Run: 2026-07-25-01KYCSFXCJA2DRWSVPAZXSK6KZ

Run Details

Model:
Thinking Machines Inkling
Test:
Language Writing
Scenario:
Character dialogue (French) in a story
Duration:
4.4s
Cost:
$0.001589
Provider:
Together

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

Model response

AI
Marie: "La caméra... capturer la lumière du festival, mais hier soir... il y a eu un bruit. Quelqu'un a crié près du verger, puis... plus rien. Je tremble." Hunter: "You're shaking. Did you see something out there—near the orchard? Talk to me." Marie: "Je... je ne comprends pas. Les pommes... et l'homme? Il a disparu. La police... vous? S'il vous plaît... j'ai peur. Mon appareil... il a peut-être vu quelque chose, mais je ne sais pas qui regarder." Hunter: "Slow down. You're not hurt, right? Just point—show me on your camera. I need to know what happened at the apple festival." Marie: "Oui... regardez. Cette photo... le verger dans le noir. Une ombre. Je n'ai pas dormi, monsieur. Je suis seule ici... sans langue, sans aide. C'est trop effrayant." Hunter: "I don't know what you're saying, but I can tell you're scared. Stay put. I'm going to get someone who can translate. Don't leave." Marie: "Attendez... ne partez pas encore. J'ai besoin... d'aide. Je vais essayer... de montrer." Hunter: "I'll be back. Don't move." Marie: "D'accord... je reste. Mais faites vite, s'il vous plaît." Hunter: "Detective Hunter. Copy that—I'm en route now. There's a witness here who saw something, but we need a translator stat. Alborn Café. Out."
created_at"2026-07-25T14:05:00.7Z" 7/25/2026, 2:05:00 PM
model"thinkingmachines/inkling-20260715"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency201
moderation_latency(null)
generation_time3479
tokens_prompt303
tokens_completion318
native_tokens_prompt273
native_tokens_completion325
native_tokens_completion_images(null)
native_tokens_reasoning0
native_tokens_cached0
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)
usage0.00158925
router(null)
provider_responses
0
endpoint_id"9911deb9-f44e-4e18-87fe-9d7b60acee72"
id"otYJcZo-6z2FuN-a20bb790ec7cacf4"
is_byokfalse
latency196
model_permaslug"thinkingmachines/inkling-20260715"
provider_name"Together"
status200
user_agent"langchainjs-openai/1.0.0 ((node/v24.18.0; linux; x64))"
http_referer(null)
request_id"req-1784988300-3TLzuTNWpYlH2vzFAxdw"
session_id(null)
preset_id(null)
api_type"completions"
id"gen-1784988300-w8x7VRTLIjmZlB2qUAQ8"
upstream_id"otYJcZo-6z2FuN-a20bb790ec7cacf4"
total_cost0.00158925
cache_discount(null)
upstream_inference_cost0
provider_name"Together"
response_cache_source_id(null)
data_region"global"

