NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1M1K662KW72JQM6NTKP0D11
Run Details
Model:
Qwen 3.8 27B (Reasoning, XHigh)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
2m 12s
Cost:
$0.026155
Provider:
AkashML
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 50% 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
Bill unfolded a napkin map on the cake table while Molly tucked a tiny grappling hook into her party hat. "The presents are stacked behind the balloon arch." Bill pointed at the glittery boxes, his eyes bright with criminal ambition. "We need to be gentle." Molly adjusted her paper hat, pretending she was not a felon. "Gentle? We are thieves, not babysitters." Bill held a lollipop like a microphone. "Yes, but these children believe in Santa." Molly pointed at a photo of a child holding a crayon. "Exactly. We are the good guys." Bill winked at the clown balloon. "Then we must steal only ugly sweaters." Molly shuddered, remembering a Christmas she survived. "All the presents, Bill. Every one." Bill spread his fingers, promising total theft. "That is a greedy plan." Molly opened the tiny escape window. "It is an elegant plan." Bill placed a glitter bomb on the table. "With a backup plan." Molly slid the cake pan. "Our backup plan is cake." "Cake is not a plan." "Cake is the best plan." "The clown knows our face." "Then we wear the clown hats." "We are not funny." "We are hilarious." "Let us begin." "May the presents be merry."
created_at
"2026-09-03T16:28:23.183Z"
9/3/2026, 4:28:23 PM
model
"qwen/qwen3.8-27b-20260814"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
777
moderation_latency
(null)
generation_time
132305
tokens_prompt
75
tokens_completion
8301
native_tokens_prompt
118
native_tokens_completion
10447
native_tokens_completion_images
(null)
native_tokens_reasoning
8007
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
0.02615526
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788452903-KTTF7XqjxQQ5g5Pmwl6V"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788452903-5GoNqHwAK5PqtzgPDxuL"
upstream_id
"chatcmpl-9be13d07f7f233d7"
provider_responses
0
endpoint_id
"c15e008c-6180-4155-8707-bde541bc7884"
id
"chatcmpl-9be13d07f7f233d7"
is_byok
false
latency
777
model_permaslug
"qwen/qwen3.8-27b-20260814"
provider_name
"AkashML"
status
200
total_cost
0.02615526
cache_discount
(null)
upstream_inference_cost
0
provider_name
"AkashML"
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: 50.00%, Deviation: 0.00%
neededClean
false
wordsTotal
200
wordsDialogue
100
100.0000%