NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-10-01KR8XEC213F8AYPHRY79N3YKV
Run Details
Model:
Gemma 4 26B (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
3m 51s
Cost:
$0.000094
Provider:
DekaLLM
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
100.0000%
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 stolen blueprint across the sticky kitchen table, her eyes narrowing with intense, professional focus. "The target is a five-year-old's birthday bash, Bill. This is high-stakes larceny." "Is there chocolate cake?" Bill asked, eyeing a stray chocolate crumb on his lip. "Focus! We enter via the bouncy castle. It’s the perfect soft-landing zone for a quick getaway." "What if I get stuck in the inflatable slide?" Bill whispered, his hands trembling slightly. "Then you’re a total liability," Molly snapped, pacing the small, dim room. "We grab the LEGO sets and the remote-controlled cars, then vanish before the clown arrives." "Do clowns work for the local police?" "They’re freelancers, Bill. Just stay low and avoid the juice boxes." "Juice boxes are a major tripping hazard," Bill muttered, looking genuinely worried about the mission. "Precisely. Now, grab the tactical diaper bag." "Does it come in blue?" Molly rubbed her aching temples, wondering if she should have hired a professional instead of a man who feared clowns and craved frosting. She stared at the colorful map, realizing their entire heist relied on a single piece of inflatable vinyl and a ridiculous amount of hope. It was going to be a disaster.
created_at
"2026-05-10T12:22:55.818Z"
5/10/2026, 12:22:55 PM
model
"google/gemma-4-26b-a4b-it-20260403"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
9920
moderation_latency
(null)
generation_time
231410
tokens_prompt
77
tokens_completion
6846
native_tokens_prompt
68
native_tokens_completion
273
native_tokens_completion_images
(null)
native_tokens_reasoning
7095
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
0.00009417
router
(null)
provider_responses
0
endpoint_id
"d99bcbe6-bec3-4991-965e-45fea79fe63c"
id
"chatcmpl-80038f9a196ce30f"
is_byok
false
latency
8693
model_permaslug
"google/gemma-4-26b-a4b-it-20260403"
provider_name
"DekaLLM"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1778415775-HZD1sUCCZaHPSSACK5lk"
session_id
(null)
api_type
"completions"
id
"gen-1778415775-oRAooyGE4g4CoQctFYwB"
upstream_id
"chatcmpl-80038f9a196ce30f"
total_cost
0.00009417
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DekaLLM"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
200
100.00%
Dialogue to Total Word Ratio
Ratio: 50.24%, Deviation: 0.24%
neededClean
false
wordsTotal
205
wordsDialogue
103
100.0000%