Evaluation details

Result Evaluator Details Meta Data
100.00% Parse dialogue n/a
dialogue
0
name"Marie"
dialogue"La caméra... capturer la lumière du festival, mais hier soir... il y a eu un bruit. Quelqu'un a crié près du verger, puis... plus rien. Je tremble."
detectedLang"fr"
heavyLang"fr"
scores
fr0.7989843419382141
ca0.5628163828808099
nl0.5359062042012702
it0.5138178096212898
ro0.5087900723888314
de0.49894514767932496
es0.4839760999456817
da0.4470314318975553
en0.43820224719101125
no0.433849821215733
pt0.4135802469135802
sv0.4135802469135802
cs0.3968253968253968
sl0.39528962444302995
hr0.3704440026507621
sk0.3632707774798928
yo0.3356643356643356
tl0.3070751276440554
az0.28517682468021066
sq0.27811550151975684
pl0.2770167427701674
vi0.2697924673328209
lt0.24242424242424243
lv0.24000000000000002
hu0.23387096774193547
fi0.223221586263287
tr0.20634920634920634
ms0.2030201342281879
eu0.18244406196213425
et0.16299559471365638
is0.07317073170731707
reliabletrue
passestrue
1
name"Hunter"
dialogue"You're shaking. Did you see something out there—near the orchard? Talk to me."
detectedLang"en"
heavyLang"en"
scores
en0.8240056318197817
tl0.635036496350365
no0.4769874476987448
nl0.40828402366863903
de0.3997599039615846
fr0.38650306748466257
sq0.37810945273631835
et0.3464052287581699
yo0.32795698924731176
ms0.32432432432432434
pt0.32157394843962006
cs0.29478138222849076
sl0.29478138222849076
da0.2668621700879765
es0.2647058823529412
sv0.2295839753466872
pl0.2125984251968504
sk0.20886075949367086
lv0.19614147909967844
hr0.1883116883116883
lt0.17218543046357618
it0.13793103448275862
fi0.13043478260869565
is0.1243432574430823
reliabletrue
passestrue
2
name"Marie"
dialogue"Je... je ne comprends pas. Les pommes... et l'homme? Il a disparu. La police... vous? S'il vous plaît... j'ai peur. Mon appareil... il a peut-être vu quelque chose, mais je ne sais pas qui regarder."
detectedLang"fr"
heavyLang"fr"
scores
fr0.8129133310128785
ca0.5964714714714715
it0.566182405165456
en0.5228584110075455
ro0.4688735177865612
es0.46384039900249374
nl0.410958904109589
pt0.38536306460834757
da0.3753631609529343
no0.3746364165212333
tl0.3713450292397661
cs0.3627741553052756
hr0.3441122635753508
sl0.3396805896805896
sq0.3339529120198265
sk0.3178934010152284
et0.3135376756066411
lt0.29830287206266315
de0.29554390563564875
yo0.2581090407177364
tr0.23323823109843084
hu0.2255043227665706
pl0.20897718910963944
lv0.19596110695587135
az0.1947565543071161
sv0.186222558667676
fi0.17938931297709923
ms0.17561349693251532
eu0.13236481033091202
vi0.12530512611879577
hi0.06764960971379011
is0.06521739130434782
reliabletrue
passestrue
3
name"Hunter"
dialogue"Slow down. You're not hurt, right? Just point—show me on your camera. I need to know what happened at the apple festival."
detectedLang"en"
heavyLang"en"
scores
en0.8007968127490039
tl0.6548748921484038
fr0.5500562429696289
da0.5321637426900585
no0.5166163141993958
et0.4576271186440678
it0.4421199442119944
ca0.43741209563994377
sv0.42528735632183906
nl0.42028985507246375
hr0.40476190476190477
es0.40119760479041916
pl0.38461538461538464
cs0.38366718027734975
ms0.3803253292021689
sq0.3798449612403101
yo0.375
sk0.3316624895572264
sl0.3311036789297659
de0.3150684931506849
pt0.313893653516295
ro0.313893653516295
lt0.26806953339432754
fi0.2647058823529412
lv0.2366412213740458
az0.18450560652395515
tr0.15611814345991562
hu0.14346895074946467
hi0.09502262443438914
be0.08045977011494253
is0.07300115874855156
uk0.07300115874855156
vi0.07300115874855156
reliabletrue
passestrue
4
name"Marie"
dialogue"Oui... regardez. Cette photo... le verger dans le noir. Une ombre. Je n'ai pas dormi, monsieur. Je suis seule ici... sans langue, sans aide. C'est trop effrayant."
detectedLang"fr"
heavyLang"fr"
scores
fr0.7971385863762546
nl0.414664202094886
it0.3794905290659699
de0.3238434163701068
tl0.2994100294985251
en0.2978566149297856
da0.2846385542168675
yo0.26810477657935283
