NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ08GHDTF2Q74J0JYF87YEVZ
Run Details
Model:
GPT-OSS 120B
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
3m 11s
Cost:
$0.001079
Provider:
SiliconFlow
Evaluation summary
Score
Evaluator
Details Link
99.98%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
99.9917%
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 warehouse smelled of stale pizza and cheap cologne, the perfect hideout for two professional party raiders. Molly perched on a rusty ladder, scanning the flickering fluorescent lights while Bill fiddled with a ten‑second timer on a flashbang. They'd heard the birthday boy's dad brag about a mountain of Toys‑R‑Us boxes, a trophy case of candy, and a secret stash of chocolate‑covered strawberries. The plan was simple: slip through the service door, distract the clown with a fake balloon animal, and loot the room before the parents noticed the missing glitter. The clock ticked; the party was minutes away now. "We hit the cake table first, grab the big ones before the kids even see." "And the piñata—full of candy—got to be our last target, it's a goldmine." "I'll plant the smoke bomb by the inflatable tunnel; you distract the clown with the squeaky duck." "Deal, but watch the security camera; I saw a guard in the hallway, green uniform." "No worries, I have the remote jammer; once I flip it, the feeds go static and we slip out with the loot." "Then we split the bounty, each taking half the toys and the chocolate strawberries for a sweet celebration."
created_at
"2026-04-24T17:27:29.475Z"
4/24/2026, 5:27:29 PM
model
"openai/gpt-oss-120b"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3280
moderation_latency
(null)
generation_time
190563
tokens_prompt
77
tokens_completion
2498
native_tokens_prompt
127
native_tokens_completion
2383
native_tokens_completion_images
(null)
native_tokens_reasoning
2126
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
0.0010787
router
(null)
provider_responses
0
endpoint_id
"ce118593-d9b2-4d2d-bcd4-33f0609b42f1"
id
"019dc08849195f513835dba3691af79f"
is_byok
false
latency
3106
model_permaslug
"openai/gpt-oss-120b"
provider_name
"SiliconFlow"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777051649-L10bu2ePAkA9yMmYiFXb"
session_id
(null)
api_type
"completions"
id
"gen-1777051649-RQU5uMbZ7bBgdVzHzxpC"
upstream_id
"019dc08849195f513835dba3691af79f"
total_cost
0.0010787
cache_discount
(null)
upstream_inference_cost
0
provider_name
"SiliconFlow"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
99.98%
Matches word count
n/a
neededClean
false
words
202
100.00%
Dialogue to Total Word Ratio
Ratio: 50.50%, Deviation: 0.50%
neededClean
false
wordsTotal
202
wordsDialogue
102
99.9917%