NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-09-01KX40ZAN7W3PQK1ZKJ4TKDHWR
Run Details
Model:
GPT-5.6 Luna (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
9.3s
Cost:
$0.009888
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
100.0000%
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 and Bill crouched behind a hedge outside the community hall, where balloons bobbed like colorful surveillance cameras. Inside, children shrieked around a mountain of brightly wrapped presents. A banner announced Tommy's seventh birthday, though Bill insisted the lettering looked suspiciously like a ransom note. Molly unfolded a grease-spotted map across her knee. “We enter through the kitchen, distract the clown, and exit wearing party hats.” Bill whispered. “Excellent. I brought disguises and emotional support.” Molly examined two black masks, a coil of rope, and a sack labeled Emergency Cupcakes. Bill produced a rubber chicken from his coat. It squeaked, causing a nearby balloon to burst. Both froze. From inside, someone yelled that the treasure hunt had begun. Bill grinned, mistaking panic for destiny. They crept toward the kitchen window, but Molly noticed its latch was guarded by a sleeping terrier wearing a tiny crown. She tossed Bill's cupcake sack toward the bushes. The dog woke, saluted the snack, and charged after it, dragging a tablecloth into the moonlight. Presents toppled everywhere. Children screamed with delight, assuming this was scheduled entertainment. Molly and Bill scrambled inside, grabbing every present while the clown applauded their performance. By midnight, they escaped triumphant.
created_at
"2026-07-09T18:06:54.126Z"
7/9/2026, 6:06:54 PM
model
"openai/gpt-5.6-luna-20260709"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1963
moderation_latency
(null)
generation_time
8765
tokens_prompt
77
tokens_completion
719
native_tokens_prompt
66
native_tokens_completion
1637
native_tokens_completion_images
0
native_tokens_reasoning
1365
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"
service_tier
"default"
usage
0.009888
router
(null)
provider_responses
0
endpoint_id
"eebea444-34a5-4642-a766-cb319471d33a"
id
"resp_0ac7832dc3fdcf8f016a4fe33e33c881909b27b06c3840297d"
is_byok
false
latency
288
model_permaslug
"openai/gpt-5.6-luna-20260709"
provider_name
"OpenAI"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.18.0; linux; x64))"
http_referer
(null)
request_id
"req-1783620414-EnE5r3a2EuHsY0p6PwVf"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1783620414-pXQQSMmToSPdfGuv72bl"
upstream_id
"resp_0ac7832dc3fdcf8f016a4fe33e33c881909b27b06c3840297d"
total_cost
0.009888
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
response_cache_source_id
(null)
data_region
"global"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
200
100.00%
Dialogue to Total Word Ratio
Ratio: 9.95%, Deviation: 0.05%
neededClean
false
wordsTotal
201
wordsDialogue
20
100.0000%