NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCR0JTRYJ0SV3E4QEG5F0GS
Run Details
Model:
Claude Opus 5 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
13.0s
Cost:
$0.013965
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
35.00%
Matches word count
(details)
0.11%
Dialogue to Total Word Ratio
(details)
17.5569%
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, strictly speaking, blueprints. They were a placemat from the Fun Zone Pizza Palace, illustrated with a maze, a word search, and a cartoon mouse holding a slice, but she had annotated it in red pen and that lent it authority. Bill studied the maze. He had been studying it for eleven minutes. The party began at two. Forty children, one bounce castle, and a folding table groaning under a ziggurat of wrapped boxes—remote-control helicopters, dolls that wept convincingly, a bicycle with tassels. Molly had scouted it twice, once as a balloon vendor and once, more successfully, as a woman looking for her lost dog. "The clown," she said, tapping the mouse. "The clown is our way in." Bill nodded slowly, which was his method of pretending to already know things. Molly outlined the plan. He would enter as Bobo the Magnificent, absorb the parents' attention with a routine involving three scarves and a wilted balloon giraffe, while she reversed the van to the patio doors and loaded the haul during the piñata frenzy, when no adult present would be looking at anything but the swinging donkey. "Any questions?" "Do I get cake?"
created_at
"2026-07-25T13:39:09.791Z"
7/25/2026, 1:39:09 PM
model
"anthropic/claude-opus-5-20260723"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
5733
moderation_latency
(null)
generation_time
12862
tokens_prompt
75
tokens_completion
385
native_tokens_prompt
93
native_tokens_completion
540
native_tokens_completion_images
(null)
native_tokens_reasoning
60
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
0.013965
router
(null)
provider_responses
0
endpoint_id
"76cb4608-f48c-483d-8da8-9957fb44244e"
id
"msg_011CdNsLvW2KKD8xxssrxVJk"
is_byok
false
latency
3556
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-1784986749-HIz2FHEfwv1jC4s4NGnT"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784986749-0ezvS1v8TgsToge3y7Eh"
upstream_id
"msg_011CdNsLvW2KKD8xxssrxVJk"
total_cost
0.013965
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
35.00%
Matches word count
n/a
neededClean
false
words
218
0.11%
Dialogue to Total Word Ratio
Ratio: 26.15%, Deviation: 16.15%
neededClean
false
wordsTotal
218
wordsDialogue
57
17.5569%