NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCRH9WKZQCXS4BD0HPGDYCG
Run Details
Model:
Claude Opus 5 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
11.0s
Cost:
$0.013990
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
99.98%
Matches word count
(details)
51.52%
Dialogue to Total Word Ratio
(details)
75.7509%
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, the target," Bill said. "Ninth birthday. Ballpit. Forty-two RSVPs." "Forty-two presents." "Forty-one. Cousin Gavin brings a card." "What's our way in?" "Bouncy castle. Round the back, blind spot from the kitchen window, and nobody looks at a bouncy castle." "You're going to bounce into a heist." "I'm going to *traverse* a bouncy castle, Molly, with dignity." "And the parents?" "Sedated by small talk. There's a woman called Deirdre who corners people about her extension. Twelve minutes minimum. We move during Deirdre." "What about the birthday boy?" "Callum. Weak point. He's got a wooden sword and a grudge against everyone taller than four foot." "So we go in low." "We go in *crouched*. Like professionals." "And the presents come out how?" "Wheelie bin. I've lined it with a tablecloth so nothing rattles." "Bill, there's a magician." "...Say that again." "There's a magician. Two till three. Mr Marvello." "Marvello's straight, he wouldn't touch this." "Marvello owes me eighty quid and a rabbit." "Then Marvello does thirty minutes of misdirection while we clean out the conservatory." "And the cake?" "What about the cake?" "I want the cake, Bill." "It's shaped like a digger." "I want the digger cake." "Fine. We take the digger cake."
created_at
"2026-07-25T13:48:17.691Z"
7/25/2026, 1:48:17 PM
model
"anthropic/claude-opus-5-20260723"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2499
moderation_latency
(null)
generation_time
10861
tokens_prompt
75
tokens_completion
353
native_tokens_prompt
93
native_tokens_completion
541
native_tokens_completion_images
(null)
native_tokens_reasoning
19
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
0.01399
router
(null)
provider_responses
0
endpoint_id
"76cb4608-f48c-483d-8da8-9957fb44244e"
id
"msg_011CdNt3K5CL4Yio36SDjMCG"
is_byok
false
latency
1156
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-1784987297-9DRM6assxF8MfA5cpAzM"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784987297-aKyUzhRIC3lBquqOXhqX"
upstream_id
"msg_011CdNt3K5CL4Yio36SDjMCG"
total_cost
0.01399
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
99.98%
Matches word count
n/a
neededClean
false
words
202
51.52%
Dialogue to Total Word Ratio
Ratio: 99.02%, Deviation: 9.02%
neededClean
false
wordsTotal
205
wordsDialogue
203
75.7509%