NC Bench
Overview
About
Tests
Models
Vendors
Compare
Run: 2026-02-24-01KJ8VMPQPZB1907XGPYGGEKQ7
Run Details
Model:
Claude Sonnet 4.6 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
24.3s
Cost:
$0.022731
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
20.19%
Matches word count
(details)
99.78%
Dialogue to Total Word Ratio
(details)
59.9872%
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
"Okay, the party starts at two," said Molly, spreading a hand-drawn map across the hood of their van. "Do we really need a map of a bouncy castle?" Bill asked. "Every job needs a map." "It's a semicircle, Molly." "Focus. The presents are piled near the cake table. We go in through the back gate during musical chairs." "Why musical chairs?" "Because every adult in that garden will be screaming at children. Nobody watches the gift table during musical chairs." "That's actually brilliant," Bill admitted. "I know." "What do we wear?" "I'm thinking—" "Please don't say clown suits." "Clown suits." "Molly, no." "Bill, yes. We blend right in." "With the other clowns?" "There's always a clown at these things." "And if there isn't?" "Then we're the entertainment and nobody questions us near the presents." "This is the stupidest plan I've ever heard." "You said that about the dog show job." "We made forty quid from the dog show job." "Exactly." Bill stared at the map. "I want it on record that I hate this." "Noted. Now put your wig on."
created_at
"2026-02-24T22:17:15.292Z"
2/24/2026, 10:17:15 PM
model
"anthropic/claude-4.6-sonnet-20260217"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
717
moderation_latency
177
generation_time
23941
tokens_prompt
77
tokens_completion
688
native_tokens_prompt
92
native_tokens_completion
1497
native_tokens_completion_images
(null)
native_tokens_reasoning
385
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
0.022731
router
(null)
provider_responses
0
endpoint_id
"83d802cb-44f2-45a0-a9d5-cb9bf79777c8"
id
"5d3aa86e-8860-49cc-ae3a-c92491b23d88"
is_byok
false
latency
716
model_permaslug
"anthropic/claude-4.6-sonnet-20260217"
provider_name
"Amazon Bedrock"
status
200
api_type
"completions"
id
"gen-1771971435-4AkeJCODXl2GJ62adWHa"
upstream_id
"5d3aa86e-8860-49cc-ae3a-c92491b23d88"
total_cost
0.022731
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
Evaluation details
Result
Evaluator
Details
Meta Data
20.19%
Matches word count
n/a
neededClean
false
words
180
99.78%
Dialogue to Total Word Ratio
Ratio: 87.85%, Deviation: 2.15%
neededClean
false
wordsTotal
181
wordsDialogue
159
59.9872%