NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-02-25-01KJBGM1F30NCZTYATR95W7AHP
Run Details
Model:
Qwen 3.5 27B
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
2m 1s
Cost:
$0.030047
Provider:
Alibaba
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
99.85%
Dialogue to Total Word Ratio
(details)
99.9258%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% 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 adjusted her disguise. Bill checked his pockets very nervously. "Okay, Bill. The plan is simple. We infiltrate during the cake cutting." "What about the parents? They have eyes everywhere." "They'll be too busy blowing out candles to notice us vanishing the Lego sets." "And the dolls? The action figures?" "Straight into the van. Don't forget the slime. It's gold." "Slime? I'm not smuggling sticky green goo in my vest." "It's high value, Bill. Kids love it. We can sell it on the market." "The black market for birthday gifts? Who buys stolen presents?" "Exactly. Look, just grab the wrapped boxes. Leave the balloons. They're too bulky." "What if the clown sees us? He looks suspicious." "Then we steal the clown too. He's wearing a costume we can sell." "I hate working with you. You're insane." "You love the loot. Now, check your grappling hook." "It's a fishing line, Molly. We're not Batman." "Details. Point is, we get the toys. We get out. We don't eat the cake." "No cake? I'm starving." "Calories count, Bill. Now let's go before the piƱata breaks." "Do we get the party favors?" "Only if they contain candy." Bill sighed and kicked a pebble.
created_at
"2026-02-25T23:02:22.445Z"
2/25/2026, 11:02:22 PM
model
"qwen/qwen3.5-27b-20260224"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
445
moderation_latency
(null)
generation_time
121274
tokens_prompt
77
tokens_completion
9241
native_tokens_prompt
76
native_tokens_completion
12510
native_tokens_completion_images
(null)
native_tokens_reasoning
12213
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
0.0300468
router
(null)
provider_responses
0
endpoint_id
"f3f88554-0c22-4d57-973b-0dec948808e8"
id
"chatcmpl-010000b7-0630-9de6-9b4f-c1e90f925000"
is_byok
false
latency
445
model_permaslug
"qwen/qwen3.5-27b-20260224"
provider_name
"Alibaba"
status
200
api_type
"completions"
id
"gen-1772060542-U9iPepPtc71BwWm4P3T7"
upstream_id
"chatcmpl-010000b7-0630-9de6-9b4f-c1e90f925000"
total_cost
0.0300468
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Alibaba"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
199
99.85%
Dialogue to Total Word Ratio
Ratio: 91.96%, Deviation: 1.96%
neededClean
false
wordsTotal
199
wordsDialogue
183
99.9258%