NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-09-01KK9Q5VJK0F3XSB7NM7DQ0QC6
Run Details
Model:
GPT-5.4 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
32.5s
Cost:
$0.028110
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
99.19%
Dialogue to Total Word Ratio
(details)
99.5966%
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
“Bill, this is low, even for us.” “Low? It’s efficient. Children can’t fence a scooter.” “Molly, focus. Balloons at noon, magician at one, cake chaos at two. We go in during the screaming.” “Which screaming?” “All of it.” “You’ve mapped a birthday party like a bank.” “Banks rarely have pony rides.” “And conscience.” “Conscience never fit in a getaway van.” “What’s the disguise?” “Clown.” “Absolutely not.” “Fine. Harried aunt and disappointed uncle.” “That’s less suspicious?” “Everyone has one.” “What about the dog?” “I brought sausages.” “The last dog followed you home.” “He respected professionalism.” “And the presents?” “Stacked by the fireplace. We sweep, sack, smile, vanish.” “Past twenty sugared children?” “They’ll be hypnotized by the magician pulling scarves from his sleeves.” “If he pulls us from his sleeves, I’m retiring.” Molly peered through the hedge at a sea of paper hats and tiny crowns. “Look, the pirate ship bouncy castle.” “Tempting, Bill. Crime first, bouncing later.” “Agreed. In, out, no lingering near the jelly.” “You always linger near the jelly.” “It’s operational jelly.” “Wait. Why is there a llama?” “Diversion.” “We didn’t bring a llama.” “Exactly. Best kind.” “On three?” “After the birthday song. Nobody notices villains during key changes.”
created_at
"2026-03-09T16:34:10.652Z"
3/9/2026, 4:34:10 PM
model
"openai/gpt-5.4-20260305"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
31668
moderation_latency
(null)
generation_time
32305
tokens_prompt
77
tokens_completion
768
native_tokens_prompt
66
native_tokens_completion
1863
native_tokens_completion_images
0
native_tokens_reasoning
1552
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
0.02811
router
(null)
provider_responses
0
endpoint_id
"9ff5625c-403f-4d7f-b895-58ac7295062c"
id
"resp_03af13f5d52599d10169aef682ba48819390e193cf0fa55c50"
is_byok
false
latency
189
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-1773074050-EgzAOBb0mgMTbWQaUWga"
upstream_id
"resp_03af13f5d52599d10169aef682ba48819390e193cf0fa55c50"
total_cost
0.02811
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
200
99.19%
Dialogue to Total Word Ratio
Ratio: 93.00%, Deviation: 3.00%
neededClean
false
wordsTotal
200
wordsDialogue
186
99.5966%