NC Bench
Overview
About
Tests
Models
Vendors
Compare
Run: 2026-02-24-01KJ8W4TEH4XFPYQKEGV8HWM1Z
Run Details
Model:
Claude Opus 4.6 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
1m 35s
Cost:
$0.220260
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
100.0000%
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 blueprint across the hood of their dented minivan, anchoring one corner with a juice box she had swiped from a gas station. The document showed the full layout of 47 Maple Drive, including the backyard where, according to three days of surveillance, little Timmy Henderson would celebrate his seventh birthday with thirty sugar-crazed children, a bouncy castle, and a present table groaning under the weight of wrapped gifts. Bill squinted at the blueprint, then at Molly, then back at the blueprint. He tugged at his black turtleneck, which was already making him sweat in the August heat. "We breach during the piñata, when the kids go feral," Molly said, tapping the diagram. Bill nodded slowly. He had seen the piñata during reconnaissance. It was shaped like a dinosaur and stuffed with enough candy to ensure every child would be temporarily blinded by greed. The perfect window. "What about the clown?" Bill whispered. Molly's jaw tightened. She hadn't accounted for the clown. Clowns were wildcards, unpredictable agents of chaos with oversized pockets and suspicious alertness. She pulled a second juice box from her coat and took a long, contemplative sip. "We take the clown out first," she said.
created_at
"2026-02-24T22:26:03.361Z"
2/24/2026, 10:26:03 PM
model
"anthropic/claude-4.6-opus-20260205"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1488
moderation_latency
154
generation_time
94981
tokens_prompt
77
tokens_completion
1053
native_tokens_prompt
92
native_tokens_completion
8792
native_tokens_completion_images
(null)
native_tokens_reasoning
733
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
0.22026
router
(null)
provider_responses
0
endpoint_id
"a8708fb9-08ea-43bb-a3b1-165c87ef09df"
id
"504c76f8-c5f8-4ccc-9b44-a0851a5300ea"
is_byok
false
latency
1448
model_permaslug
"anthropic/claude-4.6-opus-20260205"
provider_name
"Amazon Bedrock"
status
200
api_type
"completions"
id
"gen-1771971963-S8T1gdfQxiM23A5JwSUd"
upstream_id
"504c76f8-c5f8-4ccc-9b44-a0851a5300ea"
total_cost
0.22026
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: 9.95%, Deviation: 0.05%
neededClean
false
wordsTotal
201
wordsDialogue
20
100.0000%