NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM0AP9BM2TTVSJSTGYDCTFBX
Run Details
Model:
GPT-5.4 Mini (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
9.8s
Cost:
$0.005152
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
36.79%
Dialogue to Total Word Ratio
(details)
68.3940%
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 bakery van, watching the rainbow balloons bob above the hedge like smug little moons. Inside the garden, a troop of children shrieked around a castle of cake and curling paper, while parents attempted the heroic but doomed dance of supervising sugar. Bill adjusted his tie, which was patterned with tiny pickpockets. "Easy job," he whispered. "Easy," Molly said, peering through binoculars shaped like cupcakes. "We slip in, swap the gift tags, and roll out before the clown finishes his balloon swan." Bill frowned. "What if the clown is observant?" Molly snorted. "Then we distract him with a terrible joke and a larger hat." Their plan was elegant in the way all bad plans are elegant at a distance. Bill produced a clipboard, Molly a tray of juice boxes, and together they glided toward the gate like overqualified caterers. A toddler in a dinosaur crown pointed at them. Molly waved. "Presents audit," she said. The child accepted this with the calm authority of the very young. Behind them, the gift table gleamed: ribbons, bows, teddy bears, and a suspiciously heavy box that clearly contained something expensive enough to require secrecy and enough batteries to require revenge later.
created_at
"2026-03-18T11:18:29.503Z"
3/18/2026, 11:18:29 AM
model
"openai/gpt-5.4-mini-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
9219
moderation_latency
(null)
generation_time
9523
tokens_prompt
77
tokens_completion
768
native_tokens_prompt
66
native_tokens_completion
1134
native_tokens_completion_images
0
native_tokens_reasoning
871
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
0.0051525
router
(null)
provider_responses
0
endpoint_id
"9ee065b2-3d1c-43bc-bdd7-28af3b148282"
id
"resp_0778a5d0095ce16d0169ba8a0590a08194973310afe4d7e8b0"
is_byok
false
latency
234
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-1773832709-apgwFbxfxnQVJm5Tn06q"
upstream_id
"resp_0778a5d0095ce16d0169ba8a0590a08194973310afe4d7e8b0"
total_cost
0.0051525
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
36.79%
Dialogue to Total Word Ratio
Ratio: 20.00%, Deviation: 10.00%
neededClean
false
wordsTotal
200
wordsDialogue
40
68.3940%