NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-06-01-01KT1GEDZAP00J8PDNK9STCD6Y
Run Details
Model:
Claude Opus 4.8 (Reasoning, Low)
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
29.9s
Cost:
$0.081525
Provider:
Anthropic
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
Model input
User/Human
Please write the opening scene of a murder mystery where each sentence has exactly 20 words. Please make sure that each sentence has the same length. Only return the opening itself.
Model response
Messages
Meta
AI
The rain hammered against the old mansion windows as Detective Sarah Cole stepped carefully across the creaking, rotting wooden floorboards. A single oil lamp flickered weakly in the corner, casting long, eerie shadows over the cold body near the fireplace. Lord Pemberton lay sprawled and motionless, his glassy eyes wide open, a crimson stain spreading across his white evening shirt. Sarah knelt beside him, pressing two fingers against his neck, though she already knew the terrible truth about this night. Outside, thunder rumbled ominously while seven frightened guests waited upstairs, unaware that one of them was certainly a cold killer. She rose slowly, scanning the dim room for clues, noting the shattered wine glass beside the victim's outstretched right hand.
created_at
"2026-06-01T11:52:28.911Z"
6/1/2026, 11:52:28 AM
model
"anthropic/claude-4.8-opus-20260528"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3660
moderation_latency
(null)
generation_time
29852
tokens_prompt
46
tokens_completion
437
native_tokens_prompt
60
native_tokens_completion
3249
native_tokens_completion_images
(null)
native_tokens_reasoning
235
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
0.081525
router
(null)
provider_responses
0
endpoint_id
"b0d3beaa-5ff7-4666-a749-b1bb2b14c916"
id
"msg_01BAyZovgD5pakU2TVwpoUqH"
is_byok
false
latency
944
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-1780314748-OVAp9zxENkxclgkFZzQt"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1780314748-8F4AFNWIbllPYJkpu3kG"
upstream_id
"msg_01BAyZovgD5pakU2TVwpoUqH"
total_cost
0.081525
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Anthropic"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
sentences
6
wordCounts
0
20
1
20
2
20
3
20
4
20
5
20