NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ04S2KAA872Q5EHX7GDDFZR
Run Details
Model:
GPT-OSS 120B
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
51.3s
Cost:
$0.001029
Provider:
AtlasCloud
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
100.0000%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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 night before the birthday bash, Molly and Bill crouched behind a line of balloons in the backyard of the house. The lawn was littered with plastic cups, frosting napkins, and a glitter stream that caught the streetlamp’s amber glow. A nervous squirrel darted across the sprinkler, to the heist about to unfold. Molly adjusted the strap of her duffel, feeling the weight of the lock‑picking set inside. Bill checked the battery of his goggles, then whispered a plan to himself. The air smelled of candy and anticipation, a perfect cover for mischief. Molly: "We slip through the pet door at midnight, avoid the glow sticks, and head straight for the gift table." Bill: "Got it. The presents are in a pink tent, right? We need the zip‑line to the side." Molly: "Yes, and the children will be distracted by the magician's rabbit." Bill: "I'll disable the sprinkler alarm with this little EMP widget." Molly: "Make sure the loot bags are big enough for the stuffed unicorns and the giant Lego set." Bill: "After we load everything, we exit through the backyard gate, then blend in with the cleanup crew." Molly: "If anyone asks, we’re just hired entertainers. No jokes."
created_at
"2026-04-24T16:22:14.911Z"
4/24/2026, 4:22:14 PM
model
"openai/gpt-oss-120b"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
517
moderation_latency
(null)
generation_time
51219
tokens_prompt
77
tokens_completion
2653
native_tokens_prompt
127
native_tokens_completion
2541
native_tokens_completion_images
(null)
native_tokens_reasoning
2345
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
0.0010291
router
(null)
provider_responses
0
endpoint_id
"8b516897-c13e-4925-afc3-44fa86608fe9"
id
"81592b411e7947c594226063f59b166b"
is_byok
false
latency
479
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-1777047734-yEVsjrWhgfTNdLlUMZjq"
session_id
(null)
api_type
"completions"
id
"gen-1777047734-EiZIANl4oLhKOdtlKuCv"
upstream_id
"81592b411e7947c594226063f59b166b"
total_cost
0.0010291
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
200
100.00%
Dialogue to Total Word Ratio
Ratio: 50.00%, Deviation: 0.00%
neededClean
false
wordsTotal
200
wordsDialogue
100
100.0000%