NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHKA92JMC99DGE6K4V7GXGNM
Run Details
Model:
GPT-5 Mini
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
42.8s
Cost:
$0.008223
Provider:
OpenAI
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
Nightlight-carved shadows pooled as Molly and Bill crouched behind a hedge, whispering like amateur villains plotting something slightly ridiculous today. Molly: "Bill, this is ridiculous." Bill: "Ridiculous is my middle name." Molly: "You don't have a middle name." Bill: "Technically I have three." Molly: "Focus. Presents." Bill: "Soft, squishy presents?" Molly: "All presents." Bill: "What about the one with glitter?" Molly: "All." Bill: "Even the ones with glitter glue?" Molly: "Especially those." Bill: "We're professional-ish." Molly: "We're also allergic to normal jobs." Bill: "And very committed to wrapping mastery." Molly: "How will we carry so many toys?" Bill: "With dramatic flair." Molly: "Or with a very large bag?" Bill: "Again with the practical thinking." Molly: "We'll need a diversion." Bill: "I can juggle cupcakes, partially competent." Molly: "Children love cupcakes." Bill: "Children also love mysteries." Molly: "So we juggle cupcakes, create a tiny riddle, and become mythic snack bandits?" Bill: "Mythic snack bandits with impeccable timing." Molly: "Impeccable? You mean sort of passable at best." Bill: "Passable is the new impeccable." Molly: "Fine. We run in, steal the glitter glue and leave confetti apology notes." Bill: "Confetti apology notes are environmentally questionable but theatrically brilliant." Molly: "Exactly. Now let's go."
created_at
"2026-02-16T13:30:28.95287+00:00"
2/16/2026, 1:30:28 PM
model
"openai/gpt-5-mini-2025-08-07"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2796
moderation_latency
(null)
generation_time
42493
tokens_prompt
77
tokens_completion
1242
native_tokens_prompt
66
native_tokens_completion
4103
native_tokens_completion_images
0
native_tokens_reasoning
3712
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
0.0082225
router
(null)
provider_responses
0
id
"resp_057c457eec46abd80169931bc965a48190b55c965f9137b6cc"
status
200
is_byok
false
latency
121
endpoint_id
"c4f66d01-20b0-4c27-a225-438ea22fda43"
provider_name
"OpenAI"
model_permaslug
"openai/gpt-5-mini-2025-08-07"
api_type
"completions"
id
"gen-1771248585-hvhgFnjHxlZoAyhZwD85"
upstream_id
"resp_057c457eec46abd80169931bc965a48190b55c965f9137b6cc"
total_cost
0.0082225
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
99.9840%
Matches word count
n/a
neededClean
false
words
202
0.8769%
Dialogue to Total Word Ratio
Ratio: 75.25%, Deviation: 14.75%
neededClean
false
wordsTotal
202
wordsDialogue
152
50.4305%