NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-29-01KSSJJYCJ00TK3EE65JMM6KEZ
Run Details
Model:
Claude Opus 4.8 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
10.8s
Cost:
$0.014465
Provider:
Anthropic
Evaluation summary
Score
Evaluator
Details Link
99.92%
Matches word count
(details)
93.35%
Dialogue to Total Word Ratio
(details)
96.6341%
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 backyard where a dozen six-year-olds shrieked around a bouncy castle shaped like a unicorn. Bill knelt beside her, sweating through a clown costume two sizes too small, the ruffled collar slowly strangling him. The presents glittered on a folding table near the patio, a mountain of wrapping paper and ribbon defended only by a sleeping golden retriever and a piƱata shaped like a dragon. Molly had drawn up blueprints on the back of a pizza box, complete with arrows, dotted lines, and a coffee stain she insisted was "the danger zone." "This feels wrong," Bill whispered. She ignored him, calculating angles. The plan was elegant: Bill would waddle in, distract the children with balloon animals, and Molly would slip behind the table disguised as the entertainment. They had practiced for weeks. Bill could now produce a balloon giraffe in under four seconds, though it usually exploded. A mother carried out a sheet cake topped with sparklers, and the crowd erupted. Molly tightened her grip on the duffel bag, heart hammering with the thrill of impending crime. "Remember," she breathed, "nobody gets hurt." Bill nodded solemnly, then tripped over his enormous shoes into the bushes.
created_at
"2026-05-29T09:55:58.495Z"
5/29/2026, 9:55:58 AM
model
"anthropic/claude-4.8-opus-20260528"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3343
moderation_latency
(null)
generation_time
10778
tokens_prompt
77
tokens_completion
392
native_tokens_prompt
93
native_tokens_completion
560
native_tokens_completion_images
(null)
native_tokens_reasoning
67
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
0.014465
router
(null)
provider_responses
0
endpoint_id
"b0d3beaa-5ff7-4666-a749-b1bb2b14c916"
id
"msg_01ExjRCMDsi3TyPiKGEJUYnx"
is_byok
false
latency
1255
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-1780048558-CQZdMgHzyqqV9jaTpNaL"
session_id
(null)
api_type
"completions"
id
"gen-1780048558-Eyj3I63Vib3vA4xqQlbp"
upstream_id
"msg_01ExjRCMDsi3TyPiKGEJUYnx"
total_cost
0.014465
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
203
93.35%
Dialogue to Total Word Ratio
Ratio: 4.88%, Deviation: 5.12%
neededClean
false
wordsTotal
205
wordsDialogue
10
96.6341%