NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-06-01KK1HH7DJVETFYSRNG3BNDNB6
Run Details
Model:
GPT-5.4 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
8.6s
Cost:
$0.004620
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
35.00%
Matches word count
(details)
97.17%
Dialogue to Total Word Ratio
(details)
66.0842%
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 garden shed, studying the battlefield of bunting, balloons, and sugar-fueled chaos beyond the fence. A papier-mâché dragon lolled over the gate like a drunk sentry, while inside, a clown in giant shoes lost an argument with a bubble machine. Bill, wedged beside her in a shrub that smelled aggressively of cat, adjusted his flat cap and peered through the leaves at the gift table glittering under a striped gazebo. “Easy pickings,” Molly whispered. “Terrifying pickings,” Bill muttered. Children tore across the lawn with the blind conviction of tiny cavalry. One pirate boy brandished a foam sword at a princess wearing face paint like war stripes. Near the cake, a woman in a sequined sash wrestled party bags into submission, while a magician produced handkerchiefs and the occasional look of private despair. Molly unfolded a crayon-scribbled map. Entry through the side gate, cross behind the Punch and Judy booth, lift the presents, vanish before the candles were lit. Elegant, swift, almost respectable. Bill eyed the clown, now pursuing a runaway sausage dog in a tutu. “If we survive the entertainment, we deserve the loot.” A shriek rose as the dragon split open and showered sweets everywhere. Instantly the lawn dissolved into a stampede. Molly grinned. Chaos, she believed, was simply opportunity wearing a party hat.
created_at
"2026-03-06T12:21:36.314Z"
3/6/2026, 12:21:36 PM
model
"openai/gpt-5.4-20260305"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
385
moderation_latency
(null)
generation_time
8509
tokens_prompt
77
tokens_completion
358
native_tokens_prompt
66
native_tokens_completion
297
native_tokens_completion_images
0
native_tokens_reasoning
0
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
0.00462
router
(null)
provider_responses
0
endpoint_id
"9ff5625c-403f-4d7f-b895-58ac7295062c"
id
"resp_0b007556781394620169aac6d060e48197bf2f187a466940db"
is_byok
false
latency
148
model_permaslug
"openai/gpt-5.4-20260305"
provider_name
"OpenAI"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.0; linux; x64))"
http_referer
(null)
api_type
"completions"
id
"gen-1772799696-HOaaXicASz9gEAHGNXue"
upstream_id
"resp_0b007556781394620169aac6d060e48197bf2f187a466940db"
total_cost
0.00462
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
35.00%
Matches word count
n/a
neededClean
false
words
218
97.17%
Dialogue to Total Word Ratio
Ratio: 5.88%, Deviation: 4.12%
neededClean
false
wordsTotal
221
wordsDialogue
13
66.0842%