NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-06-01-01KT1H3DTVX4ZY1KQQXMYR8YAH
Run Details
Model:
Claude Opus 4.8 (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
10.9s
Cost:
$0.014315
Provider:
Anthropic
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
95.49%
Dialogue to Total Word Ratio
(details)
97.7459%
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, her binoculars trained on the bouncy castle pulsing with the laughter of seven-year-olds. Bill wedged himself beside her, his camouflage face paint smeared with what he insisted was tactical mud but was clearly chocolate frosting from their reconnaissance snacking. The present pile glittered near the gazebo, a mountain of wrapped treasure guarded by nothing more menacing than a clown twisting balloon animals into vaguely threatening shapes. "That clown's a professional," Bill whispered. Molly rolled her eyes and consulted her clipboard, which contained a meticulously hand-drawn map of the backyard, complete with crayon arrows and a coffee stain she'd labeled "moat." Their plan was elegant in its stupidity: Bill would create a diversion by pretending to be a magician, while Molly executed a smooth grab-and-dash through the rose trellis. They had rehearsed for weeks in her living room, practicing somersaults that left them both bruised and questioning their life choices. A child shrieked with delight as the piƱata burst, raining candy across the lawn. Bill flinched, clutching his grappling hook, which was actually a curtain rod with a fishing weight duct-taped to one end. "We're going to prison," he murmured. Molly grinned. "Worth it."
created_at
"2026-06-01T12:03:56.896Z"
6/1/2026, 12:03:56 PM
model
"anthropic/claude-4.8-opus-20260528"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3499
moderation_latency
(null)
generation_time
10916
tokens_prompt
77
tokens_completion
381
native_tokens_prompt
93
native_tokens_completion
554
native_tokens_completion_images
(null)
native_tokens_reasoning
47
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
0.014315
router
(null)
provider_responses
0
endpoint_id
"b0d3beaa-5ff7-4666-a749-b1bb2b14c916"
id
"msg_01NVhZr5wpAWNAzgX2d19YVu"
is_byok
false
latency
1313
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-1780315436-EEsrFresjK21lYsogSBX"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1780315436-tOhpC9y0j5YEB1Q44Us8"
upstream_id
"msg_01NVhZr5wpAWNAzgX2d19YVu"
total_cost
0.014315
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
95.49%
Dialogue to Total Word Ratio
Ratio: 5.37%, Deviation: 4.63%
neededClean
false
wordsTotal
205
wordsDialogue
11
97.7459%