NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-10-01KR8VR49Z9PE7NXT089E5AG8V
Run Details
Model:
Gemma 4 26B (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
9m 8s
Cost:
$0.005632
Provider:
Parasail
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
99.9997%
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 crumpled blueprints over the grease-stained table. Bill stared at a shiny piece of glittery wrapping paper. He seemed more interested in the sparkles than the heist. He hummed a little tune while tapping his fingers rhythmically. Molly whispered, "The target is the Henderson residence, high concentration of LEGO sets and potentially a Nintendo Switch." Bill asked, "Do we need silly disguises? I have a clown suit and balloon animals." Molly hissed, "No clowns, Bill! We enter through the kitchen window during the cake cutting. That is our only window." Molly glared at him. She pointed her finger at a diagram of a bouncy castle. Bill wondered, "What about the bouncy castle? Could we use it for a high-speed escape?" She snapped, "It is a distraction, not a getaway vehicle." "Can I wear the festive party hat?" "Absolutely not." Molly rubbed her aching temples, wondering why she had never partnered with a professional. She sighed and stared at the white ceiling. She slammed her hand on the table. She breathed slowly. She insisted, "Think about the loot, Bill, the rewards are massive." Bill asked, "Will there be juice boxes?" Molly shouted, "Focus! Just focus on the mission, silly Bill!"
created_at
"2026-05-10T11:58:11.23Z"
5/10/2026, 11:58:11 AM
model
"google/gemma-4-26b-a4b-it-20260403"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
265
moderation_latency
(null)
generation_time
255334
tokens_prompt
77
tokens_completion
11351
native_tokens_prompt
82
native_tokens_completion
14054
native_tokens_completion_images
(null)
native_tokens_reasoning
11048
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
0.00563226
router
(null)
provider_responses
0
endpoint_id
"91f05fe1-9a18-4bcf-8cfa-093c369d8cea"
id
"chatcmpl-b30e40dc82b89d0f"
is_byok
false
latency
252
model_permaslug
"google/gemma-4-26b-a4b-it-20260403"
provider_name
"Parasail"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1778414291-1DjwvmWpCTYcdNsdRkw7"
session_id
(null)
api_type
"completions"
id
"gen-1778414291-lywiMczmKR81m9rIS3Am"
upstream_id
"chatcmpl-b30e40dc82b89d0f"
total_cost
0.00563226
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Parasail"
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: 49.50%, Deviation: 0.50%
neededClean
false
wordsTotal
202
wordsDialogue
100
99.9997%