NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCRE8QPFXYKZZ98PDAHR3R6
Run Details
Model:
Claude Opus 5 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
10.2s
Cost:
$0.012840
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
97.63%
Matches word count
(details)
99.88%
Dialogue to Total Word Ratio
(details)
98.7532%
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 had drawn the layout on the back of a grease-stained napkin: the bouncy castle, the piñata, the folding table sagging beneath a mountain of glittering wrapped boxes. She circled the table three times with her pen, hard enough to tear through, then slid the napkin across the diner booth to Bill, who was busy excavating a molar with a coffee stirrer. The party started at two. Nineteen guests, all of them under the age of eight, all of them hopped up on frosting and fruit punch, which meant chaos, which meant cover. There would be one adult on presents duty — an aunt, Molly's intelligence suggested, the sort of aunt who drinks white wine from a plastic cup and loses track of things. There would be a magician arriving at two-thirty. The magician was the window. Bill studied the napkin with the gravity of a general. He tapped the bouncy castle twice. "We go in dressed as clowns," he said. Molly closed her eyes. She had known him eleven years and he had never once been reasonable. "No clowns," she said. "Balloon animals. Nobody suspects a man twisting a giraffe." Bill considered this, nodded slowly, and ordered pie, which he always did before a job, for luck.
created_at
"2026-07-25T13:46:38.209Z"
7/25/2026, 1:46:38 PM
model
"anthropic/claude-opus-5-20260723"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3614
moderation_latency
(null)
generation_time
10056
tokens_prompt
75
tokens_completion
345
native_tokens_prompt
93
native_tokens_completion
495
native_tokens_completion_images
(null)
native_tokens_reasoning
44
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
0.01284
router
(null)
provider_responses
0
endpoint_id
"76cb4608-f48c-483d-8da8-9957fb44244e"
id
"msg_011CdNsuyhvMYRMD9zaJwPNA"
is_byok
false
latency
1245
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-1784987198-e95sVzj97qOoEJUgO3br"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784987198-NuhDSdRedioxId7CLyaa"
upstream_id
"msg_011CdNsuyhvMYRMD9zaJwPNA"
total_cost
0.01284
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
97.63%
Matches word count
n/a
neededClean
false
words
207
99.88%
Dialogue to Total Word Ratio
Ratio: 8.13%, Deviation: 1.87%
neededClean
false
wordsTotal
209
wordsDialogue
17
98.7532%