NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-18-01KHQ94QKRKVR48Z58418P3B80
Run Details
Model:
Claude Sonnet 4.6
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
8.9s
Cost:
$0.004560
Provider:
Anthropic
Evaluation summary
Score
Evaluator
Details Link
99.92%
Matches word count
(details)
97.69%
Dialogue to Total Word Ratio
(details)
98.8060%
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
The warehouse smelled of old cheese and broken dreams, which suited Bill perfectly since he had plenty of experience with both. He spread the hand-drawn blueprints across the wobbly table, smoothing the corners with his elbows while simultaneously trying to avoid the suspicious stain near sector four. Molly circled the perimeter of the table like a shark who had recently attended a tactical planning seminar. The target was a seventh birthday party at the Henderson residence. Thirty-two wrapped presents according to their intelligence, which consisted entirely of Molly having peeked over the fence last Tuesday. "We go in through the bouncy castle," Molly said. Bill nodded gravely, as though she had proposed something with genuine strategic merit rather than complete absurdity. He drew a small arrow on the blueprint pointing toward what he had labeled the Inflatable Insertion Point. The plan required disguises, a getaway vehicle, and precise timing around the scheduled appearance of someone called Mister Bubbles the Clown. Bill had nightmares about clowns. He wrote AVOID BUBBLES in capital letters and underlined it three times. "What about the kids?" Bill asked. "Cake," Molly replied simply. It was foolproof. They were, unfortunately, the fools.
created_at
"2026-02-18T02:27:01.491333+00:00"
2/18/2026, 2:27:01 AM
model
"anthropic/claude-4.6-sonnet-20260217"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
649
moderation_latency
(null)
generation_time
8836
tokens_prompt
77
tokens_completion
328
native_tokens_prompt
75
native_tokens_completion
289
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
0.00456
router
(null)
provider_responses
0
id
"msg_01XVAQZkGqdGzQTX3TPCUEZD"
status
200
is_byok
false
latency
649
endpoint_id
"6d408764-7dd7-4626-bb87-a6cc1589bc86"
provider_name
"Anthropic"
model_permaslug
"anthropic/claude-4.6-sonnet-20260217"
api_type
"completions"
id
"gen-1771381612-ffiatcpXXbz7ZbLPbsPo"
upstream_id
"msg_01XVAQZkGqdGzQTX3TPCUEZD"
total_cost
0.00456
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Anthropic"
Evaluation details
Result
Evaluator
Details
Meta Data
99.92%
Matches word count
n/a
neededClean
false
words
197
97.69%
Dialogue to Total Word Ratio
Ratio: 6.09%, Deviation: 3.91%
neededClean
false
wordsTotal
197
wordsDialogue
12
98.8060%