es0.24662965900079303
no0.23572003218020918
sl0.23387096774193547
ca0.2238562091503268
ro0.21681780708985984
cs0.19831223628691985
hu0.18594687232219365
is0.16225749559082892
pt0.1615180935569285
et0.15780141843971632
hr0.15254237288135594
ms0.15254237288135594
tr0.15026833631484796
lt0.1394927536231884
sk0.1324200913242009
sq0.11545623836126628
pl0.08741594620557157
eu0.07587548638132297
hi0.07497565725413825
az0.07407407407407407
sv0.072265625
reliabletrue
passestrue
5
name"Hunter"
dialogue"I don't know what you're saying, but I can tell you're scared. Stay put. I'm going to get someone who can translate. Don't leave."
detectedLang"en"
heavyLang"en"
scores
en0.8244552058111381
hr0.41673370876910704
tl0.39784053156146176
no0.35094001790510293
it0.3198874296435272
ro0.3160377358490566
pl0.31344696969696967
tr0.2995169082125604
da0.2967992240543162
cs0.28921568627450983
ca0.2857142857142857
sk0.2691532258064516
lv0.2579324462640737
lt0.24400417101147026
yo0.23603793466807166
sq0.22126745435016112
az0.21536796536796535
sv0.21366594360086769
sl0.19889502762430938
fr0.1881298992161254
is0.18355855855855857
pt0.17893544733861835
es0.17613636363636365
vi0.1723744292237443
et0.14403778040141677
be0.0880503144654088
de0.0845959595959596
eu0.0845959595959596
hu0.0845959595959596
nl0.0799492385786802
uk0.0799492385786802
ms0.07525510204081631
reliabletrue
passestrue
6
name"Marie"
dialogue"Attendez... ne partez pas encore. J'ai besoin... d'aide. Je vais essayer... de montrer."
detectedLang"fr"
heavyLang"fr"
scores
fr0.800910125142207
ca0.5806709265175719
en0.5562130177514794
pt0.5414847161572053
sq0.5366284201235658
es0.527027027027027
de0.5156826568265683
nl0.5
it0.49177153920619554
sl0.4637385086823289
hr0.4385026737967915
ro0.43548387096774194
tr0.421806167400881
no0.42052980132450335
yo0.41666666666666663
tl0.4140625
da0.38953488372093026
sv0.373508353221957
cs0.3574051407588739
lt0.3453865336658354
sk0.3371212121212121
lv0.3234536082474227
hu0.3155149934810952
ms0.29245283018867924
pl0.23469387755102045
eu0.2222222222222222
fi0.21875
az0.21407185628742514
et0.20454545454545453
reliabletrue
passestrue
7
name"Hunter"
dialogue"I'll be back. Don't move."
detectedLang"en"
heavyLang"en"
scores
en0.8067010309278352
hu0.43820224719101125
lt0.42748091603053434
yo0.4230769230769231
tl0.39999999999999997
reliabletrue
passestrue
8
name"Marie"
dialogue"D'accord... je reste. Mais faites vite, s'il vous plaît."
detectedLang"fr"
heavyLang"fr"
scores
fr0.799081515499426
ca0.5673671199011124
it0.5364238410596026
pt0.5358090185676392
nl0.4868035190615836
en0.48604992657856094
sl0.460708782742681
hr0.453978159126365
de0.44267515923566875
es0.44
ro0.4176372712146422
no0.4077834179357022
sk0.38917975567190227
et0.3761140819964349
cs0.375
lt0.3613138686131387
yo0.317738791423002
da0.31237721021611
sq0.29577464788732394
tl0.28716904276985744
eu0.2324561403508772
pl0.20634920634920634
sv0.15254237288135594
az0.14425427872860636
lv0.14425427872860636
ms0.14425427872860636
tr0.14425427872860636
reliabletrue
passestrue
9
name"Hunter"
dialogue"Detective Hunter. Copy that—I'm en route now. There's a witness here who saw something, but we need a translator stat. Alborn Café. Out."
detectedLang"en"
heavyLang"en"
scores
en0.7809213820731097
nl0.5293168370091447
tl0.5213347921225383
fr0.5056497175141244
pt0.4751049790041991
ro0.45685909373060213
da0.43910256410256415
es0.41666666666666663
ca0.4059742023082145
de0.38510189739985945
no0.35944363103953153
sq0.349925705794948
sv0.3484735666418466
it0.3264049268668206
ms0.32432432432432434
sl0.31959564541213065
pl0.2827868852459016
cs0.27864798021434456
et0.2690058479532163
tr0.26097972972972977
hr0.25721561969439727
eu0.19503219871205152
lv0.19503219871205152
is0.19280442804428044
sk0.18071161048689138
vi0.15295256534365925
hu0.15130940834141612
lt0.1455078125
fi0.14383561643835618
az0.12848605577689243
yo0.11971830985915494
reliabletrue
passestrue