NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-29-01KSSJPPB5NDJCX8WY1MYBQZJZ
Run Details
Model:
Claude Opus 4.8 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
13.9s
Cost:
$0.014765
Provider:
Anthropic
Evaluation summary
Score
Evaluator
Details Link
99.92%
Matches word count
(details)
82.86%
Dialogue to Total Word Ratio
(details)
91.3873%
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 bouncy castle as though it were a fortified bank vault. Beside her, Bill chewed nervously on a stolen party hat, the elastic strap snapping against his chin with every anxious breath. Spread before them on a checkered picnic blanket lay their meticulous blueprints, drawn in crayon because that was the only writing implement Bill had managed to liberate during their reconnaissance. The presents glittered in the afternoon sun, stacked beside a table groaning under the weight of frosted cupcakes and suspicious-looking punch. Twelve children, ages six to eight, swarmed the lawn like tiny, sugar-fueled security guards, their reflexes terrifyingly unpredictable. "They have a clown," Bill whispered, voice trembling. Molly lowered the binoculars and shot him a withering glare that could curdle milk. She had planned heists in casinos, museums, even a particularly tense incident involving a duchess's tiara. A clown would not be her undoing. The plan was simple. Bill would create a diversion involving the piƱata. Molly would slip through the gap in the fence, load the gift bags into her oversized trench coat, and vanish before the cake was cut. Bill exhaled, gripping his crayon blueprint. "This is madness," he muttered miserably.
created_at
"2026-05-29T09:58:01.324Z"
5/29/2026, 9:58:01 AM
model
"anthropic/claude-4.8-opus-20260528"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2923
moderation_latency
(null)
generation_time
13839
tokens_prompt
77
tokens_completion
393
native_tokens_prompt
93
native_tokens_completion
572
native_tokens_completion_images
(null)
native_tokens_reasoning
56
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
0.014765
router
(null)
provider_responses
0
endpoint_id
"dfc0e5bd-d703-4fe2-a7bb-655eb95d5441"
id
"msg_01Va4qUx1H2fnmVYnKSGo5Z9"
is_byok
false
latency
1015
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-1780048681-erA1nPzZE2mvP1dduXfu"
session_id
(null)
api_type
"completions"
id
"gen-1780048681-9pdo5fVMHaSwF1vsPsun"
upstream_id
"msg_01Va4qUx1H2fnmVYnKSGo5Z9"
total_cost
0.014765
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
82.86%
Dialogue to Total Word Ratio
Ratio: 3.41%, Deviation: 6.59%
neededClean
false
wordsTotal
205
wordsDialogue
7
91.3873%