NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCRH1KSM97S7CRKSYWGC3Z5
Run Details
Model:
Claude Opus 5 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 500 words with 70% dialogue
Duration:
23.0s
Cost:
$0.031340
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
0.49%
Matches word count
(details)
0.04%
Dialogue to Total Word Ratio
(details)
0.2658%
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 lopsided rectangle. "That's the trestle table with the sausage rolls. And that—" she stabbed the napkin hard enough to tear it, "—is the present pile." Bill leaned in, squinting. "Why's the present pile bigger than the house?" "Because it's *important*, Bill. It's not to scale, it's to emphasis." "Right. Only, if it's not to scale, how do I know where to park the van?" "You park the van where I tell you to park the van." "See, that's what you said in Dorking, and I ended up in a duck pond." Molly took a long breath through her nose. "The birthday girl is called Poppy. She's turning seven. Her father is something horrible in property, which means the presents are going to be obscene. Tablets. Scooters. One of those hoverboard things that sets fire to the airing cupboard." "So we're stealing from a child." "We're stealing from a *portfolio*. Poppy's fine. Poppy has a pony called Barnaby." "Barnaby," Bill repeated, unconvinced. "What's the entry?" "Side gate, eleven forty. The entertainer arrives at eleven forty-five. Chap called Mister Wobbles." "And Mister Wobbles won't notice two adults strolling past with a wheelbarrow?" "Mister Wobbles won't be there. Mister Wobbles has come down with a nasty case of me phoning his agent and cancelling." Bill sat back slowly. "No." "Yes." "Molly." "You've got the shoes already." "I've got the shoes because of a *misunderstanding*—" "You've got the shoes, you've got the nose, and you've got that thing you do with the balloons where the dog looks like it's been in an accident." "That dog is anatomically ambitious," Bill said stiffly. "And clowns are frightening now. There have been films. The children will scream." "The children screaming is the plan. That's the *whole* plan. Twenty-two seven-year-olds shrieking in a bouncy castle is what we in the trade call cover noise." "And where will you be while I'm being savaged by the under-eights?" "Behind the marquee, loading. Two minutes forty for the pile, ninety seconds to the gate, out before the cake." "Why before the cake?" "Because after the cake the mothers stop drinking prosecco and start *paying attention*." Bill turned the napkin around and studied it upside down, which did not help. "What about the dog?" "Barnaby's a pony." "There's a dog. I've seen it on the mother's Facebook. Big black thing with a face like a dropped pie." "Then you'll distract it." "With what?" "You'll be carrying eleven sausage rolls in your trouser pocket, Bill. You'll be the most popular man at the party." Bill was quiet a moment. Then, grudgingly: "Do I get to do the unicycle?" "Absolutely not." "I've been practising." "You fell into a hedge outside Greggs." "I got out of that hedge with dignity." "You got out of that hedge with a Cornish pasty in your hair." Molly folded the napkin and tucked it into her jacket. "Eleven forty. Wear the nose." "Fine." Bill drained his tea. "But if one of them pulls the wig, we're calling it a day."
created_at
"2026-07-25T13:48:09.217Z"
7/25/2026, 1:48:09 PM
model
"anthropic/claude-opus-5-20260723"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3843
moderation_latency
(null)
generation_time
22846
tokens_prompt
75
tokens_completion
860
native_tokens_prompt
93
native_tokens_completion
1235
native_tokens_completion_images
(null)
native_tokens_reasoning
58
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
0.03134
router
(null)
provider_responses
0
endpoint_id
"76cb4608-f48c-483d-8da8-9957fb44244e"
id
"msg_011CdNt2gm9BVR3HMur22vB7"
is_byok
false
latency
1813
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-1784987289-OJlGtPRp0Xn1PiyjyDCK"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784987289-oR89UE8VdBAqmbUzsEAZ"
upstream_id
"msg_011CdNt2gm9BVR3HMur22vB7"
total_cost
0.03134
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
0.49%
Matches word count
n/a
neededClean
false
words
527
0.04%
Dialogue to Total Word Ratio
Ratio: 82.52%, Deviation: 12.52%
neededClean
false
wordsTotal
532
wordsDialogue
439
0.2658%