NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-18-01KHQ92GKXGKV8ATPRRSN2JFZX
Run Details
Model:
Claude Sonnet 4.6
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
8.8s
Cost:
$0.005070
Provider:
Anthropic
Evaluation summary
Score
Evaluator
Details Link
68.10%
Matches word count
(details)
98.43%
Dialogue to Total Word Ratio
(details)
83.2647%
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, so the birthday kid turns seven at two o'clock," Molly whispered, unrolling a crude crayon drawing onto the table. "Is that our blueprint?" Bill squinted. "Did you draw this yourself?" "I had to improvise. The architect wasn't available." "Molly, you've drawn the bouncy castle bigger than the house." "It's to scale." "It absolutely is not to scale." "Focus, Bill. We enter through the garden gate during musical chairs. Everyone looks left, everyone looks right, nobody watches the present table." "What about the clown?" "What clown?" "Every children's party has a clown, Molly." "We're not afraid of clowns." "Speak for yourself." "Bill." "I'm just saying he'll have a clear sightline from the balloon station." "We disable the clown first." "And how exactly do we disable a clown?" "We take his bicycle horn." "That's your whole plan? Take his horn?" "A clown without his horn is nothing, Bill. He's just a sad man in makeup." "I genuinely cannot argue with that." "Then we grab the presents, load the van, and we're gone before they cut the cake." "What kind of cake?" "Irrelevant." "Is it chocolate?" "Bill, please."
created_at
"2026-02-18T02:25:48.64586+00:00"
2/18/2026, 2:25:48 AM
model
"anthropic/claude-4.6-sonnet-20260217"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
463
moderation_latency
(null)
generation_time
8723
tokens_prompt
77
tokens_completion
325
native_tokens_prompt
75
native_tokens_completion
323
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
0.00507
router
(null)
provider_responses
0
id
"msg_018LfGyU2mGnvdtwKq12uQ8N"
status
200
is_byok
false
latency
463
endpoint_id
"6d408764-7dd7-4626-bb87-a6cc1589bc86"
provider_name
"Anthropic"
model_permaslug
"anthropic/claude-4.6-sonnet-20260217"
api_type
"completions"
id
"gen-1771381539-VQOREaJ0sRDu0GCxHzaf"
upstream_id
"msg_018LfGyU2mGnvdtwKq12uQ8N"
total_cost
0.00507
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Anthropic"
Evaluation details
Result
Evaluator
Details
Meta Data
68.10%
Matches word count
n/a
neededClean
false
words
186
98.43%
Dialogue to Total Word Ratio
Ratio: 93.55%, Deviation: 3.55%
neededClean
false
wordsTotal
186
wordsDialogue
174
83.2647%