NC Bench
Overview
About
Tests
Models
Model
Z.AI GLM 4.7
Test
Dialogue tags
Scenario
Write 200 words with 10% dialogue
Run ID
2026-02-08-01KGYY0QZ1Q9MG979QA2T83YYR
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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 adjusted his oversized, squeaky clown nose while peering through the dense rhododendrons at the target suburban backyard. The castle-themed bounce house loomed ahead like a colorful, inflatable beast guarding the treasure trove of expensive wrapping paper and satin bows. Molly, squeezed into a polyester fairy tutu that strained against every seam, checked her wristwatch with the grim precision of a bomb disposal expert. She had calculated the exact millisecond the mediocre magician would pull the live rabbit out of the hat, creating the necessary sensory overload for their ingress. The logistics were brutal; navigating a minefield of sticky toddlers and spilled juice boxes required agility they simply didn't possess. Bill signaled that the perimeter was clear, his face painted with a greasepaint smile that barely masked his desperate need for a new toaster oven. They weren't just stealing plastic toys; they were stealing the unadulterated joy of six-year-olds. "Is the target piƱata filled with high grade explosives?" Bill asked. "No, strictly high-fructose corn syrup," Molly replied.
created_at
"2026-02-08T15:33:34.90384+00:00"
Sunday, February 8th, 2026 at 3:33:34 PM GMT+00:00
model
"z-ai/glm-4.7-20251222"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
297
moderation_latency
(null)
generation_time
173743
tokens_prompt
61
tokens_completion
3876
native_tokens_prompt
66
native_tokens_completion
3893
native_tokens_completion_images
(null)
native_tokens_reasoning
4101
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
0.00682891
router
(null)
provider_responses
0
id
"chatcmpl-Rp7e7r5Y39qYTlygBiwdJuhn"
status
200
is_byok
false
latency
74
endpoint_id
"ab79ffa8-8dcc-41c4-9a9f-6cc408135243"
provider_name
"DeepInfra"
model_permaslug
"z-ai/glm-4.7-20251222"
api_type
"completions"
id
"gen-1770564640-7tv5qaEf9Sv5ojkxuB3X"
upstream_id
"chatcmpl-Rp7e7r5Y39qYTlygBiwdJuhn"
total_cost
0.00682891
cache_discount
0.00001024
upstream_inference_cost
0
provider_name
"DeepInfra"
Evaluation details
Result
Evaluator
Details
Meta Data
0.0848%
Matches word count
n/a
neededClean
false
words
171
99.9773%
Dialogue to Total Word Ratio
Ratio: 8.77%, Deviation: 1.23%
neededClean
false
wordsTotal
171
wordsDialogue
15
50.0310%