NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-02-08-01KGYX23X4RYAPA1T5G28NXCX1
Run Details
Model:
Claude Opus 4.6
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
10.0s
Cost:
$0.008000
Provider:
Anthropic
Evaluation summary
Score
Evaluator
Details Link
98.71%
Matches word count
(details)
0.19%
Dialogue to Total Word Ratio
(details)
49.4520%
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 pressed her binoculars against the minivan window, watching a stream of parents carrying wrapped boxes through the front door of 47 Maple Street. She whistled low. "That's the third kid hauling in a gift bag bigger than himself," she said. "We're looking at a serious payload here, Bill." Bill adjusted his fake mustache in the rearview mirror and frowned. "Remind me again why we're robbing children." "We're not robbing children. We're robbing a house that happens to contain children. There's a moral distinction." "Is there, though?" "Absolutely not, but it makes me feel better." Molly pulled out a hand-drawn blueprint of the property, which she had sketched on a napkin from Denny's. "The presents are in the living room. We enter through the back sliding door during the piñata window." "The piñata window?" "Every kid at that party will be in the backyard swinging a bat at a papier-mâché unicorn. That gives us roughly four minutes of total chaos to work with." Bill studied the napkin blueprint, turning it sideways. "This looks like a duck." "That's the kitchen island." "And that?" "Also the kitchen island. I'm not an architect, Bill. I'm a criminal."
created_at
"2026-02-08T15:14:07.824853+00:00"
2/8/2026, 3:14:07 PM
model
"anthropic/claude-4.6-opus-20260205"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1513
moderation_latency
(null)
generation_time
9926
tokens_prompt
61
tokens_completion
271
native_tokens_prompt
75
native_tokens_completion
305
native_tokens_completion_images
(null)
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)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
usage
0.008
router
(null)
provider_responses
0
id
"msg_01WVwMyRkPUh37wDaVv9sDR3"
status
200
is_byok
false
latency
1513
endpoint_id
"c926c048-563e-44b0-8434-95965bee924c"
provider_name
"Anthropic"
model_permaslug
"anthropic/claude-4.6-opus-20260205"
api_type
"completions"
id
"gen-1770563637-4j3KxZOLnVn71dFJ5mea"
upstream_id
"msg_01WVwMyRkPUh37wDaVv9sDR3"
total_cost
0.008
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Anthropic"
Evaluation details
Result
Evaluator
Details
Meta Data
98.71%
Matches word count
n/a
neededClean
false
words
194
0.19%
Dialogue to Total Word Ratio
Ratio: 65.82%, Deviation: 15.82%
neededClean
false
wordsTotal
196
wordsDialogue
129
49.4520%