NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ065V478X6VP8KZYP9KQ344
Run Details
Model:
GPT-OSS 120B
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
36.6s
Cost:
$0.000289
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
99.9993%
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
Under the flickering glow of a rogue streetlamp, Molly slipped a damp newspaper over her face, while Bill adjusted his oversized gloves. The abandoned park bench gave them a temporary sanctuary as the muffled giggles from the neighbor’s yard hinted at the upcoming chaos. A balloon‑laden van was parked crookedly, its side doors ajar, promising a trove of plastic‑wrapped wonders. Molly traced a finger along the dented metal, envisioning the mountain of squeaky toys, crayons, and candy bars awaiting their deft hands. Bill chuckled, his breath forming tiny clouds, and whispered, “We hit the cake table first; the sugar will melt the alarms.” They exchanged a conspiratorial grin, their shadows merging like mischievous twins. A stray cat slinked past, purring like a tiny accomplice, adding rhythm to their heartbeat. “Watch the kids’ parents—door codes change at midnight,” Molly reminded, her eyes narrowing. Their plan unfolded like a kid’s coloring book, each line precise, each color bold. The night grew thicker, the scent of popcorn lingered, and the duo prepared to transform a birthday celebration into a loot‑fest. They packed their backpacks with oversized zip‑ties, a flashlight, and a glitter‑covered map, confident that sunrise would reveal their victorious spoils for everyone.
created_at
"2026-04-24T16:46:41.814Z"
4/24/2026, 4:46:41 PM
model
"openai/gpt-oss-120b"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
237
moderation_latency
(null)
generation_time
36182
tokens_prompt
77
tokens_completion
1638
native_tokens_prompt
114
native_tokens_completion
1497
native_tokens_completion_images
(null)
native_tokens_reasoning
1304
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
0.000288876
router
(null)
provider_responses
0
endpoint_id
"85835306-dba3-4334-87bc-ab9ffa5c9c62"
id
"chatcmpl-RYA3nzYo7E7fqH0xT8f7eZQv"
is_byok
false
latency
135
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-1777049201-aqBrXEltvUGcOUIHU3Jw"
session_id
(null)
api_type
"completions"
id
"gen-1777049201-Lus07SkZtj9mjiEOnB26"
upstream_id
"chatcmpl-RYA3nzYo7E7fqH0xT8f7eZQv"
total_cost
0.000288876
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
201
100.00%
Dialogue to Total Word Ratio
Ratio: 10.45%, Deviation: 0.45%
neededClean
false
wordsTotal
201
wordsDialogue
21
99.9993%