NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCRN0V437DG1YYP9DXYX3QT
Run Details
Model:
Claude Opus 5 (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
10.3s
Cost:
$0.012765
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
51.74%
Dialogue to Total Word Ratio
(details)
75.8681%
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
"Bouncy castle's the weak point," said Molly. "It's a bouncy castle, Moll. It's not a castle." "It's got turrets." "It's got a puncture, is what it's got. Focus. The presents are stacked on the trestle table by the cake." "How many?" "Twenty-two kids invited, so twenty-two presents, minus whichever child's mum forgot, plus the one from the nan who buys for the whole street." "Twenty-two and a bit. What's the birthday boy's name?" "Tobias. He's seven and he's had a difficult year, apparently." "Don't do that." "Do what?" "Humanise him, Bill. You did it with the pensioner in Croydon and I had to drive us home while you wept into a stolen tea cosy." "That was a lovely cosy." "So we go in at four, during the magician." "Why the magician?" "Because everyone's watching the magician. It's called misdirection, Bill. It's the whole point of magicians." "And what if he's rubbish?" "Then they'll all be watching the presents, won't they, out of boredom. Fine. Half three. Pass the parcel." "I love pass the parcel." "You're not playing it, you're stealing it." "Can't I do both?" "Bill." "I'll bring a gift bag. Blend in." "Bring two. There's always the nan."
created_at
"2026-07-25T13:50:19.5Z"
7/25/2026, 1:50:19 PM
model
"anthropic/claude-opus-5-20260723"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2290
moderation_latency
(null)
generation_time
10150
tokens_prompt
75
tokens_completion
346
native_tokens_prompt
93
native_tokens_completion
492
native_tokens_completion_images
(null)
native_tokens_reasoning
39
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
0.012765
router
(null)
provider_responses
0
endpoint_id
"76cb4608-f48c-483d-8da8-9957fb44244e"
id
"msg_011CdNtCHr2HaitB5cBpaoJe"
is_byok
false
latency
1186
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-1784987419-xpi7OtKqCH2GBNbjNRbc"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784987419-Br4VGJsRxde1CIsjex9F"
upstream_id
"msg_011CdNtCHr2HaitB5cBpaoJe"
total_cost
0.012765
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
100.00%
Matches word count
n/a
neededClean
false
words
199
51.74%
Dialogue to Total Word Ratio
Ratio: 99.01%, Deviation: 9.01%
neededClean
false
wordsTotal
202
wordsDialogue
200
75.8681%