NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM082JK6NJCB6N3X8JVZ2EZW
Run Details
Model:
GPT-5.4 Mini (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
15.6s
Cost:
$0.011560
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
91.58%
Dialogue to Total Word Ratio
(details)
95.7905%
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
Molly crouched behind the bakery dumpster, studying the glittering house across the street where a birthday banner trembled in the wind. Inside, laughter burst like confetti. Bill adjusted his borrowed bow tie and sighed. "Do you think the clown suspects anything?" "Bill, the clown suspects everyone. It's his face." "Excellent. So we're blending in." "With what? Your trench coat and a fruit basket?" He frowned at the basket. "It is a very convincing fruit basket." Molly peered at the gift table through the window. Towers of wrapped boxes gleamed under the balloons. "Easy score. We enter as tasteful party guests, distract the adults, and vanish with the presents." "And the cake?" "No." "Harsh." A shriek of happy children floated out, followed by a chorus of off-key singing. Bill swallowed. "I told you this felt wrong." "It’s only wrong if you get sentimental." He straightened his bow tie. "I am not sentimental. I’m practical." "Then practice being quiet." "Ah. My specialty." Molly smirked, tugged on her gloves, and led the way toward the cheerful front door, where the doormat read, Come on in! Any thief worth her salt could not resist an invitation like that. "Ready to get hilariously illegal, then, Molly?"
created_at
"2026-03-18T10:32:46.448Z"
3/18/2026, 10:32:46 AM
model
"openai/gpt-5.4-mini-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
14025
moderation_latency
(null)
generation_time
15398
tokens_prompt
77
tokens_completion
635
native_tokens_prompt
66
native_tokens_completion
2558
native_tokens_completion_images
0
native_tokens_reasoning
2276
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
0.0115605
router
(null)
provider_responses
0
endpoint_id
"9ee065b2-3d1c-43bc-bdd7-28af3b148282"
id
"resp_02d7eca2dcaf35820169ba7f4e82d4819087dc1d8d8270e56a"
is_byok
false
latency
163
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-1773829966-UDgkupZZPNsJznP73Ilj"
upstream_id
"resp_02d7eca2dcaf35820169ba7f4e82d4819087dc1d8d8270e56a"
total_cost
0.0115605
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
201
91.58%
Dialogue to Total Word Ratio
Ratio: 44.55%, Deviation: 5.45%
neededClean
false
wordsTotal
202
wordsDialogue
90
95.7905%