NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-18-01KHQ94R8MCNC9WNC0R8X1W66P
Run Details
Model:
Claude Sonnet 4.6
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
8.2s
Cost:
$0.004515
Provider:
Anthropic
Evaluation summary
Score
Evaluator
Details Link
99.98%
Matches word count
(details)
73.19%
Dialogue to Total Word Ratio
(details)
86.5850%
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 garden hedge, her all-black outfit somewhat undermined by the fact she had stepped in a dog mess on the way over. Bill knelt beside her, holding a hand-drawn map of the premises that looked suspiciously like it had been sketched on the back of a burger wrapper. The target was number fourteen Primrose Avenue. Inside, approximately twenty-three six-year-olds were currently shrieking through a game of musical chairs while a traumatised clown attempted to maintain crowd control. The presents were piled in the hallway. Unguarded. Beautiful. Molly studied the entry points with the cold precision of a professional. The side gate was unlocked. The parents were distracted. Everything was falling into place. "Ready?" she whispered. Bill adjusted his balaclava and nodded gravely. The two of them had robbed banks, cracked safes, and once successfully stolen an entire garden shed. Nothing in their considerable criminal experience had prepared them for the sight that greeted them as they pushed open the gate. The birthday boy was standing directly in their path, holding a juice box, staring at them with enormous unblinking eyes. "Mum," he called casually over his shoulder. "There are burglars."
created_at
"2026-02-18T02:27:01.720295+00:00"
2/18/2026, 2:27:01 AM
model
"anthropic/claude-4.6-sonnet-20260217"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
775
moderation_latency
(null)
generation_time
8160
tokens_prompt
77
tokens_completion
317
native_tokens_prompt
75
native_tokens_completion
286
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)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
usage
0.004515
router
(null)
provider_responses
0
id
"msg_01F6HsGzG1rcdL122hNYfs4f"
status
200
is_byok
false
latency
775
endpoint_id
"6d408764-7dd7-4626-bb87-a6cc1589bc86"
provider_name
"Anthropic"
model_permaslug
"anthropic/claude-4.6-sonnet-20260217"
api_type
"completions"
id
"gen-1771381612-FLLQDcNHJ0V0Drc1Je76"
upstream_id
"msg_01F6HsGzG1rcdL122hNYfs4f"
total_cost
0.004515
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Anthropic"
Evaluation details
Result
Evaluator
Details
Meta Data
99.98%
Matches word count
n/a
neededClean
false
words
198
73.19%
Dialogue to Total Word Ratio
Ratio: 2.53%, Deviation: 7.47%
neededClean
false
wordsTotal
198
wordsDialogue
5
86.5850%