NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCRB7RJVWYWQM2VRKNE17H5
Run Details
Model:
Claude Opus 5 (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
14.0s
Cost:
$0.019915
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
95.99%
Matches word count
(details)
99.96%
Dialogue to Total Word Ratio
(details)
97.9748%
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 flattened the flyer across the van's hood, smoothing it with the reverence other people reserved for treasure maps. *Tobias Perkins, Age 7, Pirate Party, 2 P.M., No Gifts Necessary.* An outrageous lie. There were always gifts. Suburban grandmothers could not be stopped; they arrived like weather, arms loaded with wrapped rectangles and gift receipts, and by three o'clock the sunroom would be a glittering mountain of untouched merchandise. Bill emerged from the back of the van in full clown regalia, wig askew, one enormous shoe already flapping loose at the toe. "Nobody suspects a clown," he said. Molly studied him the way a surgeon studies an infection. The plan was elegant. Bill would enter through the front, honk, juggle badly, and herd every child into the backyard for balloon animals. Molly, meanwhile, would slip through the side gate with two laundry sacks and clear the sunroom in under ninety seconds. The bouncy castle would drown out any noise. Parents would be filming. Nobody films the presents. "You're allergic to balloons," she reminded him. "Then I'll hold my breath." She handed him a whistle, a bag of streamers, and an EpiPen, which he tucked into his polka-dotted sleeve. "Presents first," Molly said. "Cake second." Bill nodded solemnly. "Deal."
created_at
"2026-07-25T13:44:58.905Z"
7/25/2026, 1:44:58 PM
model
"anthropic/claude-opus-5-20260723"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
4171
moderation_latency
(null)
generation_time
13905
tokens_prompt
75
tokens_completion
410
native_tokens_prompt
93
native_tokens_completion
778
native_tokens_completion_images
(null)
native_tokens_reasoning
82
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
0.019915
router
(null)
provider_responses
0
endpoint_id
"76cb4608-f48c-483d-8da8-9957fb44244e"
id
"msg_011CdNsnf6J1DxhQWE7tShHs"
is_byok
false
latency
1236
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-1784987098-mwhy0hI3ufnTDdfGl6KD"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784987098-yHDC4jQ7XXrhY8wk1NKi"
upstream_id
"msg_011CdNsnf6J1DxhQWE7tShHs"
total_cost
0.019915
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
95.99%
Matches word count
n/a
neededClean
false
words
208
99.96%
Dialogue to Total Word Ratio
Ratio: 8.61%, Deviation: 1.39%
neededClean
false
wordsTotal
209
wordsDialogue
18
97.9748%