NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCR5FJA899SY5SSJSY3M80F
Run Details
Model:
Claude Opus 5 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
19.1s
Cost:
$0.014240
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
97.63%
Matches word count
(details)
99.30%
Dialogue to Total Word Ratio
(details)
98.4657%
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 blueprints spread across the card table were, technically, a napkin from a pizzeria, and the pizzeria's logo obscured what Bill insisted was the bouncy castle. Molly studied it with the grim intensity of a general surveying a doomed valley. Twenty-two children. Three sheet cakes. One hired magician of uncertain skill and, according to reconnaissance, considerable body odor. She tapped the napkin twice. "The gift table sits here. Nine minutes, tops." Bill nodded, chewing a pen cap. The plan was elegant in the way that all their plans were elegant, which is to say it involved a rented clown costume, a stolen shopping trolley, and a fundamental misunderstanding of how party parents behave when threatened. He had spent forty dollars on balloon animals he could not make. Molly had spent nothing, because Molly had scruples about her own money. Outside, rain drummed on the fire escape. Inside, the radiator clanked like a hostage. "Kids can't identify us," Bill offered. "They're unreliable witnesses." Molly did not look up. She was calculating the weight of eleven wrapped bicycles, the resale value of a Nintendo, the precise moment at which a mother's suspicion curdles into violence. Somewhere in that arithmetic sat their retirement, gleaming, ribboned, and defended by sugar-crazed seven-year-olds.
created_at
"2026-07-25T13:41:50.293Z"
7/25/2026, 1:41:50 PM
model
"anthropic/claude-opus-5-20260723"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
8104
moderation_latency
(null)
generation_time
19037
tokens_prompt
75
tokens_completion
382
native_tokens_prompt
93
native_tokens_completion
551
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
0.01424
router
(null)
provider_responses
0
endpoint_id
"76cb4608-f48c-483d-8da8-9957fb44244e"
id
"msg_011CdNsYnpjs1EFU7sJ7S7aZ"
is_byok
false
latency
5640
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-1784986910-nYrdsLRMWwdEWUriKSMJ"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784986910-YpYkjVQekGufCyNaHKMZ"
upstream_id
"msg_011CdNsYnpjs1EFU7sJ7S7aZ"
total_cost
0.01424
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
97.63%
Matches word count
n/a
neededClean
false
words
207
99.30%
Dialogue to Total Word Ratio
Ratio: 7.11%, Deviation: 2.89%
neededClean
false
wordsTotal
211
wordsDialogue
15
98.4657%