NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-09-01KK9Q9M8V7W4J180N6WP4FB48
Run Details
Model:
GPT-5.4 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
36.1s
Cost:
$0.033690
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
99.64%
Dialogue to Total Word Ratio
(details)
99.8199%
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 peered through the hedge at the garden, where balloons bobbed like nervous witnesses and a clown made tragic animals out of balloons. “Bill, this is the lowest point in my criminal career, and I once robbed a mime.” “Correction,” Bill whispered, adjusting his velvet cap. “We are liberating unappreciated toys from sticky-fingered aristocrats under four feet tall.” “Those are six-year-olds, not dukes.” “Look at that bouncy castle. Nobody poor owns one.” Molly eyed the gift table, a mountain of wrapped boxes beside a pink banner reading HAPPY BIRTHDAY, EMILY. “We go in as entertainers?” “With these faces? We’d terrify the pony.” “Then parents. Grim, exhausted, impossible to identify individually.” “Perfect. I can carry a casserole dish. Respectable people always carry casseroles.” “And I’ll look disappointed in everyone.” “Natural talent.” “Just smile warmly and don’t mention your record around the toddlers.” From the patio came shrieking laughter, the sound of sugar discovering its constitutional rights. Bill unfolded a map that appeared to be mostly gravy stains. Molly sighed, tightened her gloves, and watched Emily whack a piñata with the joyous fury of a tiny tax collector. Beyond her, the presents gleamed in the sun, innocent, plentiful, and almost certainly battery-operated.
created_at
"2026-03-09T16:36:14.242Z"
3/9/2026, 4:36:14 PM
model
"openai/gpt-5.4-20260305"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
32587
moderation_latency
(null)
generation_time
35959
tokens_prompt
77
tokens_completion
484
native_tokens_prompt
66
native_tokens_completion
2235
native_tokens_completion_images
0
native_tokens_reasoning
1948
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
0.03369
router
(null)
provider_responses
0
endpoint_id
"9ff5625c-403f-4d7f-b895-58ac7295062c"
id
"resp_03c919d6a28b7b630169aef6fe57848190a7af14d16011045b"
is_byok
false
latency
184
model_permaslug
"openai/gpt-5.4-20260305"
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-1773074174-nRYGRKaQmIUoFJvX7A1p"
upstream_id
"resp_03c919d6a28b7b630169aef6fe57848190a7af14d16011045b"
total_cost
0.03369
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
200
99.64%
Dialogue to Total Word Ratio
Ratio: 47.55%, Deviation: 2.45%
neededClean
false
wordsTotal
204
wordsDialogue
97
99.8199%