NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM0944KPEV21FH7XP5KECD28
Run Details
Model:
GPT-5.4 Mini (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
2.8s
Cost:
$0.001786
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
60.28%
Matches word count
(details)
76.33%
Dialogue to Total Word Ratio
(details)
68.3016%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% 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, tell me again why the target is a children’s party,” Bill whispered, tugging at his gloves. “Because, Bill, every child in the neighborhood will be busy doing the Macarena, eating frosting, and screaming at a clown.” “Comforting.” “And because presents are portable.” “Morally, this is a low point for us.” “Bill, we are thieves. Our moral compass is a decorative item.” “You say that like it helps.” “It does. Less guilt, more stealing.” “Before I agree to anything, I need to know the plan.” “The plan is simple.” “Oh, good. I hate those.” “We stroll in, blend in, admire the balloons, and wait for the gift mountain to become emotionally vulnerable.” “‘Emotionally vulnerable’?” “Yes. Then we scoop up the presents and vanish like responsible adults avoiding a dentist appointment.” “Do we have disguises?” “Of course.” “Please tell me you didn’t buy clown noses again.” “I bought subtle clown noses.” “That’s not a thing.” “It is if you believe in yourself.” “Who are we supposed to be?” “Uncle Bill and Aunt Molly, relatives no one trusts but everyone feeds.” “I do have the face for it.” “You have the face for crime, Bill.” “That’s the nicest thing anyone’s ever said to me.” “Stop blushing and pass me the fake mustache. We’re making history, preferably quietly.”
created_at
"2026-03-18T10:51:06.243Z"
3/18/2026, 10:51:06 AM
model
"openai/gpt-5.4-mini-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1354
moderation_latency
(null)
generation_time
2696
tokens_prompt
77
tokens_completion
409
native_tokens_prompt
66
native_tokens_completion
386
native_tokens_completion_images
0
native_tokens_reasoning
86
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
0.0017865
router
(null)
provider_responses
0
endpoint_id
"9ee065b2-3d1c-43bc-bdd7-28af3b148282"
id
"resp_0f911b4356e571620169ba839a4dac81939579e0d5f7497dd6"
is_byok
false
latency
216
model_permaslug
"openai/gpt-5.4-mini-20260317"
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-1773831066-cy0f2FdcmPKBcVr8Ukxd"
upstream_id
"resp_0f911b4356e571620169ba839a4dac81939579e0d5f7497dd6"
total_cost
0.0017865
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
60.28%
Matches word count
n/a
neededClean
false
words
215
76.33%
Dialogue to Total Word Ratio
Ratio: 97.21%, Deviation: 7.21%
neededClean
false
wordsTotal
215
wordsDialogue
209
68.3016%