NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCQW355RTT1GP5FQMK9YKN2
Run Details
Model:
Claude Opus 5 (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
11.9s
Cost:
$0.013915
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
99.92%
Matches word count
(details)
92.54%
Dialogue to Total Word Ratio
(details)
96.2305%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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 blueprint across the hood of the van. It was a napkin. "That's the bouncy castle," she said, tapping a grease stain. "That's the piƱata. And that, Bill, is our exit." "It's a hedge." "It's a *tactical* hedge." Bill lowered his binoculars. Twenty-three children were currently orbiting a folding table stacked with glittering, ribboned loot. "There's a clown," he said. "So?" "I don't like clowns, Moll. They've got no tells. You can't read a face that's already painted." "You're forty-six." "Trauma doesn't check ID." She handed him a party hat and a plastic trumpet. He stared at them the way other men stare at divorce papers. "Blend in," she said. "Nobody suspects a man having fun." "Nobody's ever suspected me of that in my life." "Sing 'Happy Birthday.' Loudly. While I reverse the van to the gift table." "And if the mother asks whose parent I am?" "Say you're Uncle Gary. Every family has an Uncle Gary nobody invited." Bill sighed, snapping the elastic under his chin. "One hour. Then we're gone." "Ninety seconds," Molly corrected, starting the engine. "We're professionals." The clown turned, slowly, and looked directly at the van. Bill whimpered. "He knows."
created_at
"2026-07-25T13:36:42.669Z"
7/25/2026, 1:36:42 PM
model
"anthropic/claude-opus-5-20260723"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
4193
moderation_latency
(null)
generation_time
11800
tokens_prompt
75
tokens_completion
365
native_tokens_prompt
93
native_tokens_completion
538
native_tokens_completion_images
(null)
native_tokens_reasoning
52
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
0.013915
router
(null)
provider_responses
0
endpoint_id
"76cb4608-f48c-483d-8da8-9957fb44244e"
id
"msg_011CdNsA6y1R7fSqxC9YnnDa"
is_byok
false
latency
2010
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-1784986602-Pk9QOgnXlWdEUTy6pUqO"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784986602-6Hul5bISz5jbYHZ2HeIB"
upstream_id
"msg_011CdNsA6y1R7fSqxC9YnnDa"
total_cost
0.013915
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
99.92%
Matches word count
n/a
neededClean
false
words
197
92.54%
Dialogue to Total Word Ratio
Ratio: 55.28%, Deviation: 5.28%
neededClean
false
wordsTotal
199
wordsDialogue
110
96.2305%