NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCPV2KXT0C8D5Y7GHXMQ7QG
Run Details
Model:
Claude Opus 5
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
10.5s
Cost:
$0.012515
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
20.19%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
60.0948%
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
The blueprint spread across the kitchen table was, technically, a birthday party invitation, but Bill had annotated it heavily in red pen. Arrows. Circles. A skull and crossbones drawn over the bouncy castle for reasons he had not yet explained. Molly leaned over the paper, squinting at his handwriting, which resembled a seismograph reading during a modest earthquake. The gift table, he had determined, sat beneath the gazebo in the Hendersons' back garden, sandwiched between a piñata and a folding chair full of grandmothers. Fourteen presents. Possibly fifteen, if the cousins came through. "Grandmothers," she said, "are the problem." Bill nodded gravely and tapped the piñata. The plan, as he had constructed it over three days and an alarming quantity of instant coffee, involved a diversionary sugar crash, one clown costume acquired under false pretenses from a party supply shop in Fenwick, and a wheelbarrow disguised as a novelty gift. The wheelbarrow was parked in the alley already, wrapped in paper printed with dinosaurs, a bow the size of a hubcap taped to its handle. Molly considered the skull and crossbones for a long moment. She thought about the grandmothers again, their sensible shoes, their terrible patience, their willingness to hold a child's hand for hours. "We're going to jail," she said. Bill smiled and reached for the clown wig.
created_at
"2026-07-25T13:18:40.771Z"
7/25/2026, 1:18:40 PM
model
"anthropic/claude-opus-5-20260723"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1891
moderation_latency
(null)
generation_time
10447
tokens_prompt
75
tokens_completion
347
native_tokens_prompt
93
native_tokens_completion
482
native_tokens_completion_images
(null)
native_tokens_reasoning
0
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
0.012515
router
(null)
provider_responses
0
endpoint_id
"76cb4608-f48c-483d-8da8-9957fb44244e"
id
"msg_011CdNqnKvtb1e6ZLRGVfBqf"
is_byok
false
latency
1889
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-1784985520-vA7wH9l9sqY8m5XD8MT6"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784985520-r8wzrsGT7IpZGTZlPXkI"
upstream_id
"msg_011CdNqnKvtb1e6ZLRGVfBqf"
total_cost
0.012515
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
20.19%
Matches word count
n/a
neededClean
false
words
220
100.00%
Dialogue to Total Word Ratio
Ratio: 10.00%, Deviation: 0.00%
neededClean
false
wordsTotal
220
wordsDialogue
22
60.0948%