NC Bench
Overview
About
Tests
Models
Vendors
Compare
Run: 2026-02-24-01KJ8V6TD2P8BN42K1DP1JQH2G
Run Details
Model:
Claude Opus 4.6 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
38.4s
Cost:
$0.074835
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
99.98%
Matches word count
(details)
99.42%
Dialogue to Total Word Ratio
(details)
99.7011%
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 crayon-drawn map across the dashboard of their dented minivan. The target: 47 Elmwood Drive. Timmy Henderson's seventh birthday. Approximately thirty wrapped presents, estimated street value of four hundred dollars counting gift cards. "We go in through the back gate at three fifteen," Molly said, tapping the map with a breadstick. "That's when the magician starts. Every kid and parent will be watching some guy pull scarves out of his sleeve." Bill squinted at the map. "Is that a dog or a trampoline?" "Bouncy castle. Focus." "Remind me why we don't just walk in the front door like normal people?" "Normal people bring presents, Bill. We take them." She bit the breadstick in half. "I've rented matching clown costumes. Nobody questions a clown at a children's party." Bill scratched his chin. "People absolutely question clowns at children's parties." "Fine. Nobody stops a clown. They're too afraid." "That part I believe." Molly folded the map with surgical precision. Outside, afternoon sun glinted off a mailbox shaped like a dinosaur. Somewhere nearby, a child's laughter drifted through the suburbs, blissfully unaware that the worst clowns in the tristate area were about to crash the party of a lifetime.
created_at
"2026-02-24T22:09:40.266Z"
2/24/2026, 10:09:40 PM
model
"anthropic/claude-4.6-opus-20260205"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1558
moderation_latency
214
generation_time
38132
tokens_prompt
77
tokens_completion
1441
native_tokens_prompt
92
native_tokens_completion
2975
native_tokens_completion_images
(null)
native_tokens_reasoning
1114
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
0.074835
router
(null)
provider_responses
0
endpoint_id
"a8708fb9-08ea-43bb-a3b1-165c87ef09df"
id
"55fd862e-abbd-41df-81e8-f2e97050975f"
is_byok
false
latency
1526
model_permaslug
"anthropic/claude-4.6-opus-20260205"
provider_name
"Amazon Bedrock"
status
200
api_type
"completions"
id
"gen-1771970980-FfAiJocWpvZ1mXifT2f5"
upstream_id
"55fd862e-abbd-41df-81e8-f2e97050975f"
total_cost
0.074835
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
99.42%
Dialogue to Total Word Ratio
Ratio: 47.24%, Deviation: 2.76%
neededClean
false
wordsTotal
199
wordsDialogue
94
99.7011%