NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-10-01KR90BEKZFCPJ7ACD940PMB9K
Run Details
Model:
Gemma 4 26B
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
16.6s
Cost:
$0.000075
Provider:
Cloudflare
Evaluation summary
Score
Evaluator
Details Link
2.01%
Matches word count
(details)
99.72%
Dialogue to Total Word Ratio
(details)
50.8642%
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
Molly spread the blueprints across the sticky picnic table, squinting through the haze of spilled juice boxes and glitter. The target was a suburban fortress of joy, currently defended by a sugar-high toddler in a dinosaur onesie. According to her reconnaissance, the haul consisted of three high-end gaming consoles, a collection of limited-edition action figures, and perhaps a very expensive remote-controlled drone disguised as a bubble machine. Bill leaned in, his tactical turtleneck looking absurdly out of place next to a pile of half-eaten cupcakes. He tapped a finger on the living room floor plan, specifically targeting the corner where the mountain of brightly wrapped boxes sat unguarded. "The bouncy castle is the primary obstacle," Molly whispered, her eyes narrowing with professional intensity. "We use the distraction of the clown," Bill replied, nodding solemnly. The plan was madness. They would infiltrate during the peak of the cake-cutting ritual, utilizing a smoke bomb disguised as a balloon animal to facilitate their exit. It was high-stakes larceny, wrapped in polka dots and smelling faintly of strawberry frosting.
created_at
"2026-05-10T13:13:45.862Z"
5/10/2026, 1:13:45 PM
model
"google/gemma-4-26b-a4b-it-20260403"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
289
moderation_latency
(null)
generation_time
5743
tokens_prompt
77
tokens_completion
292
native_tokens_prompt
79
native_tokens_completion
225
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
0.0000754
router
(null)
provider_responses
0
endpoint_id
"e22ce918-7adb-4e4f-b2e2-c6c5b3066b69"
is_byok
false
latency
651
model_permaslug
"google/gemma-4-26b-a4b-it-20260403"
provider_name
"NextBit"
status
429
1
endpoint_id
"d71c6981-347d-4622-a86b-2c9e5d0f2c6c"
is_byok
false
latency
47
model_permaslug
"google/gemma-4-26b-a4b-it-20260403"
provider_name
"DeepInfra"
status
429
2
endpoint_id
"d99bcbe6-bec3-4991-965e-45fea79fe63c"
is_byok
false
latency
10077
model_permaslug
"google/gemma-4-26b-a4b-it-20260403"
provider_name
"DekaLLM"
status
504
3
endpoint_id
"e2a16fa6-1f65-413e-9ecb-93901089ddb1"
id
"id-1778418836884"
is_byok
false
latency
249
model_permaslug
"google/gemma-4-26b-a4b-it-20260403"
provider_name
"Cloudflare"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1778418825-XCKs9SNpueK9hAVmaYQ2"
session_id
(null)
api_type
"completions"
id
"gen-1778418825-qzfMaM5PW97xiDxIsiaZ"
upstream_id
"id-1778418836884"
total_cost
0.0000754
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Cloudflare"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
2.01%
Matches word count
n/a
neededClean
false
words
175
99.72%
Dialogue to Total Word Ratio
Ratio: 7.69%, Deviation: 2.31%
neededClean
false
wordsTotal
182
wordsDialogue
14
50.8642%