NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCPYCP8GPQGBVFCNF3WXGFR
Run Details
Model:
Claude Opus 5
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
9.8s
Cost:
$0.011040
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
77.86%
Dialogue to Total Word Ratio
(details)
88.9280%
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 blueprints spread across the kitchen table were, in fact, a paper placemat from Chuckles Pizza Palace, but Molly had annotated it heavily in red pen. Bill leaned over her shoulder, chewing a pencil he'd found somewhere unsanitary, and studied the layout of the birthday venue with the gravity of a man defusing a bomb. The ball pit was circled three times. Molly tapped the northeast corner, where a crude drawing of a bouncy castle sagged under the weight of her ambitions. Presents accumulated there, she explained, in a glittering pyramid, guarded by nothing more formidable than a folding table and an aunt named Deirdre. "Deirdre drinks," Bill said. "Deirdre is our window." They had planned for the piƱata, for the sugar-crazed stampede that would follow, for the eleven-minute blindness of every adult in the room when the candy hit the floor. They had planned for the clown, who was allegedly former military. They had not planned for the possibility that a seven-year-old might notice two grown adults in matching cargo shorts loitering near the goodie bags, and this oversight would eventually cost them everything. Bill folded the placemat with reverence, tucked it into his sock, and reached for the balloons.
created_at
"2026-07-25T13:20:29.538Z"
7/25/2026, 1:20:29 PM
model
"anthropic/claude-opus-5-20260723"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1908
moderation_latency
(null)
generation_time
9594
tokens_prompt
75
tokens_completion
312
native_tokens_prompt
93
native_tokens_completion
423
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
0.01104
router
(null)
provider_responses
0
endpoint_id
"76cb4608-f48c-483d-8da8-9957fb44244e"
id
"msg_011CdNqvLsAnT4vYQctTNLzz"
is_byok
false
latency
1891
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-1784985629-RGZkJNlOQEGM2V5HjI3M"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784985629-EHBDM0op99ryl8xdGzck"
upstream_id
"msg_011CdNqvLsAnT4vYQctTNLzz"
total_cost
0.01104
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
77.86%
Dialogue to Total Word Ratio
Ratio: 2.93%, Deviation: 7.07%
neededClean
false
wordsTotal
205
wordsDialogue
6
88.9280%