NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCRCDZG180RAEYT9V9SMB4X
Run Details
Model:
Claude Opus 5 (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
10.6s
Cost:
$0.012940
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
51.23%
Dialogue to Total Word Ratio
(details)
75.6170%
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
"Right, the party starts at two," Molly said. "Cake at two-thirty. Presents at three." "So we go in at two-thirty." "We go in at two-forty. Nobody watches anything during cake, Bill. Cake is a religious experience for the under-tens." "And the parents?" "Photographing the cake." "What about the entertainment?" "A magician. Gary the Great." "Gary the Great's a grass." "Gary the Great owes me forty quid, which is why Gary the Great is going to do a very long trick with a rope at two-forty." "And I'm the balloon man." "You're the balloon man." "Molly, I can't make balloon animals." "Nobody can make balloon animals. You make a sort of long twisted thing and you say it's a giraffe, and if anyone argues, you say it's abstract." "To a six-year-old?" "Especially to a six-year-old. They respect confidence." "And the presents go where?" "Bin bags. Two trips. Out through the side gate, into the van, gone before they've blown the candles out." "Feels wrong, robbing a child." "It's a bouncy castle in Surrey, Bill, not an orphanage. That boy's getting eleven scooters." "Eleven?" "His mother posted the list." "...Fine. But I'm keeping one scooter." "You're forty-six." "I'm keeping one scooter."
created_at
"2026-07-25T13:45:38.04Z"
7/25/2026, 1:45:38 PM
model
"anthropic/claude-opus-5-20260723"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2670
moderation_latency
(null)
generation_time
10462
tokens_prompt
75
tokens_completion
336
native_tokens_prompt
93
native_tokens_completion
499
native_tokens_completion_images
(null)
native_tokens_reasoning
19
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
0.01294
router
(null)
provider_responses
0
endpoint_id
"76cb4608-f48c-483d-8da8-9957fb44244e"
id
"msg_011CdNsqZoPDJs81EowAYRyB"
is_byok
false
latency
1581
model_permaslug
"anthropic/claude-opus-5-20260723"
provider_name
"Amazon Bedrock"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.18.0; linux; x64))"
http_referer
(null)
request_id
"req-1784987138-W37glttwja5AEsduib5H"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784987138-6Re5QH27imZCSapmh17Z"
upstream_id
"msg_011CdNsqZoPDJs81EowAYRyB"
total_cost
0.01294
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
51.23%
Dialogue to Total Word Ratio
Ratio: 99.04%, Deviation: 9.04%
neededClean
false
wordsTotal
209
wordsDialogue
207
75.6170%