NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCR2W3NSNACT37T51QTMWJ3
Run Details
Model:
Claude Opus 5 (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
13.6s
Cost:
$0.019790
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
98.71%
Matches word count
(details)
74.72%
Dialogue to Total Word Ratio
(details)
86.7186%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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 blueprint was a pizza placemat, grease-translucent, mapped in crayon. Molly weighted its corners with salt shakers and tapped the crooked rectangle she had labeled TARGET. Present table. Northeast corner of the Hendersons' backyard, beneath a canopy of streamers, guarded by nothing more formidable than a woman named Deb and a sheet cake shaped like a dinosaur. Sixty gifts, minimum. Wrapped, ribboned, wholly untraceable. A birthday was the only occasion in the civilized world where merchandise sat stacked in plain sight and nobody kept a receipt. Bill arrived at the booth in full costume: rainbow wig, red nose, shoes like two capsized canoes. "Nobody suspects a clown," he said. Molly stared at him for a long, arithmetic moment. "Everybody suspects a clown, Bill." She rolled the placemat and explained the plan again, slower, using the salt shakers as figurines. Bill would enter at two-fifteen, during the piƱata, when forty children would be blindfolded, armed, and swinging wildly. Chaos as cover. Molly would idle the minivan by the alley gate with the sliding door open and a bag of juice boxes for credibility. Bill nodded, honking his nose thoughtfully. The wig, Molly decided, could stay.
created_at
"2026-07-25T13:40:24.83Z"
7/25/2026, 1:40:24 PM
model
"anthropic/claude-opus-5-20260723"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3794
moderation_latency
(null)
generation_time
13495
tokens_prompt
75
tokens_completion
394
native_tokens_prompt
93
native_tokens_completion
773
native_tokens_completion_images
(null)
native_tokens_reasoning
85
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
0.01979
router
(null)
provider_responses
0
endpoint_id
"76cb4608-f48c-483d-8da8-9957fb44244e"
id
"msg_011CdNsSTG6AtW3QD1bcFMzZ"
is_byok
false
latency
1159
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-1784986824-KfnmboSxjPyPqEKRN3iu"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784986824-ZteZ2EPVyr9s2lkfqFWo"
upstream_id
"msg_011CdNsSTG6AtW3QD1bcFMzZ"
total_cost
0.01979
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
98.71%
Matches word count
n/a
neededClean
false
words
194
74.72%
Dialogue to Total Word Ratio
Ratio: 17.35%, Deviation: 7.35%
neededClean
false
wordsTotal
196
wordsDialogue
34
86.7186%