NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCQQY2E2896W2RGTGA8P1S6
Run Details
Model:
Claude Opus 5 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
11.5s
Cost:
$0.013940
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
97.63%
Matches word count
(details)
65.09%
Dialogue to Total Word Ratio
(details)
81.3570%
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," said Molly. "Fourteen hundred hours. Bouncy castle goes up, security goes down." "Security being?" "Barbara. Mum of the birthday boy. Wine spritzer at half twelve, second one at one, by two she couldn't identify her own husband in a line-up." "And the presents?" "Trestle table by the patio doors. Stacked like Christmas. I clocked at least eleven, one of them's shaped suspiciously like a Nintendo." "I'm not stealing from a seven-year-old, Molly." "He's turning eight." "Oh, well, in that case." "Don't get moral on me now, Bill, you nicked a defibrillator in March." "That was from a bank. Banks have insurance. Children have *feelings*." "Children have four hundred quid of unopened Lego and no receipt. It's the perfect crime." "What's my cover?" "Entertainer. I got you a costume." "What kind of costume?" "You'll like it." "Molly." "It's a clown." "Absolutely not." "There's a wig." "I'm allergic to wigs." "You're not allergic to wigs, you're allergic to *dignity loss*." "I have a reputation." "You have a caution for stealing a defibrillator." Bill sighed. "Do I have to do balloons?" "Three balloons, one magic trick, then you 'go to your van for props' and I'm out the side gate with the loot." "Fine. But I'm keeping the Nintendo."
created_at
"2026-07-25T13:34:26.39Z"
7/25/2026, 1:34:26 PM
model
"anthropic/claude-opus-5-20260723"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2572
moderation_latency
(null)
generation_time
11401
tokens_prompt
75
tokens_completion
352
native_tokens_prompt
93
native_tokens_completion
539
native_tokens_completion_images
(null)
native_tokens_reasoning
20
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
0.01394
router
(null)
provider_responses
0
endpoint_id
"76cb4608-f48c-483d-8da8-9957fb44244e"
id
"msg_011CdNrz3gnPB8hV3gTaUmWb"
is_byok
false
latency
1429
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-1784986466-7RyRbYk8vT8ag0yEevOE"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784986466-AfK5fnEZKi2B9rQWIUVp"
upstream_id
"msg_011CdNrz3gnPB8hV3gTaUmWb"
total_cost
0.01394
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
97.63%
Matches word count
n/a
neededClean
false
words
207
65.09%
Dialogue to Total Word Ratio
Ratio: 98.10%, Deviation: 8.10%
neededClean
false
wordsTotal
210
wordsDialogue
206
81.3570%