NC Bench
Overview
About
Tests
Models
Vendors
Compare
Run: 2026-02-24-01KJ8TKBSPHYYVYQKE4R8YYSZF
Run Details
Model:
Claude Sonnet 4.6 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
9.7s
Cost:
$0.006741
Provider:
Anthropic
Evaluation summary
Score
Evaluator
Details Link
20.19%
Matches word count
(details)
92.41%
Dialogue to Total Word Ratio
(details)
56.2997%
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
"Right," said Molly, spreading the hand-drawn map across the park bench. "The party starts at two." "Got it. What's our window?" "Pin the tail on the donkey buys us four minutes, maybe five if the blindfold's tight." Bill squinted at the map. "What's this circle here?" "That's the bouncy castle. Avoid it at all costs." "Why?" "Kids in bouncy castles have unpredictable trajectories, Bill." "Fair enough. What about the presents?" "Pile's near the back fence. Stack looks enormous. Little Timmy apparently has very generous grandparents." "How do we carry it all?" "I bought a wheelbarrow." "A wheelbarrow." "It's a lot of presents, Bill." "Won't we look suspicious? Two adults with a wheelbarrow at a six-year-old's birthday party?" "I'm wearing a clown wig." Bill stared at her. "That makes it worse, Molly." "Does it though?" "Enormously, yes." "Well, what's your plan?" "I don't know, something that doesn't involve a wheelbarrow and a clown wig." "You've had three weeks to contribute ideas and this is the first objection you've raised." Bill went quiet. "Clown wig it is," said Molly, folding the map.
created_at
"2026-02-24T21:59:03.055Z"
2/24/2026, 9:59:03 PM
model
"anthropic/claude-4.6-sonnet-20260217"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
499
moderation_latency
(null)
generation_time
9234
tokens_prompt
77
tokens_completion
400
native_tokens_prompt
92
native_tokens_completion
431
native_tokens_completion_images
(null)
native_tokens_reasoning
84
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
0.006741
router
(null)
provider_responses
0
endpoint_id
"6d408764-7dd7-4626-bb87-a6cc1589bc86"
id
"msg_01EqgzNohEdm2SjC5rD1j3oj"
is_byok
false
latency
466
model_permaslug
"anthropic/claude-4.6-sonnet-20260217"
provider_name
"Anthropic"
status
200
api_type
"completions"
id
"gen-1771970343-zMzWwkS0LkSBLN6gv9dZ"
upstream_id
"msg_01EqgzNohEdm2SjC5rD1j3oj"
total_cost
0.006741
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Anthropic"
Evaluation details
Result
Evaluator
Details
Meta Data
20.19%
Matches word count
n/a
neededClean
false
words
180
92.41%
Dialogue to Total Word Ratio
Ratio: 84.70%, Deviation: 5.30%
neededClean
false
wordsTotal
183
wordsDialogue
155
56.2997%