NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-01-01KWE9081T6080FFMG0CF1XWSY
Run Details
Model:
Claude Sonnet 5 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
8.4s
Cost:
$0.005086
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
36.79%
Dialogue to Total Word Ratio
(details)
68.3935%
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
"Okay, Bill, run it by me again." "Simple. We go in dressed as clowns, we do some balloon animals, we grab the presents, we leave." "That's it? That's the whole plan?" "What more do you want? It's a five-year-old's birthday party, Molly, not Fort Knox." "Five-year-olds have parents, Bill. Parents have phones. Phones have cameras." "So we smile a lot." "We smile a lot. Brilliant. That's your master strategy." "Hey, you try planning a heist around a bounce house. There's logistics!" "What logistics? You inflate, you deflate, you're overthinking a bouncy castle." "Overthinking? Last time I underthought a bouncy castle I got stuck inside for forty minutes." "That was one time." "It was humiliating, Molly. A seven-year-old had to pull me out by my ankles." "Focus. The presents are on the table by the cake, right?" "Right. Big table, dinosaur tablecloth, mountain of presents wrapped in that shiny paper kids love." "And the piñata?" "Forget the piñata." "I'm not fighting a piñata, Bill." "Nobody's fighting the piñata! We grab the loot, we wave goodbye, we're out before 'Happy Birthday' even finishes." "Fine. But if there's a bounce house—" "There's always a bounce house, Molly." "Then God help us both."
created_at
"2026-07-01T07:23:55.337Z"
7/1/2026, 7:23:55 AM
model
"anthropic/claude-sonnet-5-20260630"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1511
moderation_latency
(null)
generation_time
8394
tokens_prompt
77
tokens_completion
343
native_tokens_prompt
93
native_tokens_completion
490
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
0.005086
router
(null)
provider_responses
0
endpoint_id
"37b16f45-eeae-45f3-9b85-2137f7c6d61b"
id
"msg_01AoBQgEWuBx844L8XJ5RVTh"
is_byok
false
latency
1511
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-1782890635-2bhw6NAR4EdEOrLMmYy8"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1782890635-U87EoVpMAPh5Xs3bNEv3"
upstream_id
"msg_01AoBQgEWuBx844L8XJ5RVTh"
total_cost
0.005086
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
199
36.79%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
205
wordsDialogue
205
68.3935%