NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-06-01-01KT1HYYZEW5H14Y4BGQVH7YZQ
Run Details
Model:
Claude Opus 4.8 (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
11.5s
Cost:
$0.014490
Provider:
Anthropic
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 crouched behind the hydrangeas, binoculars trained on the suburban fortress. Streamers sagged from the gutters like surrender flags, and a bouncy castle wobbled menacingly in the breeze. Somewhere inside, a clown was losing the will to live. Bill adjusted his fake mustache, which he insisted made him look "distinguished" rather than like a man wearing a dead caterpillar. He clutched the blueprints, which were actually a placemat from the pancake house, decorated with crayon mazes he'd already solved. "The presents pile is by the cake," he whispered. Molly nodded gravely. Intelligence suggested forty wrapped boxes, possibly containing electronics, possibly containing socks. The risk was enormous. Children were unpredictable, sticky, and traveled in packs. One wrong move and they'd be swarmed by sugar-fueled seven-year-olds demanding to know if they were the magician. She'd disguised herself as a face painter, armed with glitter and a deep reluctance. "What if they ask for a unicorn?" Bill asked. "Then I paint a unicorn." They synchronized their watches, which were also crayon drawings. The plan was elegant: enter during the piƱata frenzy, when chaos peaked and adults wept quietly into juice boxes, then exit with their loot before anyone noticed the birthday boy crying.
created_at
"2026-06-01T12:18:59.189Z"
6/1/2026, 12:18:59 PM
model
"anthropic/claude-4.8-opus-20260528"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3155
moderation_latency
(null)
generation_time
11447
tokens_prompt
77
tokens_completion
396
native_tokens_prompt
93
native_tokens_completion
561
native_tokens_completion_images
(null)
native_tokens_reasoning
59
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
0.01449
router
(null)
provider_responses
0
endpoint_id
"b0d3beaa-5ff7-4666-a749-b1bb2b14c916"
id
"msg_018YriRydYVJo8P1jCkjW8u9"
is_byok
false
latency
1502
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-1780316339-Z1nU5hcTVqkmo7o6momk"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1780316339-GmtcRPfkBwR6skycGRnK"
upstream_id
"msg_018YriRydYVJo8P1jCkjW8u9"
total_cost
0.01449
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
200
100.00%
Dialogue to Total Word Ratio
Ratio: 9.85%, Deviation: 0.15%
neededClean
false
wordsTotal
203
wordsDialogue
20
100.0000%