NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCPT5TKQNK4H4Q1GMDNQ8D4
Run Details
Model:
Claude Opus 5
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
10.4s
Cost:
$0.011365
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
99.38%
Matches word count
(details)
90.16%
Dialogue to Total Word Ratio
(details)
94.7687%
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 unrolled the blueprint across the hood of the Buick, smoothing it flat with her palm. It was, technically, a paper placemat from the Sizzler, but she'd drawn the bounce house in red pen and that counted for something. Bill leaned in, chewing a toothpick with the gravity of a man defusing a bomb, and studied the crayon-colored perimeter she'd labeled BALLOON ARCH — CHOKE POINT. The party started at two. By two-fifteen, the presents would be stacked on a folding table beside the piñata, unguarded except for a grandmother and a golden retriever named Pudding, both of whom Molly had assessed as neutralizable with sliced turkey. "Clowns," Bill said. "One clown." He shook his head slowly, the way men do when they've seen things. Molly ignored him and tapped the placemat twice. The plan was elegant. Bill would arrive as a magician, badly, and hold the crowd hostage with an eleven-minute rope trick. Molly would enter through the side gate dressed as an aunt — nobody ever counts the aunts — and load the gift bags into a wagon painted to look like part of the decorations. The dog barked somewhere down the street. Bill spat out his toothpick. "For the record," he said, "I hate cake."
created_at
"2026-07-25T13:18:11.288Z"
7/25/2026, 1:18:11 PM
model
"anthropic/claude-opus-5-20260723"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1537
moderation_latency
(null)
generation_time
10316
tokens_prompt
75
tokens_completion
308
native_tokens_prompt
93
native_tokens_completion
436
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
0.011365
router
(null)
provider_responses
0
endpoint_id
"76cb4608-f48c-483d-8da8-9957fb44244e"
id
"msg_011CdNqk9zHjpKJPdnXtBtp8"
is_byok
false
latency
1537
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-1784985491-W58ObqPkNYuUK9kiBaC9"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784985491-SybY0clEEdR4Nbz7v2ew"
upstream_id
"msg_011CdNqk9zHjpKJPdnXtBtp8"
total_cost
0.011365
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
99.38%
Matches word count
n/a
neededClean
false
words
205
90.16%
Dialogue to Total Word Ratio
Ratio: 4.33%, Deviation: 5.67%
neededClean
false
wordsTotal
208
wordsDialogue
9
94.7687%