NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ0NR95H9BHRY27MDAAH6Y3E
Run Details
Model:
GPT-5.5
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
8.0s
Cost:
$0.008550
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
99.38%
Matches word count
(details)
99.92%
Dialogue to Total Word Ratio
(details)
99.6460%
Overall
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 unfolded the party invitation like it was a bank vault blueprint, smoothing the glittery corners with grave professional care. Bill crouched beside her behind the hedge, wearing a clown wig, a burglar’s mask, and the haunted expression of a man already regretting three separate decisions. Across the street, the community hall blazed with balloons, banners, and the unmistakable shriek of sugared children. A mountain of presents sat beneath a cardboard castle, guarded only by a grandmother with a whistle and the posture of a retired prison warden. “Timing?” Molly whispered. “During cake,” Bill said. “That’s your whole plan?” “It’s a large cake.” Molly nodded, reluctantly impressed. Bill produced a sack labeled LAUNDRY, which fooled nobody, especially since it had dollar signs drawn on it in crayon. Molly pointed toward the side door, where a magician was arguing with a rabbit that refused to enter a hat. “We go in as entertainment,” she said. “I hate children.” “They hate clowns.” “Excellent cover.” Then the birthday boy spotted Bill’s wig bobbing above the hedge and yelled with battlefield enthusiasm. Thirty children surged toward them, demanding balloon swords, face paint, and justice. Molly pocketed the invitation and sighed. The heist, she realized, had already stolen their afternoon.
created_at
"2026-04-24T21:18:54.648Z"
4/24/2026, 9:18:54 PM
model
"openai/gpt-5.5-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
560
moderation_latency
(null)
generation_time
7937
tokens_prompt
77
tokens_completion
365
native_tokens_prompt
66
native_tokens_completion
274
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)
num_fetches
(null)
web_search_engine
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"completed"
usage
0.00855
router
(null)
provider_responses
0
endpoint_id
"58e5b336-423e-430b-a2ab-8bc353f0c51b"
id
"resp_0238edce1c5466250169ebde3ec1148193b9408517fc750933"
is_byok
false
latency
263
model_permaslug
"openai/gpt-5.5-20260423"
provider_name
"OpenAI"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777065534-NEtq6BPFK3Lw15dXPlRo"
session_id
(null)
api_type
"completions"
id
"gen-1777065534-8lpEcekCNJWbiVwjwgTT"
upstream_id
"resp_0238edce1c5466250169ebde3ec1148193b9408517fc750933"
total_cost
0.00855
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
99.38%
Matches word count
n/a
neededClean
false
words
205
99.92%
Dialogue to Total Word Ratio
Ratio: 11.71%, Deviation: 1.71%
neededClean
false
wordsTotal
205
wordsDialogue
24
99.6460%