NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-31-01KSYX80ZX7C59030PK3VGN45P
Run Details
Model:
Claude Opus 4.8 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
9.5s
Cost:
$0.011915
Provider:
Anthropic
Evaluation summary
Score
Evaluator
Details Link
99.92%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
49.9595%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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 table, knocking over a juice box she'd stolen earlier as a test run. "The bouncy castle is our blind spot," she said, jabbing the map. "Security can't see behind it." Bill squinted. "Security? Molly, it's a seven-year-old's birthday party." "The clown counts as security." "The clown does not count as security." She slid a photograph toward him. "Tell that to Pickles the Clown, former Navy SEAL. He's got eyes like a hawk and balloons like a weapon." Bill rubbed his temples. "Why are we doing this again?" "Because," Molly whispered dramatically, "those presents contain limited-edition action figures worth thousands on the collector's market." "They're plastic toys." "They're treasure." He sighed. "And the plan?" "You distract them with the piƱata. While everyone's swinging, I grab the loot bag and we vanish through the ball pit." Bill blinked. "Through the ball pit?" "It connects to the ventilation system." "That's the dumbest thing I've ever heard." Molly grinned. "Which is exactly why it'll work. Nobody suspects the ball pit." Bill stared at her for a long moment, then grabbed his fake mustache. "Fine," he muttered. "But if that clown sees me, I'm blaming you."
created_at
"2026-05-31T11:38:27.362Z"
5/31/2026, 11:38:27 AM
model
"anthropic/claude-4.8-opus-20260528"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1774
moderation_latency
(null)
generation_time
9229
tokens_prompt
77
tokens_completion
335
native_tokens_prompt
93
native_tokens_completion
458
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)
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
0.011915
router
(null)
provider_responses
0
endpoint_id
"b0d3beaa-5ff7-4666-a749-b1bb2b14c916"
id
"msg_01YKPfGFKJ5mJ13eLDK62jVR"
is_byok
false
latency
1774
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-1780227507-rI7WU0KaJEf8tiQUdTZV"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1780227507-hzYOY8y6aorIPDRvO3KZ"
upstream_id
"msg_01YKPfGFKJ5mJ13eLDK62jVR"
total_cost
0.011915
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Anthropic"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
99.92%
Matches word count
n/a
neededClean
false
words
197
0.00%
Dialogue to Total Word Ratio
Ratio: 70.00%, Deviation: 20.00%
neededClean
false
wordsTotal
200
wordsDialogue
140
49.9595%