NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHK99B8XC2QAXJCHYMB2QK7P
Run Details
Model:
GPT-5
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
1m 36s
Cost:
$0.068043
Provider:
OpenAI
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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 and Bill crouched behind a rabbit-shaped topiary, practicing nonchalance like pickpockets at a bake sale. The hall across the lawn fizzed with balloons, streamers, and a banner yelling HAPPY BIRTHDAY in confetti. Molly consulted a notebook nabbed from the coloring aisle; their blueprint was a rectangle labeled Joy Box, arrows all directions, plus a raccoon in shades. Bill adjusted a paper crown tilting like a guilty halo. Children whooped inside, the sound of stampeding cupcakes. Molly said, "We steal joyfully, not loudly." Bill practiced a smile so wholesome it needed permits. Confetti clung to their elbows like glittery guilt. He produced name tags: Aunt, Uncle, and Cousin Misplaced. They rehearsed cover stories: deliverer of napkins, balloon morale officer, emergency piƱata consultant. Bill murmured, "Balloons are guards with alibis." Molly flipped a coin that proved chocolate, then ate the evidence, declaring omens favorable. A breeze carried frosting and absolution. They synchronized watches, which were actually friendship bracelets with clocks drawn on. Molly whispered, "Remember the cake camouflage plan." Bill unfolded a tote bag the size of modest philosophy, then gazed at Mount Giftmore, wrapped, ribboned, irresistible. Bill grinned, "Pockets ready, smiles set, innocent." The topiary sneezed tinsel, and both thieves.
created_at
"2026-02-16T13:14:02.521721+00:00"
2/16/2026, 1:14:02 PM
model
"openai/gpt-5-2025-08-07"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3218
moderation_latency
(null)
generation_time
95685
tokens_prompt
77
tokens_completion
1551
native_tokens_prompt
66
native_tokens_completion
6796
native_tokens_completion_images
0
native_tokens_reasoning
6464
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
0.0680425
router
(null)
provider_responses
0
id
"resp_0f0fc5cf3a56007b01699317b9b950819698964551760eb7a3"
status
200
is_byok
false
latency
207
endpoint_id
"7c2f859a-7890-4e8e-b1de-1cd1c0a800b4"
provider_name
"OpenAI"
model_permaslug
"openai/gpt-5-2025-08-07"
api_type
"completions"
id
"gen-1771247545-wMxc7FQoAHzsbD4kLDVk"
upstream_id
"resp_0f0fc5cf3a56007b01699317b9b950819698964551760eb7a3"
total_cost
0.0680425
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
99.9990%
Matches word count
n/a
neededClean
false
words
201
100.0000%
Dialogue to Total Word Ratio
Ratio: 9.95%, Deviation: 0.05%
neededClean
false
wordsTotal
201
wordsDialogue
20
99.9995%