NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCPMNA5KD994SP5WV4PGAQC
Run Details
Model:
Claude Opus 5
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
9.3s
Cost:
$0.011940
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
93.65%
Matches word count
(details)
79.48%
Dialogue to Total Word Ratio
(details)
86.5627%
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
Molly spread the crayon-drawn invitation across the hood of the van like a battlefield map. "Bounce house here," she said, tapping the paper. "Present table here. Thirty seconds, tops." Bill squinted. "Whose birthday is it?" "Does it matter?" "It matters to me. I've got standards." "You stole a defibrillator." "From a *gym*," Bill said. "Gyms are villains." He picked up the invitation and held it to the streetlight. "Tabitha. Turning seven. There's a glitter unicorn on this." "Which is why nobody will suspect a thing. Who robs a seven-year-old?" "We do, apparently." Molly pulled two clown noses from her jacket pocket and offered him one. He stared at it the way a man stares at a summons. "Absolutely not." "It's a costume party." "It's a *humiliation* party." "Bill. There is a Nintendo on that table. Wrapped. Untraceable." He took the nose. He put it on. He looked, Molly thought, deeply unwell. "Twenty-eight seconds," he muttered. "And I'm not eating cake." "You'll eat cake and you'll smile." "Why would I smile?" "Because," Molly said, sliding the van door open, "the loot's in the piƱata too, and somebody's got to swing the bat."
created_at
"2026-07-25T13:15:10.539Z"
7/25/2026, 1:15:10 PM
model
"anthropic/claude-opus-5-20260723"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1183
moderation_latency
(null)
generation_time
9230
tokens_prompt
75
tokens_completion
301
native_tokens_prompt
93
native_tokens_completion
459
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
0.01194
router
(null)
provider_responses
0
endpoint_id
"76cb4608-f48c-483d-8da8-9957fb44244e"
id
"msg_011CdNqWppWcpp7C5MFM2N6Y"
is_byok
false
latency
1183
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-1784985310-46KVjCtHn4o9pupFERTc"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784985310-Sdj0iBPsEC1svOzJB8Eg"
upstream_id
"msg_011CdNqWppWcpp7C5MFM2N6Y"
total_cost
0.01194
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
93.65%
Matches word count
n/a
neededClean
false
words
191
79.48%
Dialogue to Total Word Ratio
Ratio: 56.92%, Deviation: 6.92%
neededClean
false
wordsTotal
195
wordsDialogue
111
86.5627%