NC Bench
Overview
About
Tests
Models
Model
Z.AI GLM 4.6
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2026-02-08-01KGYZMJPQ1SRNRRDCCZX8BH2H
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 peered through binoculars at the brightly colored house. “Okay, presents are staged by the fireplace. The main obstacle is the bouncy castle.” “What about Patches the Clown? He looks shifty,” Bill whispered, adjusting his ski mask. “You’re the diversion. Engage the target. Ask for a complex balloon animal.” “A complex what? Last time he made me a worm, Molly. A worm! I have a reputation to maintain.” “Your reputation is that you can carry a lot of loot. Now, the kids are the real threat. They’re sticky, unpredictable, and I’ve seen at least three with glitter. That’s a biohazard.” Bill squinted. “So I dodge the glitter, distract the clown, and what? Make a run for it through the Crying Zone?” “Exactly. I’ll be in and out. Thirty seconds. Don’t get your face painted.” “Right. No face paint. What if he offers me one of those candy cigarettes? I can’t refuse professional courtesy.” “Bill, for the last time, a party clown is not a peer in our field. Just grab the balloon poodle and run.”
created_at
"2026-02-08T16:00:09.888117+00:00"
Sunday, February 8th, 2026 at 4:00:09 PM GMT+00:00
model
"z-ai/glm-4.6"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
4874
moderation_latency
(null)
generation_time
69789
tokens_prompt
61
tokens_completion
1645
native_tokens_prompt
66
native_tokens_completion
1653
native_tokens_completion_images
(null)
native_tokens_reasoning
1444
native_tokens_cached
64
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
0.0028821999999552
router
(null)
provider_responses
0
id
"chatcmpl-RAySf70G1z7XWFOxx9zrjjf5"
status
200
is_byok
false
latency
116
endpoint_id
"c8607edc-8577-4199-b03d-1213da4743dc"
provider_name
"DeepInfra"
model_permaslug
"z-ai/glm-4.6"
api_type
"completions"
id
"gen-1770566339-PRcqqBXKY9lDhUM722gB"
upstream_id
"chatcmpl-RAySf70G1z7XWFOxx9zrjjf5"
total_cost
0.0028821999999552
cache_discount
0.0000224000000448
upstream_inference_cost
0
provider_name
"DeepInfra"
Evaluation details
Result
Evaluator
Details
Meta Data
2.0116%
Matches word count
n/a
neededClean
false
words
175
99.9999%
Dialogue to Total Word Ratio
Ratio: 90.29%, Deviation: 0.29%
neededClean
false
wordsTotal
175
wordsDialogue
158
51.0058%