NC Bench
Overview
About
Tests
Models
Vendors
Compare
Run: 2026-02-24-01KJ8X5ANTK3198RCQ3YJ229H1
Run Details
Model:
Claude Opus 4.6 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
11.5s
Cost:
$0.010685
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
90.48%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
95.2419%
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," Molly said, unrolling a crayon-drawn blueprint across the dashboard. "The party starts at two. Balloon arch at the front door, bouncy castle on the east flank." "What about security?" Bill asked, squinting at the smudged drawings. "One labradoodle. Friendly but unpredictable. I've packed cheese slices for distraction purposes." "Professional. And the presents?" "Stacked on a folding table near the kitchen. We're looking at ten, maybe twelve wrapped parcels. Could be Legos, could be socks. High risk, unknown reward." "I didn't get into this business for certainty, Molly." "That's what I love about you, Bill. You're an idiot with conviction." "How do we get past the kids?" "Sugar crash. By three fifteen, they'll be face down in cake. We go in through the back gate dressed as entertainers." "I'm not wearing the clown suit again." "You're wearing the clown suit again." "Last time a child bit me." "Children bite, Bill. That's the cost of doing business." "Fine. What's our exit strategy?" "Gary waits in the minivan. We load the gifts and disappear before anyone notices." "What if someone notices?" "We sing Happy Birthday and walk out slowly." Bill nodded. "Flawless."
created_at
"2026-02-24T22:43:48.545Z"
2/24/2026, 10:43:48 PM
model
"anthropic/claude-4.6-opus-20260205"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2097
moderation_latency
219
generation_time
11201
tokens_prompt
77
tokens_completion
399
native_tokens_prompt
92
native_tokens_completion
409
native_tokens_completion_images
(null)
native_tokens_reasoning
70
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
0.010685
router
(null)
provider_responses
0
endpoint_id
"a8708fb9-08ea-43bb-a3b1-165c87ef09df"
id
"e8d81cd2-7160-40e4-abfb-c4ee02dcc024"
is_byok
false
latency
2061
model_permaslug
"anthropic/claude-4.6-opus-20260205"
provider_name
"Amazon Bedrock"
status
200
api_type
"completions"
id
"gen-1771973028-Nd5guVtuzZPV3CinHaGO"
upstream_id
"e8d81cd2-7160-40e4-abfb-c4ee02dcc024"
total_cost
0.010685
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
Evaluation details
Result
Evaluator
Details
Meta Data
90.48%
Matches word count
n/a
neededClean
false
words
190
100.00%
Dialogue to Total Word Ratio
Ratio: 90.05%, Deviation: 0.05%
neededClean
false
wordsTotal
191
wordsDialogue
172
95.2419%