NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-06-01KK1JCJF6EF6CZKGS6JNWH700
Run Details
Model:
GPT-5.4
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
8.9s
Cost:
$0.004485
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
6.09%
Matches word count
(details)
99.84%
Dialogue to Total Word Ratio
(details)
52.9654%
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 and Bill crouched behind the garden shed like two underfunded masterminds, peering through a gap in the fence at the children’s party next door. Balloons bobbed over the lawn in frantic colors, a clown collapsed onto a deck chair smoking suspiciously adult cigarettes, and a long table groaned beneath cakes, cordial, and a mountain of brightly wrapped presents. Bill adjusted his flat cap with the gravity of a surgeon. “We go in smiling.” “That’s your plan?” Molly whispered. “Children trust confidence,” he said. “And waistcoats.” Molly eyed his mustard-colored waistcoat, which made him look less like a guest and more like a substitute geography teacher who’d lost a bet. She herself wore a cardigan covered in knitted ducks, acquired from a charity shop precisely because it radiated the harmless menace of an aunt who brought raisins. Beyond the fence, a magician was extracting scarves from his sleeve with the exhausted air of a man pulling rent money from the void. Parents clustered near the buffet, distracted by prosecco and competitive anecdotes about schools with waiting lists longer than prison sentences. Molly produced a hand-drawn map of the garden. The presents were stacked beside the trampoline, guarded only by a pug in a paper crown. Bill studied the dog, the children, the clown, then nodded. “Right,” he murmured. “We steal Christmas in June.”
created_at
"2026-03-06T12:36:32.367Z"
3/6/2026, 12:36:32 PM
model
"openai/gpt-5.4-20260305"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
440
moderation_latency
(null)
generation_time
8846
tokens_prompt
77
tokens_completion
368
native_tokens_prompt
66
native_tokens_completion
288
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
0.004485
router
(null)
provider_responses
0
endpoint_id
"9ff5625c-403f-4d7f-b895-58ac7295062c"
id
"resp_0d3fda16ac77837a0169aaca5070a481908c0c248b459cdef2"
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-1772800592-XknoaSX3WprpOIqFgtZs"
upstream_id
"resp_0d3fda16ac77837a0169aaca5070a481908c0c248b459cdef2"
total_cost
0.004485
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
6.09%
Matches word count
n/a
neededClean
false
words
223
99.84%
Dialogue to Total Word Ratio
Ratio: 8.00%, Deviation: 2.00%
neededClean
false
wordsTotal
225
wordsDialogue
18
52.9654%