NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-06-01-01KT1GY59AV60194A22PHDDFYR
Run Details
Model:
Claude Opus 4.8 (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
9.2s
Cost:
$0.012240
Provider:
Anthropic
Evaluation summary
Score
Evaluator
Details Link
99.38%
Matches word count
(details)
77.70%
Dialogue to Total Word Ratio
(details)
88.5385%
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 bouncy castle, binoculars trained on the backyard fortress of suburban excess. Streamers sagged from the gutters. A piƱata shaped like a unicorn dangled menacingly from the oak tree, swaying in the breeze like a judgmental witness. "That's our exit," she whispered, pointing toward the garden gate. Bill adjusted his clown wig, which itched terribly and smelled faintly of someone else's regret. He'd insisted the disguise was necessary. Molly thought it made him look like a fever dream. The presents sat stacked on a folding table, a glittering ziggurat of wrapping paper and unearned hope. Twelve, maybe fifteen boxes. Some of them were enormous. One appeared to be moving, which neither of them wanted to investigate. "On my signal," Bill mouthed, holding up three fingers dramatically. A child shrieked. Then another. The entire party erupted into chaos as a magician's dove escaped and began dive-bombing the cake. Parents scattered. Juice boxes flew. It was, Molly thought, the most beautiful distraction money couldn't buy. She sprinted across the lawn, grabbing gifts and tossing them into her duffel bag with the practiced grace of a woman who'd robbed three quinceaƱeras last spring. Bill tripped over a tricycle and disappeared into the ball pit forever.
created_at
"2026-06-01T12:01:04.304Z"
6/1/2026, 12:01:04 PM
model
"anthropic/claude-4.8-opus-20260528"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1019
moderation_latency
(null)
generation_time
9202
tokens_prompt
77
tokens_completion
337
native_tokens_prompt
93
native_tokens_completion
471
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
0.01224
router
(null)
provider_responses
0
endpoint_id
"b0d3beaa-5ff7-4666-a749-b1bb2b14c916"
id
"msg_01UyWJQDttaDEUbseXXEiP4P"
is_byok
false
latency
1016
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-1780315264-UzzIug68OK5IHJJfkn9J"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1780315264-isjVVEQufUQMmI5MkUO9"
upstream_id
"msg_01UyWJQDttaDEUbseXXEiP4P"
total_cost
0.01224
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Anthropic"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
99.38%
Matches word count
n/a
neededClean
false
words
205
77.70%
Dialogue to Total Word Ratio
Ratio: 2.91%, Deviation: 7.09%
neededClean
false
wordsTotal
206
wordsDialogue
6
88.5385%