NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-01-01KWEA9ZWF4H13WDWHY6SF4RG5
Run Details
Model:
Claude Sonnet 5
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
19.9s
Cost:
$0.004866
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
99.92%
Dialogue to Total Word Ratio
(details)
99.9570%
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
Bill leaned against the van, arms crossed. "So we're really doing this. Robbing a six-year-old's birthday party." "Not robbing," Molly said, checking her watch. "Liberating. Those presents don't even know how good they've got it yet." "That's not better, Molly." "It's marketing. Now, you got the clown costume?" "I look ridiculous." "You look like Bobo the Magnificent, which is exactly what the invitation says is coming. Nobody questions a clown, Bill. That's rule one of heist work." "Rule one is 'don't get caught.'" "That's rule two. Focus. When we get in there, I distract the parents with the balloon animal bit—" "You can't make balloon animals." "I can make a sword. That's basically a balloon animal." "It's a stick." "It's abstract art, Bill. Anyway, while I'm doing that, you grab the present table and load it into the diaper bag." "The diaper bag holds, what, four gifts?" "It's magic. Deep pockets. Very deep pockets." "Is it stolen too?" "Everything's stolen, Bill, that's the job. Now put on the nose." Bill groaned, squeezing the red foam onto his face. "If we get arrested by a room full of six-year-olds—" "They won't even see us coming," Molly said, grinning. "Nobody suspects the clown."
created_at
"2026-07-01T07:46:43.228Z"
7/1/2026, 7:46:43 AM
model
"anthropic/claude-sonnet-5-20260630"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
4388
moderation_latency
(null)
generation_time
19826
tokens_prompt
77
tokens_completion
334
native_tokens_prompt
93
native_tokens_completion
468
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
0.004866
router
(null)
provider_responses
0
endpoint_id
"37b16f45-eeae-45f3-9b85-2137f7c6d61b"
id
"msg_01TCTvrGNpEbY27xP8twhX1f"
is_byok
false
latency
4180
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-1782892003-3GIJGQ63HmK1MG2VJFuP"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1782892003-NLSXwY3Qy8IfsZltMMcy"
upstream_id
"msg_01TCTvrGNpEbY27xP8twhX1f"
total_cost
0.004866
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
100.00%
Matches word count
n/a
neededClean
false
words
201
99.92%
Dialogue to Total Word Ratio
Ratio: 88.29%, Deviation: 1.71%
neededClean
false
wordsTotal
205
wordsDialogue
181
99.9570%