NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-10-01KR91ZM9SRT4CA224KJ36JGXQ
Run Details
Model:
Gemma 4 26B
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
3.9s
Cost:
$0.000082
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
6.09%
Matches word count
(details)
68.88%
Dialogue to Total Word Ratio
(details)
37.4836%
Overall
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
The blueprints spread across the grease-stained table were not for a high-security vault, but a sprawling suburban backyard decorated with primary colors and aggressive amounts of glitter. Molly traced a finger along the perimeter of the bouncy castle, her eyes narrowing with the intensity of a diamond thief eyeing a laser grid. She adjusted her tactical goggles, which were actually just oversized swimming goggles she’d found in the junk drawer. Bill sat opposite her, struggling to fold a heavy-duty black jumpsuit that smelled faintly of mothballs and desperation. He checked his watch, which was currently set to the wrong time zone because he’d accidentally toggled the daylight savings setting. The target was the Henderson residence, currently hosting a third birthday party for a child named Leo who possessed an alarming number of dinosaur-themed gift boxes. They needed to navigate the obstacle course of juice boxes and sticky fingers without triggering the ultimate alarm: a group of hyperactive toddlers. It was a high-stakes extraction of stuffed animals and remote-controlled cars. "Focus, Bill," Molly whispered. "I'm focused," Bill muttered.
created_at
"2026-05-10T13:42:15.617Z"
5/10/2026, 1:42:15 PM
model
"google/gemma-4-26b-a4b-it-20260403"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
98
moderation_latency
(null)
generation_time
3739
tokens_prompt
77
tokens_completion
296
native_tokens_prompt
79
native_tokens_completion
224
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
0.00008169
router
(null)
provider_responses
0
endpoint_id
"d71c6981-347d-4622-a86b-2c9e5d0f2c6c"
id
"chatcmpl-RCwJoN4vFiTdTWRVkYcqNcey"
is_byok
false
latency
73
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-1778420535-vB4BwzOQxEKwtS5dBg0F"
session_id
(null)
api_type
"completions"
id
"gen-1778420535-BSRG3SwBJZJfziXT2LaY"
upstream_id
"chatcmpl-RCwJoN4vFiTdTWRVkYcqNcey"
total_cost
0.00008169
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepInfra"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
6.09%
Matches word count
n/a
neededClean
false
words
177
68.88%
Dialogue to Total Word Ratio
Ratio: 2.19%, Deviation: 7.81%
neededClean
false
wordsTotal
183
wordsDialogue
4
37.4836%