NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ04JHFTE0N8V6HJE75F8Y2A
Run Details
Model:
GPT-OSS 120B
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
46.8s
Cost:
$0.000471
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
93.65%
Matches word count
(details)
99.92%
Dialogue to Total Word Ratio
(details)
96.7855%
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
Under the faded gazebo, the twilight hung like a curtain over the garden. Molly crouched behind a stack of overturned chairs, her sneakers whispering against the grass. Bill hovered near the confectionery table, eyeing the rainbow cupcakes as if they were ransom notes. The air smelled of cotton candy and desperation. A stray balloon bobbed, its string tangled in the fence, marking the only entrance they could use without tripping the motion sensors. Molly checked the flashlight, its beam trembling like a mouse. They both knew the children would be asleep soon, their innocent dreams a cover for a heist. Molly: "We'll slip in through the balloon opening, snatch every present, and vanish." Bill: "The kids' parents will think the toys just vanished like magic in the house." Molly: "I disabled the motion sensor with a magnet, but the alarm still hums." Bill: "Good, we just need a distraction—maybe release the clown balloons." Molly: "I'll rig a ringtone to scare the toddlers, they'll think it's a game." Bill: "Then we grab the sack of gifts and slip out the gate quietly now." Molly: "Speed is key; the party ends at nine, and the police love kids." Bill: "All set, partner. Let's make this the cleanest birthday heist ever."
created_at
"2026-04-24T16:18:40.772Z"
4/24/2026, 4:18:40 PM
model
"openai/gpt-oss-120b"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
232
moderation_latency
(null)
generation_time
46454
tokens_prompt
77
tokens_completion
2569
native_tokens_prompt
114
native_tokens_completion
2458
native_tokens_completion_images
(null)
native_tokens_reasoning
2245
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
0.000471466
router
(null)
provider_responses
0
endpoint_id
"85835306-dba3-4334-87bc-ab9ffa5c9c62"
id
"chatcmpl-R7li8EVjovNSPKNRQYGV10X5"
is_byok
false
latency
79
model_permaslug
"openai/gpt-oss-120b"
provider_name
"DeepInfra"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777047520-3Zw3Ts5EyMGd3uGTmhRv"
session_id
(null)
api_type
"completions"
id
"gen-1777047520-ShA9mzTOr1uvea6O0HWa"
upstream_id
"chatcmpl-R7li8EVjovNSPKNRQYGV10X5"
total_cost
0.000471466
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepInfra"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
93.65%
Matches word count
n/a
neededClean
false
words
209
99.92%
Dialogue to Total Word Ratio
Ratio: 48.33%, Deviation: 1.67%
neededClean
false
wordsTotal
209
wordsDialogue
101
96.7855%