NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ072T0V6ANB6ZD2VJZGV0MG
Run Details
Model:
GPT-OSS 120B
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
1m 27s
Cost:
$0.000763
Provider:
DeepInfra
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
Molly crouched behind the inflatable dinosaur, eyes scanning the chaos of streamers and toddlers. Bill slunk beside the punch bowl, licking a marshmallow off his sleeve. The party was a neon circus of plastic swords, balloon animals, and a dense fog of birthday cake frosting that clung to the air like a sugary mist. Their target: wrapped presents beside the clown’s scooter, each humming with cash‑filled wallets inside. The twins of mischief exchanged glances, knowing the other's patience was as thin as paper crowns. Molly’s mind ticked like a metronome, plotting entry points, exit routes, and the moment parents would be distracted by the magician. Bill rehearsed his hand‑over‑hand sleight, ready to swap a plastic dinosaur for a gift‑bag without raising a child's eyebrow. "Snatch the piñata, then the gifts, and ditch the cake," Molly hissed. "We'll hide behind balloons, grab everything, and vanish like ninjas," Bill whispered. A giggle echoed from the corner where a clown pretended to juggle rubber chickens, oblivious to the impending heist. The thieves slipped forward, shoes squeaking in rhythm with the birthday anthem, ready to turn a child's celebration into a loot‑filled triumph. They vanished into the night, pockets bulging with stolen joy, gleefully.
created_at
"2026-04-24T17:02:30.954Z"
4/24/2026, 5:02:30 PM
model
"openai/gpt-oss-120b"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
246
moderation_latency
(null)
generation_time
86758
tokens_prompt
77
tokens_completion
4268
native_tokens_prompt
114
native_tokens_completion
3990
native_tokens_completion_images
(null)
native_tokens_reasoning
3936
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
0.000762546
router
(null)
provider_responses
0
endpoint_id
"85835306-dba3-4334-87bc-ab9ffa5c9c62"
id
"chatcmpl-RIb0CMVHOIwaHLounLpxYVUu"
is_byok
false
latency
82
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-1777050150-tUXdHDDrCuWv8mQNcbEp"
session_id
(null)
api_type
"completions"
id
"gen-1777050150-dyRzCD8OrKzoTZVAIgM0"
upstream_id
"chatcmpl-RIb0CMVHOIwaHLounLpxYVUu"
total_cost
0.000762546
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
100.00%
Dialogue to Total Word Ratio
Ratio: 10.00%, Deviation: 0.00%
neededClean
false
wordsTotal
200
wordsDialogue
20
100.0000%