NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-10-01KR8XQ55Q3JYAJ8AMFQ2BMHT6
Run Details
Model:
Gemma 4 26B (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
2m 38s
Cost:
$0.000087
Provider:
DekaLLM
Evaluation summary
Score
Evaluator
Details Link
2.01%
Matches word count
(details)
98.88%
Dialogue to Total Word Ratio
(details)
50.4453%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% 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
"Check the perimeter, Bill," Molly commanded. "It's a bouncy castle, Molly. Not a high-security vault," Bill replied. "Precision is paramount. We penetrate the kitchen during the sugar-induced chaos of the cake cutting." "What if they start a magic show? I hate magicians. They're too twitchy." "Then we use their sleight of hand as our tactical cover. We hit the gift pile, secure the goods, and vanish." "The loot is mostly Lego and scented slime, Molly. Is this even worth the risk?" "It’s high-density plastic, Bill! Extremely liquidable on the secondary markets." "I don't know. A toddler's meltdown is more terrifying than a SWAT team." "Focus! We move fast, we grab the boxes, and we exit before the piñata explodes." "What if there’s a clown?" "Clowns are wildcards. We avoid the clown at all costs." "Right. Target: The brightly wrapped cardboard. Objective: Maximum glitter and minimal tantrums." "That’s the spirit. Now, grab the tactical juice boxes." "On it," Bill said, grabbing his tiny crowbar. "And the juice boxes, Bill! Don't forget the juice boxes!" Molly yelled.
created_at
"2026-05-10T12:27:43.678Z"
5/10/2026, 12:27:43 PM
model
"google/gemma-4-26b-a4b-it-20260403"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3939
moderation_latency
(null)
generation_time
157705
tokens_prompt
77
tokens_completion
6183
native_tokens_prompt
68
native_tokens_completion
250
native_tokens_completion_images
(null)
native_tokens_reasoning
5562
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
0.00008658
router
(null)
provider_responses
0
endpoint_id
"d99bcbe6-bec3-4991-965e-45fea79fe63c"
id
"chatcmpl-8cb873cc9414786070db38ff2c67fd48"
is_byok
false
latency
3939
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-1778416063-7yDx8YtbXQZIQjtrS78Z"
session_id
(null)
api_type
"completions"
id
"gen-1778416063-vJJoukkqZXAXCGx2OKRr"
upstream_id
"chatcmpl-8cb873cc9414786070db38ff2c67fd48"
total_cost
0.00008658
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DekaLLM"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
2.01%
Matches word count
n/a
neededClean
false
words
175
98.88%
Dialogue to Total Word Ratio
Ratio: 93.26%, Deviation: 3.26%
neededClean
false
wordsTotal
178
wordsDialogue
166
50.4453%