NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-01-01KWE9BZV6MM7Z0KYGJ1XCVV90
Run Details
Model:
Claude Sonnet 5 (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
9.9s
Cost:
$0.005506
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
43.38%
Matches word count
(details)
99.20%
Dialogue to Total Word Ratio
(details)
71.2883%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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 warehouse smelled like stale popcorn and desperation, which felt appropriate given what Molly and Bill were about to attempt. "So we just walk in dressed as clowns," Bill said, admiring his oversized shoes. "Not clowns," Molly snapped, adjusting her wig. "Mascots. There's a difference." "What difference?" "Clowns are terrifying. Mascots are beloved. We need to be beloved, Bill." Bill squeezed into a foam bear costume that smelled like someone else's regret. "I feel ridiculous." "You look like Bunsy the Birthday Bear. Very convincing." "There's a real Bunsy?" "There's always a real Bunsy." They practiced their entrance—jazz hands, a little shuffle—like two idiots auditioning for a children's show nobody asked for. "Remember," Molly said, "we grab the presents during the piñata chaos. Kids will be blind with sugar and violence. Nobody notices two mascots loading a getaway van." "And if someone asks why Bunsy's stealing presents?" "Bunsy doesn't explain himself. Bunsy just is." Bill nodded solemnly, as if this were sacred wisdom. He waddled toward the door, tripped over his own paws, and crashed into a folding table. Molly sighed, hoisting him up. "This is why we rehearse, Bill." "I thought this was rehearsal." "It was." They stepped into the sunlight, two overstuffed disasters marching toward larceny, giggling like the children they were about to rob.
created_at
"2026-07-01T07:30:20.144Z"
7/1/2026, 7:30:20 AM
model
"anthropic/claude-sonnet-5-20260630"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1889
moderation_latency
(null)
generation_time
9790
tokens_prompt
77
tokens_completion
376
native_tokens_prompt
93
native_tokens_completion
532
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
0.005506
router
(null)
provider_responses
0
endpoint_id
"37b16f45-eeae-45f3-9b85-2137f7c6d61b"
id
"msg_01CtzncSFKQgzWsnrxRgL7Tb"
is_byok
false
latency
1889
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-1782891020-WyUg6jxqmkg1WSCYYOtO"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1782891020-rrRBlQSVIqB01u9zLOow"
upstream_id
"msg_01CtzncSFKQgzWsnrxRgL7Tb"
total_cost
0.005506
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
43.38%
Matches word count
n/a
neededClean
false
words
217
99.20%
Dialogue to Total Word Ratio
Ratio: 47.00%, Deviation: 3.00%
neededClean
false
wordsTotal
217
wordsDialogue
102
71.2883%