NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM08SV1XXN6GCCHVQVX6BNH7
Run Details
Model:
GPT-5.4 Nano
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
2.1s
Cost:
$0.000373
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
1.11%
Count dialogue tags
(details)
Model input
User/Human
You are an expert novel writer in the cozy mystery genre. Write a scene of about 200 words, with dialogue between two characters. The dialogue should be unattributed, meaning the speaker is not explicitly mentioned. The scene should be set in a small town bakery. Only return the story, nothing else.
Model response
Messages
Meta
AI
The bell over the door gave a soft jingle as Maribel wiped her hands on her apron and leaned into the glass case. “You’re early,”
she said
, though the smell of cinnamon already had the place awake. “Couldn’t sleep,”
June replied
, sliding into a chair by the window. Outside, Main Street looked like it was holding its breath. “And something’s off.” Maribel set down a plate—two scones, still warm enough to steam. “Off how?” June tapped the pastry box that had come in that morning. “The label. It says almond, but the invoice mentions hazelnut. And the delivery truck was parked on the wrong side of the street.” “Trucks park where they fit,”
Maribel said
, but her eyes stayed sharp. June leaned closer, lowering her voice. “Last week, Mrs. Tolland swore her tart was missing. Today, the flour bin’s half-empty even though no one ordered more. Someone’s been in the back.” Maribel pulled on a pair of oven mitts and lifted the lid of the bread proofing bowl. “Then someone’s been in a hurry.” June watched the dough rise, slow and patient. “Or someone wants us to think it’s an accident.” Maribel nodded once. “Well. Today we’ll start noticing who walks in—and who doesn’t leave footprints in the sugar.”
created_at
"2026-03-18T10:45:28.779Z"
3/18/2026, 10:45:28 AM
model
"openai/gpt-5.4-nano-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
483
moderation_latency
(null)
generation_time
1946
tokens_prompt
81
tokens_completion
339
native_tokens_prompt
67
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
0.0003734
router
(null)
provider_responses
0
endpoint_id
"0c835f2e-c18d-4e8c-b245-e1e3bd08b97f"
id
"resp_08fa7723007fe6660169ba8248dbe08196af6d3222bb988264"
is_byok
false
latency
230
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-1773830728-uelVOwb9KERaIP8rdtdp"
upstream_id
"resp_08fa7723007fe6660169ba8248dbe08196af6d3222bb988264"
total_cost
0.0003734
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
1.11%
Count dialogue tags
n/a
neededClean
false
dialogueTags
0
"she said"
1
"June replied"
2
"Maribel said"