NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCPZ37VEB563DD7S5HXR2HR
Run Details
Model:
Claude Opus 5
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
10.7s
Cost:
$0.011790
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
75.16%
Matches word count
(details)
28.83%
Dialogue to Total Word Ratio
(details)
51.9910%
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
Molly spread the birthday invitation across the diner table like a battle map, smoothing its glittery edges with the reverence of a general handling classified documents. Bill hunched over his coffee, squinting at the cartoon dinosaur grinning up from the cardstock. Somewhere behind them a waitress dropped a fork, and both thieves flinched in perfect synchronicity, which said something unflattering about their careers. The party would be held Saturday at eleven, in the Hendersons' backyard, and according to Molly's reconnaissance—two afternoons of pretending to walk a dog she did not own—the gift table sat beneath a canopy near the fence gate. Forty children. Twelve parents. One clown of unknown competence. Bill worried about the clown. Clowns had hands, and hands had reflexes, and Bill had once been outmaneuvered by a mime in Toledo, a humiliation he had never fully processed. Molly tapped the invitation twice. "We go in as the balloon people," she said. Bill set down his mug and considered the ceiling, where a water stain shaped vaguely like Ohio seemed to judge him. "I don't have the lungs for balloons." She was already sketching the fence line on a napkin, drawing the gate, the canopy, the escape route through the neighbor's hydrangeas, humming the happy birthday song slightly off-key.
created_at
"2026-07-25T13:20:52.481Z"
7/25/2026, 1:20:52 PM
model
"anthropic/claude-opus-5-20260723"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1568
moderation_latency
(null)
generation_time
10616
tokens_prompt
75
tokens_completion
334
native_tokens_prompt
93
native_tokens_completion
453
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
0.01179
router
(null)
provider_responses
0
endpoint_id
"76cb4608-f48c-483d-8da8-9957fb44244e"
id
"msg_011CdNqx3B6xrKWyGq6FqJws"
is_byok
false
latency
1568
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-1784985652-gZUwizEsVNrwVkhqYqq0"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784985652-p4jJ62fMr4YQtDWSFzRB"
upstream_id
"msg_011CdNqx3B6xrKWyGq6FqJws"
total_cost
0.01179
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
75.16%
Matches word count
n/a
neededClean
false
words
213
28.83%
Dialogue to Total Word Ratio
Ratio: 20.56%, Deviation: 10.56%
neededClean
false
wordsTotal
214
wordsDialogue
44
51.9910%