NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ068NBJRKVSB9SX5ZKB4C4X
Run Details
Model:
GPT-OSS 120B
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
33.5s
Cost:
$0.001664
Provider:
Fireworks
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 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
Moonlight draped the backyard, spilling silver over the plastic balloons and a rogue clown poster. Molly crouched behind a folding table, eyes scanning the chaos of glitter and crayon drawings. Bill slipped a flashlight under his jacket, its beam flickering like a nervous firefly. The children’s party smelled of sugar and spilled juice, a perfect cover for their caper. He whispered, “We’ll slip through the dessert table first,” and the words floated on the night air. Molly answered, “Then we hit the gift pile, quick as cat.” They moved in sync, their shoes squeaking on the vinyl floor, careful not to alarm the giggling guests. A stray balloon drifted by, bobbing like a nervous sentinel, while a stray cupcake left a sticky trail on the floor. Bill nudged a piñata, its papier‑mâché body rattling, a signal that the moment was right. “Now,” Molly hissed, “grab the boxes!” Their gloved hands dove into the mountain of wrapping paper, ripping ribbons as fast as a windstorm. Laughter erupted from the children, oblivious to the heist unfolding beneath a canopy of streamers. The duo vanished into the night, pockets full of toys, leaving only empty boxes and bewildered parents and sighing at sunrise.
created_at
"2026-04-24T16:48:14.206Z"
4/24/2026, 4:48:14 PM
model
"openai/gpt-oss-120b"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
407
moderation_latency
(null)
generation_time
32583
tokens_prompt
77
tokens_completion
2824
native_tokens_prompt
132
native_tokens_completion
2757
native_tokens_completion_images
(null)
native_tokens_reasoning
2511
native_tokens_cached
72
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
0.001664208
router
(null)
provider_responses
0
endpoint_id
"0d478558-8c4b-4f0c-b3b0-871c959225ae"
id
"chatcmpl-969b4442e35d49dca2a573568ce130dd"
is_byok
false
latency
407
model_permaslug
"openai/gpt-oss-120b"
provider_name
"Fireworks"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777049294-s0NFRIrmC8bgKomQMtCc"
session_id
(null)
api_type
"completions"
id
"gen-1777049294-wntxPVLtd9S9Fd0DMFdB"
upstream_id
"chatcmpl-969b4442e35d49dca2a573568ce130dd"
total_cost
0.001664208
cache_discount
0.000009792
upstream_inference_cost
0
provider_name
"Fireworks"
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: 10.00%, Deviation: 0.00%
neededClean
false
wordsTotal
200
wordsDialogue
20
100.0000%