NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-09-01KX40K374VX9K2AK759YWSJY4
Run Details
Model:
GPT-5.6 Terra
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
4.8s
Cost:
$0.004995
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
51.93%
Matches word count
(details)
36.79%
Dialogue to Total Word Ratio
(details)
44.3567%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% 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, why are we whispering? It’s a bouncy castle, not Fort Knox.” “Because, Bill, children have ears like bats and a suspicious relationship with justice.” “We’re stealing presents, not the crown jewels.” “Same principle. Tiny hands, sticky fingerprints, devastating courtroom testimony.” “What’s the plan?” “You distract the parents.” “How?” “Put on this pirate hat and complain about parking.” “That’s not a distraction. That’s my personality.” “Exactly. Meanwhile, I slip through the side gate, cross the garden, and locate the gift table.” “What if there’s a dog?” “Then you throw it a sausage.” “I ate the sausages.” “All of them?” “I was nervous.” “Fine. Throw it a cupcake.” “I ate those too.” “Bill, why did we bring you?” “I’ve got the van.” “You’ve got a bicycle with a milk crate.” “It’s environmentally conscious crime.” “How many presents can it carry?” “Depends. Are we counting the ones shaped like dinosaurs?” “Yes.” “Then three. Maybe four if one is a puzzle.” “Brilliant. We’ll be rich in colouring books and plastic dinosaurs.” “There could be gift cards.” “There could also be glitter.” “Glitter’s valuable.” “Glitter is evidence that never dies.” “Look, the clown’s leaving.” “Good. Clowns always notice things.” “Ready?” “Ready.” “Wait. Why is there a banner saying ‘Happy Sixth Birthday, Bill’?” “Ah.” “Bill?” “My mum said nobody was coming.”
created_at
"2026-07-09T18:00:13.293Z"
7/9/2026, 6:00:13 PM
model
"openai/gpt-5.6-terra-20260709"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
616
moderation_latency
(null)
generation_time
4639
tokens_prompt
77
tokens_completion
475
native_tokens_prompt
66
native_tokens_completion
322
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
0.004995
router
(null)
provider_responses
0
endpoint_id
"3cc89000-ae34-4dde-9c7d-5ce009c8af0b"
id
"resp_0cde19a8d76df805016a4fe1ad60ec8196ab0d948fd5b8408f"
is_byok
false
latency
284
model_permaslug
"openai/gpt-5.6-terra-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-1783620013-ScEEExviW4aNZPHG4zHq"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1783620013-Es8Fzn6uHfk7AnV4MbeZ"
upstream_id
"resp_0cde19a8d76df805016a4fe1ad60ec8196ab0d948fd5b8408f"
total_cost
0.004995
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
51.93%
Matches word count
n/a
neededClean
false
words
216
36.79%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
216
wordsDialogue
216
44.3567%