NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCPQDNGRJAYHN7HK329JJE5
Run Details
Model:
Claude Opus 5
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
10.6s
Cost:
$0.011665
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
86.38%
Matches word count
(details)
96.43%
Dialogue to Total Word Ratio
(details)
91.4057%
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, technically, a napkin from Chuck E. Cheese with a jam stain in the corner where the ball pit should have been. Bill had drawn the ball pit anyway, plus an arrow labeled DANGER, which Molly considered generous. The real danger was the parents. She traced the perimeter with a chewed pencil, marking the bouncy castle, the folding tables, the sagging streamers, and the sacred mound of gift bags stacked beside the piƱata like tribute to a very small king. Twenty-two presents. Possibly twenty-three, if Aunt Deborah showed up, which she always did, drunk and bearing gift cards. Bill had bought clown costumes. This was the part Molly had been dreading, because Bill had bought them in a size that suggested he believed clowns were structurally hollow. "We're not clowns." "Everyone loves clowns." "Nobody has ever loved a clown." He folded the costume back into its bag with the wounded dignity of a man whose dreams were routinely audited. Molly softened, slightly, and slid him the napkin, tapping the arrow he'd drawn. They would go in as balloon artists. They would leave in eleven minutes, four seconds, and one stolen wagon, laden with wrapping paper and unearned joy, before the cake was even cut.
created_at
"2026-07-25T13:16:41.013Z"
7/25/2026, 1:16:41 PM
model
"anthropic/claude-opus-5-20260723"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1849
moderation_latency
(null)
generation_time
10522
tokens_prompt
75
tokens_completion
321
native_tokens_prompt
93
native_tokens_completion
448
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
0.011665
router
(null)
provider_responses
0
endpoint_id
"76cb4608-f48c-483d-8da8-9957fb44244e"
id
"msg_011CdNqdW2rJR1jFu3JvuMCp"
is_byok
false
latency
1849
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-1784985401-QSUvkcjnPfS9t8ziK6Qd"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784985401-aV6zzGKcihsIyXXYw6Rk"
upstream_id
"msg_011CdNqdW2rJR1jFu3JvuMCp"
total_cost
0.011665
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
86.38%
Matches word count
n/a
neededClean
false
words
211
96.43%
Dialogue to Total Word Ratio
Ratio: 5.63%, Deviation: 4.37%
neededClean
false
wordsTotal
213
wordsDialogue
12
91.4057%