NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM07BPYMQ6BZ832R93796FSA
Run Details
Model:
GPT-5.4 Nano (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
41.2s
Cost:
$0.006754
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
50.0000%
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 crouched behind the hedge, clutching bolt cutters like they were gourmet cheese. Molly adjusted a party hat over her ski mask. 'Focus,' she whispered, 'those presents are innocent, which makes them extremely stealable.' 'Innocent is code for easy,' Bill breathed, scanning the driveway where balloons bobbed like confused planets. 'Do we really need the cat costume?' Molly asked. 'It’s the getaway vehicle,' Bill said. 'The kids will think we’re their mascot and wave us through.' A clownish guitar version of “Jingle Bells” floated from the backyard. A birthday banner sagged, daring fate to trip, and fate considered it then smiled softly. 'And my stealth plan?' Molly murmured. 'Your stealth plan is that you’re short, so you can wriggle under the gift table.' Molly grinned and placed a tiny bow on a duffel bag. 'Remind me why we’re stealing from a party full of toddlers.' 'Because adults hide the receipts,' Bill said, 'and toddlers hide the receipts inside their mouths.' Molly reached into her pocket and produced sticky hands. 'No refunds,' she joked. 'We’ll leave one present,' Bill offered, 'the one that’s a toy shark.' Molly nodded. 'Perfect. We rob shark, and we swim away.' No alarms tonight, Bill; none.
created_at
"2026-03-18T10:20:17.248Z"
3/18/2026, 10:20:17 AM
model
"openai/gpt-5.4-nano-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
40510
moderation_latency
(null)
generation_time
40861
tokens_prompt
77
tokens_completion
1059
native_tokens_prompt
66
native_tokens_completion
5393
native_tokens_completion_images
0
native_tokens_reasoning
5107
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
0.00675445
router
(null)
provider_responses
0
endpoint_id
"0c835f2e-c18d-4e8c-b245-e1e3bd08b97f"
id
"resp_02ac8b0b7c758aed0169ba7c61514881949b7b10c86aa4305e"
is_byok
false
latency
213
model_permaslug
"openai/gpt-5.4-nano-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-1773829217-kssgD0vJaDLZ6czqG9mo"
upstream_id
"resp_02ac8b0b7c758aed0169ba7c61514881949b7b10c86aa4305e"
total_cost
0.00675445
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
0.00%
Dialogue to Total Word Ratio
Ratio: 78.50%, Deviation: 28.50%
neededClean
false
wordsTotal
200
wordsDialogue
157
50.0000%