NC Bench
Overview
About
Tests
Models
Model
Z.AI GLM 4.6
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2026-02-08-01KGYYZ8ET6N850A54N6KF2TDY
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 tapped the diagram. “Target: the Richardson place. The party's in the backyard. We go in through the side gate during the piñata chaos.” “Brilliant,” Bill whispered, adjusting his balaclava. “What’s the estimated payload? Are we talking LEGOs or high-end action figures?” “Focus on the objective, Bill. We grab everything from the gift table and exfiltrate. The getaway car is idling two blocks down.” “But what about the clown? He’s an unknown variable. Does he juggle chainsaws? We need intel.” “He makes balloon animals, Bill. He’s not an enforcer.” “Still. A giraffe could be used as a garrote. It’s a calculated risk. I’ll take point.” “You are not taking point on a clown.” “Fine. But I’m bringing the extra-large duffel bag. We’ll need it for the big-ticket items. I hear someone got a remote-control dinosaur.” “Just get the bag, Bill. And try to look less like you’re stealing candy from a baby.” “But that is literally the plan, Molly.”
created_at
"2026-02-08T15:48:26.753317+00:00"
Sunday, February 8th, 2026 at 3:48:26 PM GMT+00:00
model
"z-ai/glm-4.6"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2725
moderation_latency
(null)
generation_time
65605
tokens_prompt
61
tokens_completion
2144
native_tokens_prompt
66
native_tokens_completion
2159
native_tokens_completion_images
(null)
native_tokens_reasoning
1952
native_tokens_cached
32
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
0.0037738399999776
router
(null)
provider_responses
0
id
"chatcmpl-R4EVGS3dO1f1agFukrnQmgtH"
status
200
is_byok
false
latency
69
endpoint_id
"c8607edc-8577-4199-b03d-1213da4743dc"
provider_name
"DeepInfra"
model_permaslug
"z-ai/glm-4.6"
api_type
"completions"
id
"gen-1770565640-leh0Fk6VSkHk2t0H5aSi"
upstream_id
"chatcmpl-R4EVGS3dO1f1agFukrnQmgtH"
total_cost
0.0037738399999776
cache_discount
0.0000112000000224
upstream_inference_cost
0
provider_name
"DeepInfra"
Evaluation details
Result
Evaluator
Details
Meta Data
0.0000%
Matches word count
n/a
neededClean
false
words
162
96.1733%
Dialogue to Total Word Ratio
Ratio: 94.44%, Deviation: 4.44%
neededClean
false
wordsTotal
162
wordsDialogue
153
48.0866%