NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ097ABKSCP6MKEHCCFQD29X
Run Details
Model:
GPT-OSS 120B
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
1m 7s
Cost:
$0.000655
Provider:
Novita
Evaluation summary
Score
Evaluator
Details Link
99.92%
Matches word count
(details)
98.95%
Dialogue to Total Word Ratio
(details)
99.4367%
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
Night cloaked the cul‑de‑sac in fog as Molly and Bill crouched behind a rusted fence. The scent of frosting and balloons drifted from the open back door where a kids’ party roared. Their mission: slip inside, steal every gift, vanish before cake. Molly tested the lock with a cheap pick under a flickering streetlamp. Bill adjusted oversized night‑vision goggles, joking about spy movies. Timing mattered; the parents would be busy with a pop‑music remix. With a silent nod, they slipped gloved hands over the fence, ready to breach the chaotic celebration. They imagined treasure chests hidden beneath colorful wrapping paper. Molly: "I'll disable the speaker before they notice anything." Bill: "Good, then I can swipe the presents while they're dancing." Molly: "Stick to the tables near the cake; that's where the big boxes sit." Bill: "What about the piñata? That’s a mountain of candy." Molly: "We ignore candy—focus on the wrapped gifts." Bill: "Got it. You handle the lock, I handle the distraction." Molly: "If a child spots us, we improvise." Bill: "Improvisation? Like pretending to be a clown?" Molly: "Exactly—balloon animal skills, fast." Bill: "Alright, the clock ticks, let's move." Bill: "We leave no trace, just empty boxes and silence."
created_at
"2026-04-24T17:39:55.922Z"
4/24/2026, 5:39:55 PM
model
"openai/gpt-oss-120b"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
325
moderation_latency
(null)
generation_time
66351
tokens_prompt
77
tokens_completion
2668
native_tokens_prompt
114
native_tokens_completion
2598
native_tokens_completion_images
(null)
native_tokens_reasoning
2333
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
0.0006552
router
(null)
provider_responses
0
endpoint_id
"3dc95f88-3960-4c91-b2bb-bbd2f5069c48"
id
"e19f9139b6fbd867bbe8ba7fa4db9ab0"
is_byok
false
latency
266
model_permaslug
"openai/gpt-oss-120b"
provider_name
"Novita"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777052395-H2z2ItZop1Dgcy3kgKOX"
session_id
(null)
api_type
"completions"
id
"gen-1777052395-1B29N0F9BOUDxHIXvRmc"
upstream_id
"e19f9139b6fbd867bbe8ba7fa4db9ab0"
total_cost
0.0006552
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Novita"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
99.92%
Matches word count
n/a
neededClean
false
words
203
98.95%
Dialogue to Total Word Ratio
Ratio: 46.80%, Deviation: 3.20%
neededClean
false
wordsTotal
203
wordsDialogue
95
99.4367%