
et0.3280496209510682
pt0.29755043227665706
fi0.26636568848758463
tr0.26581325301204817
es0.25799086757990863
ms0.25344563552833077
lv0.2511520737327189
hu0.22680412371134018
sl0.22680412371134018
az0.20988654781199353
is0.18885191347753744
lt0.18410041841004185
hi0.15364583333333331
vi0.12003610108303249
zh0.07319391634980989
be0.06698564593301436
eu0.06698564593301436
uk0.06069364161849711
reliabletrue
passestrue
8
name"Hunter"
dialogue"I've got to take this. Don't move. We'll talk through the photos when I get back."
detectedLang"en"
heavyLang"en"
scores
en0.8211091234347049
tl0.62178517397882
no0.4110718492343934
yo0.3983152827918171
da0.3909866017052376
pl0.3429697766097241
fr0.34210526315789475
lv0.33862433862433866
hr0.33774834437086093
lt0.33065595716198126
cs0.3206521739130435
sv0.30167597765363136
sq0.29775280898876405
ca0.29478138222849076
sk0.28977272727272724
sl0.284692417739628
is0.24585218702865763
nl0.2366412213740458
it0.18699186991869918
ro0.15254237288135594
es0.13793103448275862
pt0.13793103448275862
ms0.13494809688581316
hi0.1334488734835355
de0.1243432574430823
be0.12280701754385964
tr0.12280701754385964
hu0.11816578483245149
az0.11190053285968028
et0.11190053285968028
uk0.11190053285968028
vi0.11190053285968028
reliabletrue
passestrue