NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-01-01KWE9TFNJ57DWAECCJ9V0H6YH
Run Details
Model:
Claude Sonnet 5 (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
8.3s
Cost:
$0.004726
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
75.16%
Matches word count
(details)
68.11%
Dialogue to Total Word Ratio
(details)
71.6318%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% 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
"So we're agreed," Molly said. "In through the bounce house, out through the balloon arch." "I still think the clown costume is overkill," Bill said. "Bill. It's a *children's party*. You need the clown costume." "I feel ridiculous." "You look ridiculous. That's the point. Nobody suspects a ridiculous man." "Fine. What's the signal when the presents are secured?" "Two honks of the nose." "Two honks." "Two honks, Bill. Don't overthink it." "What if there's cake? Do I eat the cake? Is that suspicious, a clown not eating cake?" "Eat the cake. Blend in. Just don't get frosting on the loot bag." "There's a loot bag now?" "I sewed it myself. It says 'Happy Birthday' on it." "That's either brilliant or the worst idea you've ever had." "It's both, Bill. It's always both." "What about the parents?" "Distraction. You do balloon animals, badly, while I grab the gifts from the table." "How badly?" "Bill-level badly. Which, conveniently, is very badly." "I resent that." "Resent it after we've got forty presents in a stolen wagon." "...Fine. Two honks." "Two honks." "I really hate the shoes." "Everyone hates the shoes."
created_at
"2026-07-01T07:38:15.103Z"
7/1/2026, 7:38:15 AM
model
"anthropic/claude-sonnet-5-20260630"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1787
moderation_latency
(null)
generation_time
8296
tokens_prompt
77
tokens_completion
323
native_tokens_prompt
93
native_tokens_completion
454
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
0.004726
router
(null)
provider_responses
0
endpoint_id
"37b16f45-eeae-45f3-9b85-2137f7c6d61b"
id
"msg_01CixE6jgHHhUQQZMFzcpAeW"
is_byok
false
latency
1787
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-1782891495-SbFZbfU5DO7SXyLDPHwc"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1782891495-hV5TBc1xyOcJ0iT1FmD3"
upstream_id
"msg_01CixE6jgHHhUQQZMFzcpAeW"
total_cost
0.004726
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
75.16%
Matches word count
n/a
neededClean
false
words
187
68.11%
Dialogue to Total Word Ratio
Ratio: 97.87%, Deviation: 7.87%
neededClean
false
wordsTotal
188
wordsDialogue
184
71.6318%