NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-10-01KR8XKBQZ6PHKAKGEM1HFB25W
Run Details
Model:
Gemma 4 26B
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
4.7s
Cost:
$0.000097
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
27.17%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
13.5829%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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 spread the blueprint across the sticky kitchen table. "The target is a seven-year-old’s birthday bash, Bill. High stakes." Bill squinted at the colorful diagram. "Is that a bounce house or a tactical obstacle course?" "It is both," Molly whispered, tapping a drawing of a clown. "The clown is the heavy security. We move during the cake cutting." "What about the juice box perimeter?" Bill asked, wiping sweat from his brow. "I heard they have unlimited fruit punch. It’s a sticky trap." "We wear gloves, Bill. No fingerprints in the frosting," Molly commanded. "And the presents? Are we talking high-end electronics or just plastic dinosaurs?" Molly leaned in close. "It is a treasure trove of LEGO sets and remote-controlled cars. Pure gold." "I need a distraction," Bill muttered, checking his empty pockets. "Something loud. Bubbles? A runaway pony?" "You will blow the bubbles," Molly decided. "I will swoop in, bag the gift boxes, and vanish before the 'Happy Birthday' song ends." "A daring plan," Bill grinned. "But what if the kid sees us?" "Then you start dancing, Bill. Just start dancing."
created_at
"2026-05-10T12:25:39.335Z"
5/10/2026, 12:25:39 PM
model
"google/gemma-4-26b-a4b-it-20260403"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
126
moderation_latency
(null)
generation_time
4596
tokens_prompt
77
tokens_completion
296
native_tokens_prompt
79
native_tokens_completion
268
native_tokens_completion_images
(null)
native_tokens_reasoning
0
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"
service_tier
(null)
usage
0.00009665
router
(null)
provider_responses
0
endpoint_id
"d71c6981-347d-4622-a86b-2c9e5d0f2c6c"
id
"chatcmpl-RYi7uZbOn0NfVCELPzJcWx5P"
is_byok
false
latency
63
model_permaslug
"google/gemma-4-26b-a4b-it-20260403"
provider_name
"DeepInfra"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1778415939-L7LjYXfBIu5KOeiFEIVi"
session_id
(null)
api_type
"completions"
id
"gen-1778415939-uyghWe3ImFAmK5MCwd9I"
upstream_id
"chatcmpl-RYi7uZbOn0NfVCELPzJcWx5P"
total_cost
0.00009665
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepInfra"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
27.17%
Matches word count
n/a
neededClean
false
words
181
0.00%
Dialogue to Total Word Ratio
Ratio: 75.14%, Deviation: 25.14%
neededClean
false
wordsTotal
185
wordsDialogue
139
13.5829%