NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-06-01-01KT1GT35G9X8R58NP5VE5S3ZR
Run Details
Model:
Claude Opus 4.8 (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
13.8s
Cost:
$0.014665
Provider:
Anthropic
Evaluation summary
Score
Evaluator
Details Link
97.63%
Matches word count
(details)
90.02%
Dialogue to Total Word Ratio
(details)
93.8255%
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 blueprints across the sticky diner table, smoothing out a coffee stain that had unfortunately obscured the bouncy castle. Bill leaned in, chewing a pen, his eyes darting between the clown's stage and the heavily fortified snack table where the loot—a glittering mountain of wrapped presents—awaited liberation. The plan was elegant in its absurdity. They would arrive disguised as entertainers, Bill as a balloon artist and Molly as a face painter, slipping past the parents who guarded the perimeter like exhausted, juice-box-wielding sentries. Once inside, they would create a diversion during musical chairs, when chaos reigned supreme and no adult could be trusted to count children, let alone gift bags. Bill traced the escape route with a trembling finger, calculating how many parcels could fit inside their oversized novelty trousers. "Children are vicious," he whispered, remembering his nephew's birthday and the incident with the piñata stick. Molly nodded gravely, sliding him a smoke bomb shaped like a party popper. The trickiest part remained the cake. Tradition demanded singing, and singing meant scrutiny, and scrutiny meant capture. "We grab everything," she muttered, "before the candles." Bill saluted with his pen, knocking over the coffee, drowning the bouncy castle entirely beneath a fresh brown tide.
created_at
"2026-06-01T11:58:51.06Z"
6/1/2026, 11:58:51 AM
model
"anthropic/claude-4.8-opus-20260528"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3386
moderation_latency
(null)
generation_time
13813
tokens_prompt
77
tokens_completion
415
native_tokens_prompt
93
native_tokens_completion
568
native_tokens_completion_images
(null)
native_tokens_reasoning
64
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
0.014665
router
(null)
provider_responses
0
endpoint_id
"b0d3beaa-5ff7-4666-a749-b1bb2b14c916"
id
"msg_01QERF62bf2bq1hujCG7o1DM"
is_byok
false
latency
1197
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-1780315131-f8wFrVPYs8XeLsptTJBT"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1780315131-AvEn37CVU1ijp0aaH2yF"
upstream_id
"msg_01QERF62bf2bq1hujCG7o1DM"
total_cost
0.014665
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Anthropic"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
97.63%
Matches word count
n/a
neededClean
false
words
207
90.02%
Dialogue to Total Word Ratio
Ratio: 4.31%, Deviation: 5.69%
neededClean
false
wordsTotal
209
wordsDialogue
9
93.8255%