NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM091VRRMS64W7ZKS3MQ3N19
Run Details
Model:
GPT-5.4 Mini (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
2.3s
Cost:
$0.001858
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
99.92%
Matches word count
(details)
36.79%
Dialogue to Total Word Ratio
(details)
68.3535%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% 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, you brought the disguises?” “Of course I did, Molly. I’m not a monster. I brought a clown nose, a balloon sword, and a cardigan that says ‘trust me with cake.’” “Brilliant. So we’re infiltrating as entertainers?” “We’re infiltrating as the sort of people nobody checks twice.” “You mean children’s party staff.” “I mean emotionally available.” “Mmm. And the presents?” “Stacked by the rainbow table, according to the baker’s nephew.” “The baker’s nephew?” “Tiny informant. Big ears.” “Bill, are you certain this is a good idea?” “No, but it is a festive idea.” “What if they ask our names?” “You’re Molly.” “And you?” “Bill.” “That’s not a disguise.” “It’s a classic. Nobody suspects a Bill.” “Bill, children are sticky.” “I’ve considered that.” “Have you considered the cake?” “Only in a tactical sense.” “And the balloon animals?” “Diversionary assets.” “And if the host asks why we’re carrying sacks?” “We say it’s a surprise sack race.” “That’s terrible.” “It’s inspired.” “I hate that I love it.” “Hush. The party’s starting.” “One last thing, Bill.” “Yes, Molly?” “After we steal the presents, we do not, under any circumstances, take the pony.” “The pony’s a trap.” “Good.” “Though if it’s a very small pony, I might reconsider.”
created_at
"2026-03-18T10:49:51.652Z"
3/18/2026, 10:49:51 AM
model
"openai/gpt-5.4-mini-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1052
moderation_latency
(null)
generation_time
2171
tokens_prompt
77
tokens_completion
406
native_tokens_prompt
66
native_tokens_completion
402
native_tokens_completion_images
0
native_tokens_reasoning
93
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
0.0018585
router
(null)
provider_responses
0
endpoint_id
"9ee065b2-3d1c-43bc-bdd7-28af3b148282"
id
"resp_0c1a54e5d1ddcdf40169ba834fb9b08193a39359c8e978f22b"
is_byok
false
latency
223
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-1773830991-NuWYkgsfzGIpLAPJleIB"
upstream_id
"resp_0c1a54e5d1ddcdf40169ba834fb9b08193a39359c8e978f22b"
total_cost
0.0018585
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
99.92%
Matches word count
n/a
neededClean
false
words
203
36.79%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
203
wordsDialogue
203
68.3535%