NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCQZPZM0FVVA7QTRD8A0JRK
Run Details
Model:
Claude Opus 5 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
27.2s
Cost:
$0.059640
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
99.9992%
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 napkin across the table, smoothing it like a blueprint. Bill leaned in, squinting at her crayon diagram. "That's the bouncy castle," she said. "That's the piñata. And that, Bill, is forty-two presents stacked like Fort Knox with ribbons." "Why is the cake circled twice?" "Because I want cake." He sat back, arms folded, unconvinced. The café's espresso machine shrieked behind him, drowning out a toddler's tantrum. "We're robbing a seven-year-old." "We're robbing a seven-year-old's *parents*," Molly said. "Dentists. Two of them. They gave out floss last Halloween." Bill's jaw tightened. Justice, apparently, had a flavor, and it tasted like unsweetened dental tape. "Fine. What's my role?" "Clown." "Absolutely not. Never again." "You've got the shoes." "Those are orthopedic!" She slid a red foam nose across the table. It rolled, wobbled, and dropped into his coffee, where it bobbed accusingly. "Twenty minutes of balloon animals," she said, "while I load the van. Then we vanish before the parachute game." Bill fished out the nose, examined it, and sighed the sigh of a man who had once had dreams. "If any child asks me to make a giraffe," he warned, "I'm walking." "Deal. But you're carrying the piñata."
created_at
"2026-07-25T13:38:41.284Z"
7/25/2026, 1:38:41 PM
model
"anthropic/claude-opus-5-20260723"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
4119
moderation_latency
(null)
generation_time
27047
tokens_prompt
75
tokens_completion
675
native_tokens_prompt
93
native_tokens_completion
2367
native_tokens_completion_images
(null)
native_tokens_reasoning
352
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
0.05964
router
(null)
provider_responses
0
endpoint_id
"76cb4608-f48c-483d-8da8-9957fb44244e"
id
"msg_011CdNsJptNbCyRJ5VSCeNYB"
is_byok
false
latency
1419
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-1784986721-gpuxJS9XcTHAzTKE5iB6"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784986721-SEtu5GTmJHjGL1DengYP"
upstream_id
"msg_011CdNsJptNbCyRJ5VSCeNYB"
total_cost
0.05964
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
199
100.00%
Dialogue to Total Word Ratio
Ratio: 50.49%, Deviation: 0.49%
neededClean
false
wordsTotal
204
wordsDialogue
103
99.9992%