NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-23-01M37HFVQJN1AY9Q7WWSS5NTRH
Run Details
Model:
GPT-6 Sol
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
7.9s
Cost:
$0.003282
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
43.38%
Matches word count
(details)
15.91%
Dialogue to Total Word Ratio
(details)
29.6446%
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 and Bill crouched behind a hedge shaped like a smiling dinosaur. Across the lawn, balloons bobbed above a table stacked with presents. “Is that the target?” Bill whispered. “No, Bill. That’s a dinosaur hedge.” “I meant the table.” “Then yes. Try pointing next time.” They wore black turtlenecks. Bill’s had a glittery cupcake on it, but he insisted the glitter helped him blend in. “Security?” he asked. “One grandmother at the gate. Two parents by the cake.” “And the children?” “Twenty-three, according to the invitations.” Bill swallowed. “Twenty-three witnesses.” Molly produced a clipboard and a cone-shaped hat. “We go in as party inspectors.” “That’s a job?” “It is if you look annoyed enough.” At the gate, the grandmother examined their clipboards. Molly frowned at a balloon. Bill wrote “balloon” and underlined it twice. “Cake inspection,” Molly announced. “Present inspection,” Bill added. The grandmother smiled. “Excellent. The children have been waiting for the magicians.” Before either thief could object, twenty-three children surrounded them, chanting for tricks. Bill pulled a coin from behind Molly’s ear. Molly made his clipboard disappear down the back of his trousers. The grandmother applauded. Then she handed them aprons and pointed toward the cake. “Lovely,” Molly muttered. “Now we’re catering.” Bill adjusted his hat. “Do caterers get cake?” “After cleanup.” “Best heist ever.”
created_at
"2026-09-23T16:27:27.355Z"
9/23/2026, 4:27:27 PM
model
"openai/gpt-6-sol-20260922"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1534
moderation_latency
(null)
generation_time
7849
tokens_prompt
75
tokens_completion
406
native_tokens_prompt
66
native_tokens_completion
315
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"
service_tier
"default"
usage
0.003282
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1790180847-ZyMcIZz6lb9uH7W60CRp"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790180847-V5ut84b38jPABjuaQcLn"
upstream_id
"resp_03fdb15d3a80bd65016ab3fdef751487d1a7018fe207761a02"
provider_responses
0
endpoint_id
"1cfc7d9d-4404-4b8e-9ee4-58ae45c9dcd4"
id
"resp_03fdb15d3a80bd65016ab3fdef751487d1a7018fe207761a02"
is_byok
false
latency
1178
model_permaslug
"openai/gpt-6-sol-20260922"
provider_name
"OpenAI"
status
200
total_cost
0.003282
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
response_cache_source_id
(null)
data_region
"global"
workspace_id
"97e315e5-d303-487d-83c1-83180e8a13d4"
Evaluation details
Result
Evaluator
Details
Meta Data
43.38%
Matches word count
n/a
neededClean
false
words
217
15.91%
Dialogue to Total Word Ratio
Ratio: 38.36%, Deviation: 11.64%
neededClean
false
wordsTotal
219
wordsDialogue
84
29.6446%