NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCRC93M8XTXTJ7CFPRJVG7S
Run Details
Model:
Claude Opus 5 (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
10.7s
Cost:
$0.014215
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
98.71%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
49.3562%
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 blueprint across the hood of the van, which was really just a napkin with a bouncy castle drawn on it. "Bounce house here," she said. "PiƱata here. Presents stacked on the folding table, unguarded, like fruit in Eden." "There'll be parents," Bill said. "There'll be *sangria*. By two o'clock they won't be able to identify their own children, let alone us." "And the birthday boy? Kids notice things." "Kids are the least credible witnesses on earth. Last year a six-year-old told police I was nine feet tall and made of spaghetti." Bill chewed his thumbnail. "I still say we go in as clowns." "We are not going in as clowns." "Nobody looks a clown in the eye, Molly. It's basic psychology." "Nobody *hires* a clown anymore either. It's magicians now. Balloon animals. Sad men with doves." "I can do a dove." "You have a pigeon in a shoebox." "He's got range." Molly folded the napkin and tucked it into her jacket. "You'll be Uncle Terry. Nobody knows who Uncle Terry is, and everyone's too polite to ask. You carry the gifts to the car because you're 'organizing.'" Bill brightened. "And you?" "I'll be crying by the buffet. Parents avoid crying women like landmines."
created_at
"2026-07-25T13:45:33.052Z"
7/25/2026, 1:45:33 PM
model
"anthropic/claude-opus-5-20260723"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3631
moderation_latency
(null)
generation_time
10594
tokens_prompt
75
tokens_completion
360
native_tokens_prompt
93
native_tokens_completion
550
native_tokens_completion_images
(null)
native_tokens_reasoning
51
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
0.014215
router
(null)
provider_responses
0
endpoint_id
"76cb4608-f48c-483d-8da8-9957fb44244e"
id
"msg_011CdNsqBpnrwTx8zC8zzMW5"
is_byok
false
latency
1481
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-1784987133-2U8zYnZwrlc4ciO5OfWy"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784987133-IVfiTVRqaTcZivm610cs"
upstream_id
"msg_011CdNsqBpnrwTx8zC8zzMW5"
total_cost
0.014215
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
98.71%
Matches word count
n/a
neededClean
false
words
206
0.00%
Dialogue to Total Word Ratio
Ratio: 79.33%, Deviation: 29.33%
neededClean
false
wordsTotal
208
wordsDialogue
165
49.3562%