NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-09-01KK9QERN6Y67ZDXVH74F53ZAG
Run Details
Model:
GPT-5.4 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
52.3s
Cost:
$0.046635
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
100.0000%
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
Bill and Molly crouched behind a hedge shaped like a surprised rabbit, studying the garden beyond. Paper lanterns bobbed over a pink castle bouncy house, while parents drifted around folding tables with the distracted majesty of overworked zoo keepers. The mountain of presents glowed beside the cake like a treasure pile assembled by small pirates. Bill wore a blazer stolen from a golf captain; Molly had chosen pearls and the expression of a woman disappointed by everyone. Between them sat a duffel bag, several helium balloons, and a map that looked less like strategy and more like an octopus doodle. “Molly, children are ruthless; one nearly garroted me with streamers.” “That was a magician's assistant, Bill, and you deserved it.” “We need disguises: cheerful smiles, sensible shoes, absolutely no crowbars.” “Crowbars say confidence, but fine; I'll carry balloons and menace.” “Remember, we're stealing presents, not traumatizing the birthday monarchy today.” “Relax; I speak fluent parent: bunting, where's the gift table?” “And if we're caught, Bill? Children can smell criminal vibes.” “Then smile wider; adults distrust frowns, but children love lunatics.” “Fine, cake first, presents second; I have standards, unlike you.” “Good. No thief with manners ever interrupts the frosting ceremony.”
created_at
"2026-03-09T16:39:02.576Z"
3/9/2026, 4:39:02 PM
model
"openai/gpt-5.4-20260305"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
51282
moderation_latency
(null)
generation_time
51563
tokens_prompt
77
tokens_completion
1112
native_tokens_prompt
66
native_tokens_completion
3098
native_tokens_completion_images
0
native_tokens_reasoning
2816
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
0.046635
router
(null)
provider_responses
0
endpoint_id
"9ff5625c-403f-4d7f-b895-58ac7295062c"
id
"resp_04e83a7ef6a9eefa0169aef7a6af9c819098752db7b54a287a"
is_byok
false
latency
243
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-1773074342-Akz5HR5ZAKMA9ZFlmfQa"
upstream_id
"resp_04e83a7ef6a9eefa0169aef7a6af9c819098752db7b54a287a"
total_cost
0.046635
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
100.00%
Dialogue to Total Word Ratio
Ratio: 50.00%, Deviation: 0.00%
neededClean
false
wordsTotal
200
wordsDialogue
100
100.0000%