Run: 2026-05-27-01KSMEKK3E85D9F6A5SC0296TC

Run Details

Model:
Skyfall 36B V2
Test:
Language Writing
Scenario:
Character dialogue (Spanish) in a story
Duration:
10.0s
Cost:
$0.000570
Provider:
Parasail

Evaluation summary

Score Evaluator
Details Link
80.00% 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

AI
**Voice Sheet:** 1. *Maria is studying the screen of her camera intently, frowning as if she's trying to make sense of something. She looks up as Hunter approaches her table.* Maria: (in Spanish, softly) ¿Qué problema hay? ¿Ha pasado algo? (What's wrong? Has something happened?) 2. *Hunter scratches his head, realizing Maria doesn't speak English. He pulls out a chair and sits down across from her, getting out his going through his wallet and pulling out a small Spanish phrase book. He finds a page and reads aloud in broken Spanish.* Hunter: (in rough Spanish) Excuse me. I am Detective Hunter. I need help. Perhaps you have seen something. (in English) Damn it. 3. *Maria's eyes grow large, and she starts speaking rapidly in Spanish, gesturing with her hands as she talks. Her words come out shaky and on edge.* Maria: (in Spanish, frantically) No entiendo. Todo está perdido. No sé qué hacer. Estoy asustada. (I don't understand. Everything is lost. I don't know what to do. I'm scared.) 4. *Hunter flips through the phrase book, looking for key phrases. He finds a few and tries to piece together a response.* Hunter: (in rough Spanish) Calma. Estoy aquí para ayudar. ¿Puedes mostrarme lo que viste en la cámara? (Calm down. I'm here to help. Can you show me what you saw on the camera?) 5. *Maria nods and turns the camera around to Hunter. She hits play, and a grainy video begins playing. It shows what appears to be a dark figure dragging someone into an alley. Maria looks at Hunter, her eyes wide and fear etched into her features.* 6. *Hunter's jaw tightens as he watches the video, his gaze hardening. He pulls out his phone and snaps a picture of the video. Then he gets up and starts moving to leave.* Hunter: (in English) I gotta go. Security cameras in the area. Call me. (He jots down his number and pushes the note towards Maria before rushing out of the café) 7. *Maria looks at the number, then at the empty chair where Hunter was sitting. She takes a deep breath and clasps her camera to her chest, looking determined as she takes out her own phone to take a closer look at the video* *Maria mutters something in Spanish to herself, a look of resolve crossing her face as she sets out towards the alley she saw in the video.
created_at"2026-05-27T10:10:13.243Z" 5/27/2026, 10:10:13 AM
model"thedrummer/skyfall-36b-v2"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency225
moderation_latency(null)
generation_time9818
tokens_prompt317
tokens_completion593
native_tokens_prompt269
native_tokens_completion539
native_tokens_completion_images(null)
native_tokens_reasoning0
native_tokens_cached32
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)
usage0.00056955
router(null)
provider_responses
0
endpoint_id"1eb01ded-ae11-49e6-8aa6-3067584070bd"
id"chatcmpl-9df1aacf584f262a"
is_byokfalse
latency225
model_permaslug"thedrummer/skyfall-36b-v2"
provider_name"Parasail"
status200
user_agent"langchainjs-openai/1.0.0 ((node/v24.15.0; linux; x64))"
http_referer(null)
request_id"req-1779876613-1sexhlMxqEf77HtWDdRq"
session_id(null)
api_type"completions"
id"gen-1779876613-8CLaCfSxKC9NBe5a3zLR"
upstream_id"chatcmpl-9df1aacf584f262a"
total_cost0.00056955
cache_discount0.0000096
upstream_inference_cost0
provider_name"Parasail"
response_cache_source_id(null)

