NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1KZYNYGE5JNJRSMMM3YDCMZ
Run Details
Model:
Qwen 3.8 27B (Reasoning, XHigh)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
2m 41s
Cost:
$0.019301
Provider:
Reka
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
100.0000%
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 polished her glittery wig, because the party was bright, loud, and full of children who noticed every clumsy adult. Bill rehearsed his sneeze in the bathroom mirror, which was decorated with crayon stars and a sticky handprint on glass. “The clown is a guard.” The invitation claimed birthday, but the lawn had tripwires, and the punch bowl hummed like a suspicious metal refrigerator nearby. They had studied the schedule carefully: cake at three, piñata at four, gifts under a giant inflatable unicorn in back. “I’ll dress as a birthday cake.” Molly slipped a tiny screwdriver behind a cupcake, then checked the moon, which looked annoyed by the streamers and confetti. “We grab every wrapped box.” Bill tucked a laser pointer into his sock because a party hat without gadgets felt emotionally incomplete to him anyway. “Then we bow politely.” The piñata had a security tag shaped like a star, so they needed a quiet way to disable it now. Children would arrive soon, carrying juice boxes, juice boxes that might be cameras, juice boxes that always were cameras, apparently. Bill wore a paper crown because he believed authority helped, even if the crown was already crooked and looking sad.
created_at
"2026-09-03T15:59:42.551Z"
9/3/2026, 3:59:42 PM
model
"qwen/qwen3.8-27b-20260814"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
214
moderation_latency
(null)
generation_time
161110
tokens_prompt
75
tokens_completion
6604
native_tokens_prompt
118
native_tokens_completion
7558
native_tokens_completion_images
(null)
native_tokens_reasoning
6296
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
"stop"
service_tier
(null)
usage
0.01930122
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788451182-FW8QTgaZKo1pJz3qa9iv"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788451182-b0xNjm8fz0rckSzXOEuI"
upstream_id
"chatcmpl-4725cce2-8a9d-4a8b-99ce-d2e982ea0d88"
provider_responses
0
endpoint_id
"15086968-df2f-4d69-86bb-c74c31644bb6"
id
"chatcmpl-4725cce2-8a9d-4a8b-99ce-d2e982ea0d88"
is_byok
false
latency
214
model_permaslug
"qwen/qwen3.8-27b-20260814"
provider_name
"Reka"
status
200
total_cost
0.01930122
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Reka"
response_cache_source_id
(null)
data_region
"global"
workspace_id
"97e315e5-d303-487d-83c1-83180e8a13d4"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
200
100.00%
Dialogue to Total Word Ratio
Ratio: 10.00%, Deviation: 0.00%
neededClean
false
wordsTotal
200
wordsDialogue
20
100.0000%