NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCR1TM51C61627HMR71S2GP
Run Details
Model:
Claude Opus 5 (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 500 words with 70% dialogue
Duration:
21.7s
Cost:
$0.029615
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
14.30%
Matches word count
(details)
0.35%
Dialogue to Total Word Ratio
(details)
7.3238%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 500 word scene that has 70% 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 napkin across the table and smoothed it flat with the side of her hand. "That's the bouncy castle," she said, tapping a wobbly circle. "That's the trestle table. And that, Bill, is a hundred and forty quid of unopened Lego." "It's a birthday party." "It's a vault with balloons on it." Bill set down his tea very carefully, the way a man does when he's decided to be the reasonable one. "Molly. We did the Ardmore jewellers. We did the wine auction. We did that thing with the swan." "We don't talk about the swan." "And now we're robbing a seven-year-old." "We're robbing a seven-year-old's *guests*," Molly said. "There's a moral distinction, and I'd thank you to respect it. Every present on that table was bought by a stressed parent in a garage forecourt at nine o'clock last night. Nobody wants them. Nobody will mourn them. It's practically a mercy." "And the birthday boy?" "Gets to be the kid whose party got robbed. Do you know what that's worth? He'll dine out on it till he's forty. We're giving him a personality." Bill rubbed his eyes. "How do we get in?" "Balloon animals." She produced a bicycle pump from her bag and laid it on the napkin like a Colt revolver. "You're Bingo. I'm Bingo's assistant, Doreen." "Why do you get to be the assistant?" "Because assistants carry the big bag, Bill, and the big bag is the entire operation. Try to keep up." "I can't make balloon animals." "You make one dog. One. Then you say your wrist's gone and you do close-up magic for the rest of the hour." "I can't do close-up magic." "You can palm a wedding ring off a woman's hand in a crowded lift." "That's different." "That's *identical*, Bill, you've just never had an audience shouting 'do it again.'" She leaned forward. "Two o'clock, cake comes out. Every adult in that garden turns to look at the cake, because that's the law of cakes. Twenty seconds of total blindness. I wheel the present table behind the shed—" "Wheel it." "It's got castors. I checked on Tuesday." "You've been surveilling a birthday party since Tuesday." "I've been *working*." Molly sat back, wounded. "Then out through the side gate, into the ice cream van, and we're on the motorway before anyone's cut the first slice." "We have an ice cream van." "We have Terry's ice cream van, and Terry owes me, and Terry's chimes are broken so it just plays a sort of long groan, which frankly suits the mood." Bill was quiet for a moment. Then: "There'll be a bag for life full of party bags by the back door. Little ones. Sweets, bubbles, plastic whistle." "What about them?" "We leave them. And we leave one present. The big one, whatever it is. So the kid gets something." Molly looked at him for a long time, then folded the napkin and slid it into her pocket. "Bill," she said, standing, "you're going soft, and one day it'll get us both nicked." "Is that a no?" "That's a two o'clock. Bring a red nose."
created_at
"2026-07-25T13:39:50.542Z"
7/25/2026, 1:39:50 PM
model
"anthropic/claude-opus-5-20260723"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2921
moderation_latency
(null)
generation_time
21625
tokens_prompt
75
tokens_completion
803
native_tokens_prompt
93
native_tokens_completion
1166
native_tokens_completion_images
(null)
native_tokens_reasoning
53
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
0.029615
router
(null)
provider_responses
0
endpoint_id
"76cb4608-f48c-483d-8da8-9957fb44244e"
id
"msg_011CdNsPvcJk17qZ1auWzYDG"
is_byok
false
latency
1255
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-1784986790-T7Vs7sNdIFKEdvEr8BJd"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784986790-WSkV4xRc9xLgHoGHyUFA"
upstream_id
"msg_011CdNsPvcJk17qZ1auWzYDG"
total_cost
0.029615
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
14.30%
Matches word count
n/a
neededClean
false
words
521
0.35%
Dialogue to Total Word Ratio
Ratio: 80.65%, Deviation: 10.65%
neededClean
false
wordsTotal
527
wordsDialogue
425
7.3238%