NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-01-01KWE98CTHVW4S2X0FTPB52TK4
Run Details
Model:
Claude Sonnet 5 (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
8.7s
Cost:
$0.005006
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
99.92%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
49.9595%
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 like feet and stale donuts, which seemed appropriate given the caliber of criminal enterprise about to unfold. Molly spread the blueprints across her lap—actual blueprints, stolen from a birthday planning website, complete with a bounce house rendered in suspicious detail. "Six-year-old's birthday party," she said. "Backyard. Two dozen presents, minimum. Frozen theme, so expect glitter. Lots of glitter." Bill adjusted his clown wig, the one he insisted was "tactical." "Glitter's a liability," he said. "Sticks to everything. Forensic nightmare." "You're worried about forensics at a six-year-old's birthday party." "I'm worried about everything, Molly. That's why I'm still alive." She rolled her eyes and highlighted the fence line. The plan was elegant in its stupidity: Bill would distract the parents with balloon animals while Molly slipped through the side gate and loaded presents into a wagon disguised as party decor. "What if a kid sees you?" Bill asked. "Kids don't remember faces. They remember snacks." "That's terrifying." "That's parenting." He nodded solemnly, as though she'd revealed some ancient truth. Outside, the sun was setting on a quiet suburban street, utterly unprepared for the chaos about to arrive in a rented clown costume and a getaway wagon shaped like a pumpkin.
created_at
"2026-07-01T07:28:22.364Z"
7/1/2026, 7:28:22 AM
model
"anthropic/claude-sonnet-5-20260630"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1540
moderation_latency
(null)
generation_time
8669
tokens_prompt
77
tokens_completion
350
native_tokens_prompt
93
native_tokens_completion
482
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
0.005006
router
(null)
provider_responses
0
endpoint_id
"37b16f45-eeae-45f3-9b85-2137f7c6d61b"
id
"msg_01Ah2qLVVhbctLnTowLR6naY"
is_byok
false
latency
1540
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-1782890902-pTMdEFntorEbilGJLtCG"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1782890902-lGJOyytqPz6tjJ1OfalK"
upstream_id
"msg_01Ah2qLVVhbctLnTowLR6naY"
total_cost
0.005006
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
99.92%
Matches word count
n/a
neededClean
false
words
203
0.00%
Dialogue to Total Word Ratio
Ratio: 31.40%, Deviation: 21.40%
neededClean
false
wordsTotal
207
wordsDialogue
65
49.9595%