NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ0135JEYFHG25E7WA22A5FP
Run Details
Model:
Z.AI GLM 4.5 Air
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
29.5s
Cost:
$0.000520
Provider:
SiliconFlow
Evaluation summary
Score
Evaluator
Details Link
99.74%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
49.8722%
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: Right, Bill. The birthday bash. presents galore. Operation Pilfer Presents. Bill: Molly, it's for little Timmy! He's seven! Molly: Precisely. Unsuspecting parents. Sugar-fueled chaos. The perfect cover. We blend. Bill: Blend? We look like... us! And the kids will scream! Molly: We come as entertainment. Clowns? Too obvious. Face painters? Patience isn't our strong suit. I've got it: balloon animals! Bill: Balloon animals? How does that help us grab the loot? Molly: Distraction, Bill! While I'm twisting a giraffe taller than you, you grab the loot. Fast, quiet. Slip it into these. Bill: These look like... giant candy canes? Molly: Disguise! We just waddle out! No one suspects the walking candy cane brigade. Bill: And the security? Timmy's Uncle Barry looks like he could bench press a car. Molly: He'll be too busy eating cake and judging my poodle balloon. Focus, Bill. Timing is everything. We strike when the piƱata explodes. Total pandemonium. Bill: Okay... balloon animals, candy cane bags... Uncle Barry... pandemonium... Got it. Just tell me again: why are we stealing from a seven-year-old? Molly: Because the presents are brand new, Bill! Untraceable! And it's hilarious. Now, practice your waddle. Smooth and sneaky.
created_at
"2026-04-24T15:17:51.324Z"
4/24/2026, 3:17:51 PM
model
"z-ai/glm-4.5-air"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
6967
moderation_latency
(null)
generation_time
29278
tokens_prompt
77
tokens_completion
653
native_tokens_prompt
66
native_tokens_completion
594
native_tokens_completion_images
(null)
native_tokens_reasoning
276
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"
usage
0.00052008
router
(null)
provider_responses
0
endpoint_id
"90fc9bb3-01bb-419f-bb58-dea60a80d201"
is_byok
false
latency
121
model_permaslug
"z-ai/glm-4.5-air"
provider_name
"Novita"
status
429
1
endpoint_id
"f7dc79ca-bbbd-41a1-8eef-616d981ff1cb"
id
"019dc0119e04078058470bcb7b76b453"
is_byok
false
latency
6949
model_permaslug
"z-ai/glm-4.5-air"
provider_name
"SiliconFlow"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777043871-dBolofP3etOPjf8DgIce"
session_id
(null)
api_type
"completions"
id
"gen-1777043871-G9ntuaU08v0LDLknPqXI"
upstream_id
"019dc0119e04078058470bcb7b76b453"
total_cost
0.00052008
cache_discount
(null)
upstream_inference_cost
0
provider_name
"SiliconFlow"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
99.74%
Matches word count
n/a
neededClean
false
words
196
0.00%
Dialogue to Total Word Ratio
Ratio: 0.00%, Deviation: 90.00%
neededClean
false
wordsTotal
199
wordsDialogue
0
49.8722%