NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-29-01KSSJQMVY6VJK3RTXZJN9VR8R
Run Details
Model:
Claude Opus 4.8 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
13.1s
Cost:
$0.011790
Provider:
Anthropic
Evaluation summary
Score
Evaluator
Details Link
95.99%
Matches word count
(details)
64.96%
Dialogue to Total Word Ratio
(details)
80.4742%
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 pressed to her face, surveying the chaos of frosting and shrieking children. Bill squatted beside her, wearing a clown costume two sizes too small, the seams straining with every breath. "This is humiliating," he whispered. She lowered the binoculars and shot him a withering glare. The plan was simple, elegant even. Wait for the piƱata distraction, infiltrate through the gift table, and extract the treasure during the inevitable sugar-fueled stampede toward the cake. Bill tugged at his rainbow wig, sweat beading beneath the synthetic curls. He'd argued against the disguise for an entire week, insisting that grown men loitering at a seven-year-old's birthday would draw suspicion regardless of their attire. Molly had countered that nothing was less suspicious than a clown, statistically speaking, and besides, they had a reputation to uphold. Three successful heists this month alone, and not one of them involving anything as glamorous as jewels or cash. She checked her watch. The mountain of brightly wrapped boxes glittered in the afternoon sun, taunting them. "Ready?" she asked. He nodded grimly, honking the red nose strapped to his face. Together they crept forward, two professional criminals descending upon the most heavily defended target imaginable: small children and their loot.
created_at
"2026-05-29T09:58:32.584Z"
5/29/2026, 9:58:32 AM
model
"anthropic/claude-4.8-opus-20260528"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1321
moderation_latency
(null)
generation_time
13057
tokens_prompt
77
tokens_completion
352
native_tokens_prompt
93
native_tokens_completion
453
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
0.01179
router
(null)
provider_responses
0
endpoint_id
"b0d3beaa-5ff7-4666-a749-b1bb2b14c916"
id
"msg_01WgTetCBLPZSU7sGDZFbBuA"
is_byok
false
latency
1268
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-1780048712-KeHravCgT8Iqym5AS3Ln"
session_id
(null)
api_type
"completions"
id
"gen-1780048712-1WMFHkIktChVUVRcsleO"
upstream_id
"msg_01WgTetCBLPZSU7sGDZFbBuA"
total_cost
0.01179
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Anthropic"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
95.99%
Matches word count
n/a
neededClean
false
words
208
64.96%
Dialogue to Total Word Ratio
Ratio: 1.90%, Deviation: 8.10%
neededClean
false
wordsTotal
211
wordsDialogue
4
80.4742%