NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCQZR2WGCAVQGKN77Z76ESY
Run Details
Model:
Claude Opus 5 (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
13.7s
Cost:
$0.019140
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
93.65%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
96.8228%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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 plan across the van's hood, smoothing it with the reverence of a surgeon, though it was drawn in crayon because Bill had lost the pens again. The Hendersons' back garden, rendered in waxy orange. A bouncy castle. A trestle table. And there, stacked in a glittering ziggurat beside the paddling pool, the target: forty-one wrapped presents for one seven-year-old named Tobias. Bill chewed a sausage roll he had already stolen, as a warm-up. "Bouncy castle's the choke point," Molly said. He nodded, spraying pastry. In his lap sat a wig, a red nose, and shoes long enough to require their own postcode. "I'll be the clown." "You'll be the diversion. Clowns get photographed." She circled the garden gate twice in orange, then drew what appeared to be a dog and, after consideration, gave it fangs. The Hendersons owned a chihuahua named Mr. Biscuit, and Molly had learned in her twenty years of professional larceny that the small ones were always the problem. Bill produced a bag of balloons and began inflating one with the grim focus of a man defusing a bomb. It squealed free of his fingers, farted across the windscreen, and died on the dashboard. Molly closed her eyes and counted, silently, to eleven.
created_at
"2026-07-25T13:38:42.403Z"
7/25/2026, 1:38:42 PM
model
"anthropic/claude-opus-5-20260723"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3991
moderation_latency
(null)
generation_time
13614
tokens_prompt
75
tokens_completion
372
native_tokens_prompt
93
native_tokens_completion
747
native_tokens_completion_images
(null)
native_tokens_reasoning
60
native_tokens_cached
0
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
num_fetches
(null)
web_search_engine
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"end_turn"
service_tier
"default"
usage
0.01914
router
(null)
provider_responses
0
endpoint_id
"76cb4608-f48c-483d-8da8-9957fb44244e"
id
"msg_011CdNsJuPzCFEzwmV92YaMw"
is_byok
false
latency
1328
model_permaslug
"anthropic/claude-opus-5-20260723"
provider_name
"Amazon Bedrock"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.18.0; linux; x64))"
http_referer
(null)
request_id
"req-1784986722-ktgBs94XlC2OkzjewFA7"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784986722-nunW2b498HH40nhEZRDf"
upstream_id
"msg_011CdNsJuPzCFEzwmV92YaMw"
total_cost
0.01914
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
response_cache_source_id
(null)
data_region
"global"
Evaluation details
Result
Evaluator
Details
Meta Data
93.65%
Matches word count
n/a
neededClean
false
words
209
100.00%
Dialogue to Total Word Ratio
Ratio: 10.80%, Deviation: 0.80%
neededClean
false
wordsTotal
213
wordsDialogue
23
96.8228%