NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-18-01KHQ952RRQTNGJTWKVNN3JWX2
Run Details
Model:
Claude Sonnet 4.6
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
7.6s
Cost:
$0.004455
Provider:
Anthropic
Evaluation summary
Score
Evaluator
Details Link
99.74%
Matches word count
(details)
52.20%
Dialogue to Total Word Ratio
(details)
75.9700%
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 crouched behind the garden hedge, peering through the gap at the bouncy castle that dominated the backyard. Streamers floated lazily in the afternoon breeze. A banner reading Happy Birthday Timmy swayed between two oak trees. She counted approximately forty children running around like sugared-up tornadoes, which, she noted grimly, was exactly what they were. Bill crawled up beside her, twigs stuck in his hair and mud on his chin, clutching a clipboard he had absolutely no need for. "Twelve presents," he whispered. Molly nodded, scanning the patio where a mountain of wrapped gifts sat beside an untended folding table. The parents were inside, probably desperately pouring wine. The clown hired for entertainment had already retreated to his van, and she could not blame him remotely. The plan was straightforward enough. Bill would create a distraction involving balloon animals gone catastrophically wrong. Molly would load the gifts into the wheelbarrow they had hidden behind the garden shed. They would be gone before anyone noticed, slipping away through the side gate while Timmy was still demanding his third helping of cake. It was, Molly thought with some shame, their most elaborate and morally questionable job yet.
created_at
"2026-02-18T02:27:11.799571+00:00"
2/18/2026, 2:27:11 AM
model
"anthropic/claude-4.6-sonnet-20260217"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
476
moderation_latency
(null)
generation_time
7541
tokens_prompt
77
tokens_completion
319
native_tokens_prompt
75
native_tokens_completion
282
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
0.004455
router
(null)
provider_responses
0
id
"msg_01XqZdRmHaFbJB4D9LZd8nPZ"
status
200
is_byok
false
latency
475
endpoint_id
"6d408764-7dd7-4626-bb87-a6cc1589bc86"
provider_name
"Anthropic"
model_permaslug
"anthropic/claude-4.6-sonnet-20260217"
api_type
"completions"
id
"gen-1771381623-fW1rq4GySi7f5i3mlqid"
upstream_id
"msg_01XqZdRmHaFbJB4D9LZd8nPZ"
total_cost
0.004455
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Anthropic"
Evaluation details
Result
Evaluator
Details
Meta Data
99.74%
Matches word count
n/a
neededClean
false
words
196
52.20%
Dialogue to Total Word Ratio
Ratio: 1.02%, Deviation: 8.98%
neededClean
false
wordsTotal
196
wordsDialogue
2
75.9700%