NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ08AB3GCSRM1VMM8JR3MRBC
Run Details
Model:
GPT-OSS 120B
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
2m 21s
Cost:
$0.000937
Provider:
AtlasCloud
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
49.9995%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% words of dialogue between two thieves named Molly and Bill who are planning to break into a children's party to steal all the presents. Only include the prose of the scene without any markdown or commentary.
Model response
Messages
Meta
AI
The kitchen smelled of stale pizza and crushed balloons, a reminder that the neighborhood kids were already in the backyard for the dreaded “Pirates and Princesses” party. Molly lounged on a dented recliner, her trench‑coat flapping like a flag of mischief, while Bill fiddled with a glittery party‑horn that squeaked louder than his conscience. “We need a plan that outruns the chaos of sugar‑high kids,” Molly whispered, tapping her finger against the invisible countdown on her wristwatch. Bill whispered, “We grab the gifts, slip out, and vanish forever.” He scanned the yard, noting the oversized piñata perched atop a table like a sugary treasure chest. The host, a plump aunt in glitter, was busy coaxing toddlers into a “dragon’s den” made of cardboard. Molly muttered, “We need a distraction that sounds like a birthday cake collapse; otherwise the kids will sniff out our footprints faster than a sugar‑rush sprint.” Bill grinned, “I’ve got a whoopee cushion rigged to explode with confetti; that’ll buy us a few seconds.” They slipped into the shadows, rehearsing their synchronized shuffle, and imagined the gleam of stolen plush bears, tiny toy swords, and endless ribbons glittering under the moonlit garden lights. Mission almost complete.
created_at
"2026-04-24T17:25:59.096Z"
4/24/2026, 5:25:59 PM
model
"openai/gpt-oss-120b"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
461
moderation_latency
(null)
generation_time
28270
tokens_prompt
77
tokens_completion
2353
native_tokens_prompt
127
native_tokens_completion
2310
native_tokens_completion_images
(null)
native_tokens_reasoning
2024
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
"stop"
usage
0.0009367
router
(null)
provider_responses
0
endpoint_id
"8b516897-c13e-4925-afc3-44fa86608fe9"
id
"b0431e89c26541248f0183490201d2f6"
is_byok
false
latency
432
model_permaslug
"openai/gpt-oss-120b"
provider_name
"AtlasCloud"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777051559-O4zeq3yLIE4u5cqWWHF2"
session_id
(null)
api_type
"completions"
id
"gen-1777051559-vyZi7kgknztGLi8iTXME"
upstream_id
"b0431e89c26541248f0183490201d2f6"
total_cost
0.0009367
cache_discount
(null)
upstream_inference_cost
0
provider_name
"AtlasCloud"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
199
0.00%
Dialogue to Total Word Ratio
Ratio: 32.66%, Deviation: 22.66%
neededClean
false
wordsTotal
199
wordsDialogue
65
49.9995%