NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCQQNJYZS5BYK8W969CEY8X
Run Details
Model:
Claude Opus 5 (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
11.0s
Cost:
$0.016290
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
95.79%
Dialogue to Total Word Ratio
(details)
97.8938%
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
The van smelled of stale popcorn and ambition. Molly had spread the blueprints across the dashboard — a hand-drawn map of the Fenwick back garden, complete with paddling pool, trampoline, and a bouncy castle marked in red pen as HOSTILE TERRAIN. Bill was working his way through a bag of jelly babies he had allegedly purchased as a disguise prop, biting the heads off with the grim efficiency of a man who had made peace with his choices. Through the binoculars, the party unfolded in all its sticky glory. Forty-odd children orbiting a folding table stacked with parcels, each one wrapped in paper so metallic it looked like the loot from a Bond villain's vault. Somewhere among them, according to Molly's source, sat a limited-edition collectible worth more than Bill's van, his flat, and both his kidneys combined. Then the gate swung open and a figure in enormous shoes honked his way onto the lawn. "Clowns," Bill said. "I don't do clowns." Molly kept counting balloons. "You'll do clowns for forty grand." He chewed a jelly baby with unnecessary violence. Twenty minutes later, wearing a pointed hat and an expression of profound spiritual defeat, Bill went in through the trampoline.
created_at
"2026-07-25T13:34:17.702Z"
7/25/2026, 1:34:17 PM
model
"anthropic/claude-opus-5-20260723"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
4385
moderation_latency
(null)
generation_time
10828
tokens_prompt
75
tokens_completion
365
native_tokens_prompt
93
native_tokens_completion
633
native_tokens_completion_images
(null)
native_tokens_reasoning
62
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
0.01629
router
(null)
provider_responses
0
endpoint_id
"76cb4608-f48c-483d-8da8-9957fb44244e"
id
"msg_011CdNryPvRQLauNbkQ1Zb7i"
is_byok
false
latency
1256
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-1784986457-LpDuUAc3t2dA3n5CCi9B"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784986457-9gTaP5O78LjyrquSl0bt"
upstream_id
"msg_011CdNryPvRQLauNbkQ1Zb7i"
total_cost
0.01629
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
95.79%
Dialogue to Total Word Ratio
Ratio: 5.45%, Deviation: 4.55%
neededClean
false
wordsTotal
202
wordsDialogue
11
97.8938%