NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ07HXF1JNBCKCAH8DWC1FEQ
Run Details
Model:
GPT-OSS 120B
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
1m 49s
Cost:
$0.000941
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
41.24%
Dialogue to Total Word Ratio
(details)
70.6179%
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
Molly slipped the flash drive into her pocket, her eyes scanning the backyard. The kids’ bounce house loomed like a neon castle, and a mountain of wrapped gifts glittered under the string lights. Bill crouched behind the garden gnome, checking the lock on the candy table. He whispered, “The alarm’s set to twenty‑second snooze, we’ve got just enough time.” Molly smirked, “Great, I brought the vacuum. We’ll suck them out like a carpet cleaning marathon.” He lifted his climbing gloves, “First we disable the motion sensor—tap‑tap, and it’s blind.” She replied, “Then I’ll swing in through the inflatable tunnel, grab the biggest pile, and hand it to you.” Bill nodded, “Watch out for the clown, he’s armed with a squeaky horn.” Molly giggled, “If he squeaks, we’ll just pretend we’re part of the party entertainment.” Bill checked his watch, “Midnight in five, we hit the gift mountain.” Molly counted the red ribbons, “Twenty‑seven presents, three oversized plushies, and the golden trophy.” Bill whispered, “The door’s ajar, just wait for the clown’s cue.” A distant dog barked. They exchanged a conspiratorial grin, then slipped into the shadows as the party music swelled. Moonlight reflected off the frosting, painting shadows on lawn.
created_at
"2026-04-24T17:10:45.996Z"
4/24/2026, 5:10:45 PM
model
"openai/gpt-oss-120b"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
609
moderation_latency
(null)
generation_time
108385
tokens_prompt
77
tokens_completion
4927
native_tokens_prompt
114
native_tokens_completion
4931
native_tokens_completion_images
(null)
native_tokens_reasoning
4591
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
0.000941336
router
(null)
provider_responses
0
endpoint_id
"85835306-dba3-4334-87bc-ab9ffa5c9c62"
id
"chatcmpl-RY2AgLX7beHGE15DVEj2r0ZM"
is_byok
false
latency
420
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-1777050645-Mi5HhZozHBldFdGnpjeL"
session_id
(null)
api_type
"completions"
id
"gen-1777050645-tag7MiafnAjP6UJpWkR7"
upstream_id
"chatcmpl-RY2AgLX7beHGE15DVEj2r0ZM"
total_cost
0.000941336
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
41.24%
Dialogue to Total Word Ratio
Ratio: 59.70%, Deviation: 9.70%
neededClean
false
wordsTotal
201
wordsDialogue
120
70.6179%