NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-31-01KSYXR4AT6Z9W6K53HACFRM0B
Run Details
Model:
Claude Opus 4.8 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
10.8s
Cost:
$0.014640
Provider:
Anthropic
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
91.39%
Dialogue to Total Word Ratio
(details)
95.6956%
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 crouched behind the hydrangea bush, binoculars trained on the backyard where a dozen balloons bobbed against a banner reading HAPPY 7TH BIRTHDAY TIMMY. Beside her, Bill struggled to fit his enormous frame behind a garden gnome that concealed roughly four percent of his torso. The present table glittered in the afternoon sun, a mountain of wrapping paper and ribbon stacked precariously beside the bouncy castle. Molly's pulse quickened. Thirty years of armed robberies, casino jobs, and one regrettable submarine incident had led to this, the heist of a lifetime. "That clown is the security," Molly whispered, gesturing toward a man twisting balloon animals with suspicious efficiency. Bill nodded gravely, adjusting his ski mask, which clashed terribly with his Hawaiian shirt. He'd insisted on the disguise. He'd also insisted on the shirt. They watched a child sprint past, juice box in hand, weaponized sugar coursing through tiny veins. The enemy was small, sticky, and unpredictable. "Wait for the piƱata," Bill murmured. The plan was elegant. During the chaos of swinging bats and scrambling toddlers, they would extract the loot through the side gate, load the getaway minivan, and vanish. Molly grinned. Somewhere, a parent lit seven candles, utterly unaware.
created_at
"2026-05-31T11:47:14.919Z"
5/31/2026, 11:47:14 AM
model
"anthropic/claude-4.8-opus-20260528"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2773
moderation_latency
(null)
generation_time
10759
tokens_prompt
77
tokens_completion
381
native_tokens_prompt
93
native_tokens_completion
567
native_tokens_completion_images
(null)
native_tokens_reasoning
48
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
0.01464
router
(null)
provider_responses
0
endpoint_id
"b0d3beaa-5ff7-4666-a749-b1bb2b14c916"
id
"msg_01VuciFt5MgLfSrAuXhUrJpC"
is_byok
false
latency
1195
model_permaslug
"anthropic/claude-4.8-opus-20260528"
provider_name
"Anthropic"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.16.0; linux; x64))"
http_referer
(null)
request_id
"req-1780228034-dM5CPjb4wXDXoakHP7t7"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1780228034-XcdIeFlQpYVsTaPebDOM"
upstream_id
"msg_01VuciFt5MgLfSrAuXhUrJpC"
total_cost
0.01464
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Anthropic"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
199
91.39%
Dialogue to Total Word Ratio
Ratio: 4.52%, Deviation: 5.48%
neededClean
false
wordsTotal
199
wordsDialogue
9
95.6956%