NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCR5AB7R06FX16P3DX0J7K6
Run Details
Model:
Claude Opus 5 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
11.0s
Cost:
$0.013740
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
99.98%
Matches word count
(details)
99.54%
Dialogue to Total Word Ratio
(details)
99.7602%
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 spread the blueprints across the hood of the van, smoothing them with the reverence of a surgeon laying out instruments. They were not, technically, blueprints. They were a placemat from the Rainbow Fun Palace, crayoned over in three colors, with the ball pit marked in ominous red. Bill studied it, chewing a straw. The party began at two. Sixteen children, one exhausted magician, and a mountain of gift-wrapped treasure stacked beneath a piƱata shaped like a whale. "Entry through the bouncy castle," Molly said, tapping the placemat. Bill's eyebrows rose. Bouncy castles were, in his experience, unforgiving terrain. He had once lost a molar to one in Cleveland, during a christening job that still haunted him. But Molly's plan had the elegance of pure lunacy: two grown adults in dinosaur costumes, blending in among the inflatables, waiting for the moment the lights dimmed for cake. She handed him a foam tail. He accepted it with dignity. "Remember," she added, "no cake until the presents are in the van." Bill nodded solemnly, though privately he made no such promise. The mother had mentioned buttercream. There were limits to a man's professionalism, and buttercream sat comfortably, deliciously, on the far side of them.
created_at
"2026-07-25T13:41:45.255Z"
7/25/2026, 1:41:45 PM
model
"anthropic/claude-opus-5-20260723"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3775
moderation_latency
(null)
generation_time
10426
tokens_prompt
75
tokens_completion
364
native_tokens_prompt
93
native_tokens_completion
531
native_tokens_completion_images
(null)
native_tokens_reasoning
48
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
0.01374
router
(null)
provider_responses
0
endpoint_id
"76cb4608-f48c-483d-8da8-9957fb44244e"
id
"msg_011CdNsYQ2Y5wcwN1oBdhtkk"
is_byok
false
latency
1201
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-1784986905-jtMk1g9YZT8NUu77nYfU"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784986905-t2W7ccSShpQWF9inpSkd"
upstream_id
"msg_011CdNsYQ2Y5wcwN1oBdhtkk"
total_cost
0.01374
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
99.98%
Matches word count
n/a
neededClean
false
words
202
99.54%
Dialogue to Total Word Ratio
Ratio: 7.39%, Deviation: 2.61%
neededClean
false
wordsTotal
203
wordsDialogue
15
99.7602%