NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCRKPNMBJS4E19GDG0V8JMG
Run Details
Model:
Claude Opus 5 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
11.0s
Cost:
$0.015165
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
93.65%
Matches word count
(details)
2.89%
Dialogue to Total Word Ratio
(details)
48.2692%
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 blueprints across the hood of the van, which was actually a laminated placemat from the Pizza Barn. "That's the bounce castle," she said, tapping it. "That's the piƱata. And that, Bill, is our extraction point." "The slip-and-slide?" "The slip-and-slide." Bill chewed his thumbnail. "There'll be forty children in there. Forty. Sugared up and feral." "Which is why you're wearing the clown suit." "I'm allergic to clown suits." "You're allergic to shellfish." "Emotionally allergic." She handed him a duffel bag stenciled BALLOONS, NOTHING SUSPICIOUS. He took it the way a man takes a subpoena. "Timeline," Molly continued. "Two-fifteen, cake. Everyone faces the cake. Nobody has ever, in recorded history, looked away from a cake. That's ninety seconds of total blindness, and in ninety seconds I can clear a present table of eleven gift bags and one suspiciously large bicycle." "And the mothers?" "Distracted. You'll be juggling." "I can't juggle." "Then they'll be riveted, Bill. Nothing holds a crowd like failure." He looked at the house, at the streamers sagging in the heat, at a small boy already crying about something structural. "This feels wrong," he said quietly. "It's a birthday, not a bank." "That's what makes it wrong." Molly checked her watch. "Two-fourteen. Honk if anybody sings."
created_at
"2026-07-25T13:49:36.316Z"
7/25/2026, 1:49:36 PM
model
"anthropic/claude-opus-5-20260723"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3053
moderation_latency
(null)
generation_time
10858
tokens_prompt
75
tokens_completion
385
native_tokens_prompt
93
native_tokens_completion
588
native_tokens_completion_images
(null)
native_tokens_reasoning
40
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
0.015165
router
(null)
provider_responses
0
endpoint_id
"76cb4608-f48c-483d-8da8-9957fb44244e"
id
"msg_011CdNt97EDnDV1mjCXYqxns"
is_byok
false
latency
1430
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-1784987376-qkXfUU3MOl8nBdFw0dgk"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784987376-TPs67zaRtxbdzxaFr8wD"
upstream_id
"msg_011CdNt97EDnDV1mjCXYqxns"
total_cost
0.015165
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
209
2.89%
Dialogue to Total Word Ratio
Ratio: 63.72%, Deviation: 13.72%
neededClean
false
wordsTotal
215
wordsDialogue
137
48.2692%