NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCQT1WF0KKA8Q29B004ZG1G
Run Details
Model:
Claude Opus 5 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
10.5s
Cost:
$0.013965
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
91.12%
Dialogue to Total Word Ratio
(details)
95.5589%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% 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
"Nine kids, one bouncy castle, and a piƱata shaped like a shark," Molly said. "That's the layout." "And the presents?" "Trestle table, back garden, guarded by a grandmother." "Guarded how?" "She's got a folding chair and a look." Bill winced. "I hate a look. What's the plan?" "You go in as the magician." "I don't know any magic." "You know how to make a wallet disappear." "That's not the same audience, Molly. Children heckle." "Then be the clown." "Absolutely not. Clowns get photographed. Do you know how many mums are on that street group chat?" "Fine. You're the balloon man." "Balloon man I can do. Balloon man has gloves, which is forensics sorted, and a big bag, which is transport sorted." Bill paused. "What are you doing while I'm twisting poodles?" "I'm the aunt nobody recognises. I compliment the sponge cake, I say 'hasn't he grown,' and I load the wheelbarrow." "There's a wheelbarrow?" "There's a shed." "Molly, that's beautiful." "One rule, Bill. We don't take the birthday boy's present." "Why not?" "Because I'm a thief, not a monster." Bill nodded slowly. "Which one's his?" "The bike." "The bike's worth two hundred quid." "Bill." "I'm just saying the number out loud."
created_at
"2026-07-25T13:35:35.83Z"
7/25/2026, 1:35:35 PM
model
"anthropic/claude-opus-5-20260723"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2932
moderation_latency
(null)
generation_time
10381
tokens_prompt
75
tokens_completion
345
native_tokens_prompt
93
native_tokens_completion
540
native_tokens_completion_images
(null)
native_tokens_reasoning
27
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_011CdNs59omkMVTwYyNS8JAC"
is_byok
false
latency
1402
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-1784986535-FKKgvXe0LYQ7OohMB9Br"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784986535-C55SG7FD2X9HELgpv7ay"
upstream_id
"msg_011CdNs59omkMVTwYyNS8JAC"
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
100.00%
Matches word count
n/a
neededClean
false
words
201
91.12%
Dialogue to Total Word Ratio
Ratio: 95.52%, Deviation: 5.52%
neededClean
false
wordsTotal
201
wordsDialogue
192
95.5589%