NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHK95SHKS64JNEF4S9WMNARX
Run Details
Model:
GPT-5.1
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
1m
Cost:
$0.024993
Provider:
OpenAI
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 adjusted the cartoon dinosaur mask over her black turtleneck and peered through the hedge at the chaos of balloons and frosting. Children swarmed the yard like sugar-high piranhas, shrieking around the mountainous gift table. A magician in a crooked top hat battled an overinflated unicorn balloon, losing. The parents clustered near the grill, distracted by smoke and arguments about gluten. Perfect cover. Bill’s stolen minivan idled at the curb, its “Princess Party Planner” magnet slightly crooked. In the back, a laundry basket waited for loot, lined with innocent duckling wrapping paper. Molly inhaled, tasting sugar, fear, and absurd ambition. "Bill, we're about to rob a bouncy castle, not Fort Knox; try to look less like a getaway driver and more like a disappointed uncle who forgot the batteries. Also, if anyone asks, your name is Sparkles, and you absolutely do not know how that piñata caught fire today anyway." "Sparkles is a strong criminal alias, thank you very much; kids trust clowns. Besides, your plan involves crawling through a ball pit ventilation duct; statistically, that's where childhood nightmares and old French fries go to die, not exactly a route optimized for stealth or personal dignity in my professional opinion."
created_at
"2026-02-16T13:11:29.862075+00:00"
2/16/2026, 1:11:29 PM
model
"openai/gpt-5.1-20251113"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
7072
moderation_latency
(null)
generation_time
59108
tokens_prompt
77
tokens_completion
1509
native_tokens_prompt
66
native_tokens_completion
2491
native_tokens_completion_images
0
native_tokens_reasoning
2225
native_tokens_cached
0
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"completed"
usage
0.0249925
router
(null)
provider_responses
0
id
"resp_092a475609b9a7610169931745ad788195b909e50e1880a384"
status
200
is_byok
false
latency
192
endpoint_id
"764eb97f-8bab-4326-b29b-7a8799b00a70"
provider_name
"OpenAI"
model_permaslug
"openai/gpt-5.1-20251113"
api_type
"completions"
id
"gen-1771247429-LyuiXF3WV263dNOIt9kF"
upstream_id
"resp_092a475609b9a7610169931745ad788195b909e50e1880a384"
total_cost
0.0249925
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
99.9990%
Matches word count
n/a
neededClean
false
words
201
99.9761%
Dialogue to Total Word Ratio
Ratio: 51.24%, Deviation: 1.24%
neededClean
false
wordsTotal
201
wordsDialogue
103
99.9875%