Evaluation details

Result Evaluator Details Meta Data
80.00% Parse dialogue n/a
dialogue
0
name"Maria"
dialogue"¿Qué problema hay? ¿Ha pasado algo?"
detectedLang"es"
heavyLang"es"
scores
es0.8173701298701299
pt0.6626686656671664
tl0.6428571428571429
it0.6256239600665559
ca0.6243739565943239
lt0.5960502692998204
ro0.584870848708487
sv0.5302713987473904
no0.5222929936305732
hr0.4863013698630137
pl0.4827586206896552
sq0.471830985915493
hu0.45121951219512196
lv0.44029850746268656
et0.43890274314214467
az0.40476190476190477
da0.3869209809264305
cs0.38524590163934425
vi0.38524590163934425
en0.38016528925619836
nl0.38016528925619836
sk0.3767313019390581
de0.375
fr0.3679775280898876
sl0.358974358974359
tr0.358974358974359
ms0.30124223602484473
eu0.29467084639498436
reliabletrue
passestrue
1
name"Hunter"
dialogue"Excuse me. I am Detective Hunter. I need help. Perhaps you have seen something. Damn it."
detectedLang"en"
heavyLang"en"
scores
en0.7943156320119671
tl0.5291095890410958
ro0.49168207024029575
sq0.4859813084112149
da0.4510978043912176
it0.4393476044852191
pt0.4204425711275026
no0.41737288135593226
ca0.4066882416396979
es0.394273127753304
fr0.39293598233995586
ms0.3707093821510297
de0.3552168815943728
et0.35064935064935066
sv0.3333333333333333
cs0.3167701863354037
nl0.2939666238767651
sl0.2801047120418848
hr0.2724867724867725
fi0.2403314917127072
yo0.2286115007012623
lv0.21316165951359084
tr0.18998527245949925
pl0.1863905325443787
hi0.13657770800627944
sk0.11575562700964631
be0.11290322580645161
hu0.1085899513776337
az0.10277324632952692
is0.10277324632952692
lt0.10277324632952692
uk0.10277324632952692
vi0.10277324632952692
reliabletrue
passestrue
2
name"Maria"
dialogue"No entiendo. Todo está perdido. No sé qué hacer. Estoy asustada."
detectedLang"es"
heavyLang"es"
scores
es0.8106060606060606
pt0.7272727272727273
ca0.6052631578947368
et0.45520581113801456
it0.44512946979038226
fr0.4325346784363178
en0.3023255813953488
no0.27652733118971057
sk0.27184466019417475
tr0.267100977198697
tl0.2598684210526316
lv0.225473321858864
is0.21465968586387435
ms0.1847826086956522
hr0.18330308529945552
fi0.16820702402957485
cs0.16201117318435754
yo0.16044776119402984
lt0.15413533834586465
nl0.14611005692599618
de0.14285714285714285
pl0.14285714285714285
sv0.14285714285714285
sq0.13793103448275862
reliabletrue
passestrue
3
name"Hunter"
dialogue"Calma. Estoy aquí para ayudar. ¿Puedes mostrarme lo que viste en la cámara?"
detectedLang"es"
heavyLang"es"
scores
es0.8079608938547486
ca0.7103738809899948
pt0.6672716273442226
fr0.570647931303669
it0.5624502784407319
no0.46236559139784944
da0.4591937069813176
tr0.439918533604888
tl0.3612078977932636
sq0.3268053855569155
et0.3150684931506849
ro0.2948717948717949
yo0.2939666238767651
nl0.2857142857142857
is0.2724867724867725
vi0.2413793103448276
de0.21540656205420827
sv0.21203438395415475
sl0.20977011494252876
hr0.2005813953488372
lv0.19472913616398244
ms0.14728682170542634
fi0.13249211356466878
cs0.12698412698412698
hu0.12698412698412698
eu0.12
en0.1143317230273752
sk0.1143317230273752
reliabletrue
passesfalse
4
name"Hunter"
dialogue"I gotta go. Security cameras in the area. Call me."
detectedLang"en"
heavyLang"en"
scores
en0.7780596068484464
it0.6679316888045541
tl0.6582031250000001
sv0.5920745920745921
ro0.5823389021479713
nl0.5333333333333334
sq0.5070422535211268
yo0.5063469675599436
no0.48604992657856094
ms0.47761194029850745
pl0.4760479041916168
es0.45054945054945056
fr0.4117647058823529
sl0.40878378378378377
et0.40170940170940167
da0.38271604938271603
ca0.37722419928825623
fi0.3482309124767225
cs0.34210526315789475
hu0.3333333333333333
pt0.31640625
lt0.30966469428007887
lv0.3027888446215139
sk0.2985971943887776
az0.29577464788732394
de0.29577464788732394
hr0.2842535787321063
be0.16666666666666666
tr0.16666666666666666
is0.15254237288135594
uk0.15254237288135594
vi0.15254237288135594
reliabletrue
passestrue