NC Bench
Overview
About
Tests
Models
Vendors
Compare
Run: 2026-02-24-01KJ8X6XM97S1VJD4136DDGTV1
Run Details
Model:
Claude Opus 4.6 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
11.2s
Cost:
$0.009960
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
99.98%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
99.9920%
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 dashboard, which appeared to have been sketched in crayon. Bill squinted at it through his ski mask, which he had already put on forty minutes too early. "So the bouncy castle is here," Molly said, tapping a lumpy purple rectangle. "That's our primary obstacle." "I hate bouncy castles," Bill muttered. "No traction." She ignored him and traced a finger toward what looked like a wobbly star. "The presents are stacked on a table near the piƱata station. We go in through the back gate, grab the loot, and get out before the clown arrives at two." Bill shifted nervously in the passenger seat. "What if the clown's early?" "Clowns are never early. That's like the one thing you can count on in this world." "And the kids?" "Hopped up on sugar. They won't notice a thing." Molly folded the map with surgical precision, creasing it into a neat square. "Just don't make eye contact with the birthday boy. Kids sense fear." Bill pulled a large garbage bag from under his seat and held it open experimentally. "This feels wrong, Molly." She started the engine and grinned. "That's what makes it fun."
created_at
"2026-02-24T22:44:40.723Z"
2/24/2026, 10:44:40 PM
model
"anthropic/claude-4.6-opus-20260205"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1337
moderation_latency
217
generation_time
10917
tokens_prompt
77
tokens_completion
371
native_tokens_prompt
92
native_tokens_completion
380
native_tokens_completion_images
(null)
native_tokens_reasoning
68
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
0.00996
router
(null)
provider_responses
0
endpoint_id
"a8708fb9-08ea-43bb-a3b1-165c87ef09df"
id
"2a0402dc-0645-44be-9aa4-6ecab107afa2"
is_byok
false
latency
1332
model_permaslug
"anthropic/claude-4.6-opus-20260205"
provider_name
"Amazon Bedrock"
status
200
api_type
"completions"
id
"gen-1771973080-gL0GwBVwdW8AnLN43f2i"
upstream_id
"2a0402dc-0645-44be-9aa4-6ecab107afa2"
total_cost
0.00996
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
Evaluation details
Result
Evaluator
Details
Meta Data
99.98%
Matches word count
n/a
neededClean
false
words
198
100.00%
Dialogue to Total Word Ratio
Ratio: 50.25%, Deviation: 0.25%
neededClean
false
wordsTotal
199
wordsDialogue
100
99.9920%