NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-02-08-01KGYZ828TYDNJWZ6TT2TDN4MS
Run Details
Model:
Claude Opus 4.6
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
11.0s
Cost:
$0.007925
Provider:
Anthropic
Evaluation summary
Score
Evaluator
Details Link
99.38%
Matches word count
(details)
98.10%
Dialogue to Total Word Ratio
(details)
98.7403%
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 sticky diner table, pushing aside a plate of cold fries. The blueprint, sketched on the back of a Chuck E. Cheese napkin, detailed the backyard of 47 Maple Drive with alarming precision. She had spent three days conducting surveillance from behind a mailbox dressed as a bush. Bill squinted at the diagram, turning it sideways, then upside down. "That's the bouncy castle," Molly whispered, tapping a wobbly square near the fence line. The bouncy castle was the problem. It blocked the only direct route between the gate and the gift table, which according to Molly's intelligence sat beneath a paper streamer canopy on the east side of the patio. They would need to go around it or, God forbid, through it. Bill had bad knees and worse balance. A bouncy castle could end his career. "We go at cake time," Bill said. "Everyone watches the candles." Molly nodded slowly, already imagining the haul. The birthday boy was turning seven, and his parents were wealthy, guilt-ridden divorces who compensated with expensive gifts. They were looking at premium toy territory. Possibly even electronics. She folded the napkin carefully and slid it into her jacket. This was going to be beautiful.
created_at
"2026-02-08T15:52:21.931255+00:00"
2/8/2026, 3:52:21 PM
model
"anthropic/claude-4.6-opus-20260205"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1635
moderation_latency
(null)
generation_time
10950
tokens_prompt
61
tokens_completion
259
native_tokens_prompt
75
native_tokens_completion
302
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)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
usage
0.007925
router
(null)
provider_responses
0
id
"msg_01T3L8uyBALyiYhWWH7aoVDc"
status
200
is_byok
false
latency
1635
endpoint_id
"c926c048-563e-44b0-8434-95965bee924c"
provider_name
"Anthropic"
model_permaslug
"anthropic/claude-4.6-opus-20260205"
api_type
"completions"
id
"gen-1770565929-6Hb2cfKOoRFTOlg9Lwvz"
upstream_id
"msg_01T3L8uyBALyiYhWWH7aoVDc"
total_cost
0.007925
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Anthropic"
Evaluation details
Result
Evaluator
Details
Meta Data
99.38%
Matches word count
n/a
neededClean
false
words
205
98.10%
Dialogue to Total Word Ratio
Ratio: 6.28%, Deviation: 3.72%
neededClean
false
wordsTotal
207
wordsDialogue
13
98.7403%