NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCQPRDQHVV80S7BMCBBR8N9
Run Details
Model:
Claude Opus 5 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
11.7s
Cost:
$0.014040
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
99.9980%
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 blueprints across the hood of the van, which was really just a laminated placemat from the pizzeria next door. "Bouncy castle here," she said, tapping it. "PiƱata here. Presents stacked on the folding table, northwest corner, guarded by one grandmother." "Grandmothers are the worst," Bill said. "They've got instincts." "She's eighty-six and she's had two glasses of sangria." "Still. My gran caught me stealing a biscuit in 1994 and I've never fully recovered." Molly ignored him and slid a clown wig across the placemat. "You'll wear this. You're Boffo. You do balloon animals for eleven minutes while I load the wagon." Bill held the wig at arm's length like it might bite. "I can't do balloon animals." "Do a snake." "A snake's just a balloon, Molly." "Then they'll assume you're avant-garde." He sighed and jammed the wig on, listing slightly to the left. Molly checked her watch, then the sky, then the small red wagon they'd stolen that morning from a garden centre in Doncaster. "One rule," she said. "Nobody touches the cake." "Why not?" "Because we're thieves, Bill, not monsters." Bill nodded solemnly, honked a bicycle horn he'd produced from nowhere, and marched toward the garden gate.
created_at
"2026-07-25T13:33:47.961Z"
7/25/2026, 1:33:47 PM
model
"anthropic/claude-opus-5-20260723"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3377
moderation_latency
(null)
generation_time
11361
tokens_prompt
75
tokens_completion
362
native_tokens_prompt
93
native_tokens_completion
543
native_tokens_completion_images
(null)
native_tokens_reasoning
46
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
0.01404
router
(null)
provider_responses
0
endpoint_id
"76cb4608-f48c-483d-8da8-9957fb44244e"
id
"msg_011CdNrwDmBAqu6jZwKZU7BL"
is_byok
false
latency
1761
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-1784986428-861xRydCJj4s8DyW8C0F"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784986428-fEWYlXkvVvpRUarUyIbK"
upstream_id
"msg_011CdNrwDmBAqu6jZwKZU7BL"
total_cost
0.01404
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
201
100.00%
Dialogue to Total Word Ratio
Ratio: 49.26%, Deviation: 0.74%
neededClean
false
wordsTotal
203
wordsDialogue
100
99.9980%