NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-18-01KHQ91FRFG8S51J3GFP3BJ99F
Run Details
Model:
Claude Sonnet 4.6
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
8.9s
Cost:
$0.004875
Provider:
Anthropic
Evaluation summary
Score
Evaluator
Details Link
86.38%
Matches word count
(details)
2.10%
Dialogue to Total Word Ratio
(details)
44.2384%
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 unrolled the hand-drawn map across the hood of the rusty van, stabbing her finger at a pink rectangle labeled "BOUNCY CASTLE." "We go in through the back garden while the clown has their attention," she whispered. "Why are we whispering?" Bill asked. "We're parked two streets away." "It's called atmosphere, Bill." He squinted at the map. "You've drawn seventeen different unicorns on this." "They're decorative. Now focus. The presents are stacked by the garden fence, which means extraction should take under four minutes." Bill scratched his chin thoughtfully. "What if some kid sees us?" "Children at parties are completely feral. Nobody will notice two adults walking out with gift bags." "I'm wearing a hi-vis jacket." "Exactly. We're invisible." A balloon drifted over the fence and bounced gently off Bill's head. They both watched it float away in silence. "Molly," Bill said slowly, "these are six year olds." "Rich six year olds." "That doesn't make it better." "One of them is getting a puppy, Bill. A living puppy as a present." Bill grabbed his end of the empty sack. "Alright," he sighed. "But we're leaving the puppy."
created_at
"2026-02-18T02:25:15.39683+00:00"
2/18/2026, 2:25:15 AM
model
"anthropic/claude-4.6-sonnet-20260217"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
983
moderation_latency
(null)
generation_time
8875
tokens_prompt
77
tokens_completion
312
native_tokens_prompt
75
native_tokens_completion
310
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
0.004875
router
(null)
provider_responses
0
id
"msg_012AEzmLwoJbt35nL4DdesTN"
status
200
is_byok
false
latency
983
endpoint_id
"6d408764-7dd7-4626-bb87-a6cc1589bc86"
provider_name
"Anthropic"
model_permaslug
"anthropic/claude-4.6-sonnet-20260217"
api_type
"completions"
id
"gen-1771381505-ZvbfztylqWBMRJzsQiVL"
upstream_id
"msg_012AEzmLwoJbt35nL4DdesTN"
total_cost
0.004875
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Anthropic"
Evaluation details
Result
Evaluator
Details
Meta Data
86.38%
Matches word count
n/a
neededClean
false
words
189
2.10%
Dialogue to Total Word Ratio
Ratio: 64.02%, Deviation: 14.02%
neededClean
false
wordsTotal
189
wordsDialogue
121
44.2384%