NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCQVHF98T2Z2AK1DDZQSBBJ
Run Details
Model:
Claude Opus 5 (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
15.3s
Cost:
$0.015515
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
99.98%
Matches word count
(details)
99.85%
Dialogue to Total Word Ratio
(details)
99.9183%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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 diner table and smoothed it flat with the side of her fork, revealing a floor plan drawn in ketchup and mustard, which was, she felt, an underappreciated medium. Bill leaned in. The party house sat on Ferndale Crescent: two stories, hedge maze of a back garden, and a garage that the birthday boy's mother had, according to three weeks of patient surveillance, converted into a gift-staging area of almost military organization. Ribbons sorted by color. Gift bags nested like Russian dolls. Bill had wept a little when he saw the photographs. "Bouncy castle's the weak point," Molly said, tapping a mustard blob. The inflatable would be positioned against the garage's side window. Thirty children would be screaming inside it. No adult voluntarily approaches a bouncy castle containing thirty screaming children; this was established science. They would go in through the window, out through the window, and the loot would travel down a slide of Bill's own design, into the hedge. He was already shaking his head, because he knew what came next. "We'll need the clown suit." "Absolutely not." "Balloon animals." Molly stabbed a pancake. "Learn them." Bill ordered another coffee, defeated.
created_at
"2026-07-25T13:36:24.562Z"
7/25/2026, 1:36:24 PM
model
"anthropic/claude-opus-5-20260723"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
5630
moderation_latency
(null)
generation_time
14279
tokens_prompt
75
tokens_completion
422
native_tokens_prompt
93
native_tokens_completion
602
native_tokens_completion_images
(null)
native_tokens_reasoning
110
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
0.015515
router
(null)
provider_responses
0
endpoint_id
"76cb4608-f48c-483d-8da8-9957fb44244e"
id
"msg_011CdNs8pdUAan68xX14R7Ti"
is_byok
false
latency
1630
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-1784986585-z5B9OPhg4aNO1WZE6mGB"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784986585-mwQCDhDQsDkNZxEDBlGt"
upstream_id
"msg_011CdNs8pdUAan68xX14R7Ti"
total_cost
0.015515
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
198
99.85%
Dialogue to Total Word Ratio
Ratio: 8.04%, Deviation: 1.96%
neededClean
false
wordsTotal
199
wordsDialogue
16
99.9183%