NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-01-01KWE8Y6F6V0A78XTWTDSH9055
Run Details
Model:
Claude Sonnet 5
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
8.4s
Cost:
$0.004926
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
98.71%
Matches word count
(details)
28.64%
Dialogue to Total Word Ratio
(details)
63.6784%
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 rain hammered against the warehouse windows as Molly spread the blueprints across the rickety table, her finger tracing the outline of a modest suburban house on Maple Street. Bill leaned over her shoulder, chewing on a toothpick like it owed him money. "Bounce house is the blind spot," Molly said, tapping a red circle near the backyard fence. "Nobody watches a bounce house once the sugar hits." Bill grunted, unimpressed. He'd robbed banks, jewelry stores, one particularly memorable art gallery in Prague, and yet here he was, forty-three years old, planning to rob a six-year-old's birthday party. "There's gotta be twenty presents in there," Molly continued, pulling out a crumpled invitation she'd swiped from the mailbox. "Easy Bake Ovens, Lego sets, probably a bike or two." "Feels wrong," Bill muttered, though he didn't put down the toothpick. "Insurance fraud is wrong, Bill. This is just—" she waved a hand vaguely, "—redistribution." He snorted. Outside, thunder rolled like a drumroll for their terrible idea. Molly folded the blueprint and stuffed it into her jacket, already mentally rehearsing her disguise as a clumsy party clown. Bill just shook his head, grabbed his coat, and followed her out into the storm, muttering about karma the entire way.
created_at
"2026-07-01T07:22:48.178Z"
7/1/2026, 7:22:48 AM
model
"anthropic/claude-sonnet-5-20260630"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1631
moderation_latency
(null)
generation_time
8342
tokens_prompt
77
tokens_completion
331
native_tokens_prompt
93
native_tokens_completion
474
native_tokens_completion_images
(null)
native_tokens_reasoning
0
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
0.004926
router
(null)
provider_responses
0
endpoint_id
"37b16f45-eeae-45f3-9b85-2137f7c6d61b"
id
"msg_01TRZvX96rfpsRGVydY6kRtU"
is_byok
false
latency
1630
model_permaslug
"anthropic/claude-sonnet-5-20260630"
provider_name
"Amazon Bedrock"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.17.0; linux; x64))"
http_referer
(null)
request_id
"req-1782890568-UwfuNn0cfjK3iXRZe9kY"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1782890568-687p3ljXpie1elbmSXiq"
upstream_id
"msg_01TRZvX96rfpsRGVydY6kRtU"
total_cost
0.004926
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
98.71%
Matches word count
n/a
neededClean
false
words
206
28.64%
Dialogue to Total Word Ratio
Ratio: 20.57%, Deviation: 10.57%
neededClean
false
wordsTotal
209
wordsDialogue
43
63.6784%