NC Bench
Overview
About
Tests
Models
Vendors
Compare
Run: 2026-02-24-01KJ8VAF0990GTTCYG0FQ4KAWN
Run Details
Model:
Claude Opus 4.6 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
30.1s
Cost:
$0.058785
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
99.9994%
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 hand-drawn map across the hood of their dented minivan, anchoring one corner with a juice box she'd swiped from a gas station. The blueprint—if you could call crayon on construction paper a blueprint—showed the layout of 47 Maple Drive, where little Timmy Henderson was about to celebrate his seventh birthday with approximately thirty sugar-fueled children and a bouncy castle. Bill squinted at the map, turning it sideways. "Why is there a dragon in the living room?" "That's the dog, Bill." She tapped a purple blob near what appeared to be the garage, explaining that the presents would be stacked there, near the piñata station. They would go in disguised as party entertainers, load the gifts into trash bags, and slip out during the inevitable cake chaos. Simple. Bill scratched his chin, considering the plan with the same intensity he typically reserved for choosing breakfast cereals. He'd already worn his lucky ski mask, which was unfortunate given that it was July and they were supposed to blend in with suburban parents. "What if the kids see us?" he whispered. Molly grinned and assured him that children were basically tiny, drunk adults who wouldn't remember a thing.
created_at
"2026-02-24T22:11:39.665Z"
2/24/2026, 10:11:39 PM
model
"anthropic/claude-4.6-opus-20260205"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1588
moderation_latency
156
generation_time
29869
tokens_prompt
77
tokens_completion
781
native_tokens_prompt
92
native_tokens_completion
2333
native_tokens_completion_images
(null)
native_tokens_reasoning
465
native_tokens_cached
0
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
usage
0.058785
router
(null)
provider_responses
0
endpoint_id
"a8708fb9-08ea-43bb-a3b1-165c87ef09df"
id
"ea0bf4a4-a7d8-4867-8f11-b99e8c036cc5"
is_byok
false
latency
1551
model_permaslug
"anthropic/claude-4.6-opus-20260205"
provider_name
"Amazon Bedrock"
status
200
api_type
"completions"
id
"gen-1771971099-cDPiylHqsp0mGgvQgKZF"
upstream_id
"ea0bf4a4-a7d8-4867-8f11-b99e8c036cc5"
total_cost
0.058785
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
200
100.00%
Dialogue to Total Word Ratio
Ratio: 9.41%, Deviation: 0.59%
neededClean
false
wordsTotal
202
wordsDialogue
19
99.9994%