NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ04YPZ3B09MZC1JVC8NZZQ3
Run Details
Model:
GPT-OSS 120B
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
1m 9s
Cost:
$0.003688
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
83.65%
Dialogue to Total Word Ratio
(details)
91.8259%
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 slunk over the suburban cul‑de‑sac as Molly and Bill crouched behind a hedge, whispering like conspirators in a cartoon safe‑house. A banner flapped above the clubhouse, reading ‘Happy Birthday Timmy!’, and the scent of frosting drifted like a sugary trap. Molly adjusted her oversized cap, eyeing the inflatable unicorn guarding the entry. Bill checked his pocket‑sized grappling hook, then tapped the map printed on the back of a birthday invitation. Their plan was simple: glide in, swipe every present, vanish before the clown could finish a single balloon twist. "Ready?" Molly whispered. "Always," Bill murmured. "First the cake, then the gifts." "Got it." "Move like ninjas," Molly giggled. "Silence is golden," Bill replied. "Watch the balloon trap." Bill slipped the hook over the fence, a metallic whisper on the grass. Molly spread a blue tarp across the slide, a makeshift shadow for the raid. They slipped toward the gift table, a tower of brightly wrapped boxes under flickering string lights. As a clown honked a squeaky horn, Molly lifted a present, feeling the crinkling paper like a secret. Bill swapped a spider for candy, laughing at kids. Their sack swelled; giggles urged them to finish before the cake burst.
created_at
"2026-04-24T16:25:19.597Z"
4/24/2026, 4:25:19 PM
model
"openai/gpt-oss-120b"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
258
moderation_latency
(null)
generation_time
68765
tokens_prompt
77
tokens_completion
6196
native_tokens_prompt
114
native_tokens_completion
6119
native_tokens_completion_images
(null)
native_tokens_reasoning
5871
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
0.0036885
router
(null)
provider_responses
0
endpoint_id
"38ee5d29-5f91-486e-8485-eaf2408ee328"
id
"chatcmpl-RVwyMgYaUuDk0uZIijhjqBnb"
is_byok
false
latency
74
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-1777047919-nDowUM7SzkHdxqpsEpbg"
session_id
(null)
api_type
"completions"
id
"gen-1777047919-5urRCXEgUEaqpyqxUd61"
upstream_id
"chatcmpl-RVwyMgYaUuDk0uZIijhjqBnb"
total_cost
0.0036885
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepInfra"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
200
83.65%
Dialogue to Total Word Ratio
Ratio: 16.50%, Deviation: 6.50%
neededClean
false
wordsTotal
200
wordsDialogue
33
91.8259%