NC Bench
Overview
About
Tests
Models
Vendors
Compare
Run: 2026-02-24-01KJ8W70J2124NC1SVT708VD67
Run Details
Model:
Claude Sonnet 4.6 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
33.3s
Cost:
$0.056931
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
86.38%
Matches word count
(details)
98.72%
Dialogue to Total Word Ratio
(details)
92.5510%
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 spread the hand-drawn map across the park bench, anchoring the corners with a juice box and a half-eaten granola bar. She had been casing the target for three days. Three very exhausting days. "It's a bouncy castle situation," she said grimly. "We didn't account for a bouncy castle." Bill squinted at the crayon drawing. "Is that a clown?" "Two clowns." He removed his sunglasses and pinched the bridge of his nose. "Molly, I want out." "You don't want out. You want those presents." She tapped the map. "The gift table is positioned near the garden fence. Low security. Distracted adults. It's practically gift-wrapped." "It literally is gift-wrapped." "Exactly." Molly rolled up the map with practiced efficiency. "We go in during the musical chairs round. Everyone's focused on the chaos. Nobody watches the table." Bill stared at a nearby pigeon. "I went to art school for this." "You went to art school for two weeks before dropping out." "Still counts." Molly stood, tucking the map into her jacket. "We move at three o'clock. Wear something festive." "How festive?" "Party hat festive." Bill groaned loud enough to startle the pigeon.
created_at
"2026-02-24T22:27:15.146Z"
2/24/2026, 10:27:15 PM
model
"anthropic/claude-4.6-sonnet-20260217"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
880
moderation_latency
169
generation_time
33041
tokens_prompt
77
tokens_completion
1285
native_tokens_prompt
92
native_tokens_completion
3777
native_tokens_completion_images
(null)
native_tokens_reasoning
973
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
0.056931
router
(null)
provider_responses
0
endpoint_id
"83d802cb-44f2-45a0-a9d5-cb9bf79777c8"
id
"beac9109-08cc-4fa3-9878-68c396b9913c"
is_byok
false
latency
879
model_permaslug
"anthropic/claude-4.6-sonnet-20260217"
provider_name
"Amazon Bedrock"
status
200
api_type
"completions"
id
"gen-1771972035-MUQGn8T7CRnBZkbt1y2z"
upstream_id
"beac9109-08cc-4fa3-9878-68c396b9913c"
total_cost
0.056931
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
Evaluation details
Result
Evaluator
Details
Meta Data
86.38%
Matches word count
n/a
neededClean
false
words
189
98.72%
Dialogue to Total Word Ratio
Ratio: 53.37%, Deviation: 3.37%
neededClean
false
wordsTotal
193
wordsDialogue
103
92.5510%