NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-10-01KR8YJB5G96FDVD82K9ZN2HE5
Run Details
Model:
Gemma 4 31B (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
4m 4s
Cost:
$0.002928
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
99.9986%
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 pointed at the blueprint of the suburban living room, her expression grim. She traced a strategic line from the dog door to the mahogany gift pile. "The target is the center table. We're looking at a high concentration of LEGOs and latest-model iPads," she whispered. "Why on earth do we need a complex diversion? It is just a bunch of noisy seven-year-olds." "Kids are chaotic agents of destruction, Bill! One sticky-fingered toddler and the whole operation is blown." Bill sighed, adjusting his oversized disguise—a giant plush penguin suit that smelled faintly of mothballs and old laundry. He looked ridiculous, yet he felt confident. "I've got the distraction covered. I'll simply pretend to be the hired entertainment." "You can't dance, Bill. You have the grace of a falling wardrobe." "I can wiggle well." Molly groaned and checked her watch. The party started in ten minutes. She handed him a bag of high-grade glitter bombs for the tactical retreat. "Just wiggle toward the presents and keep the screaming to a minimum." "Got it. Operation Birthday Bash is officially a go." She adjusted her headset, staring intensely at the suburban driveway, waiting for the first guest to arrive with a balloon.
created_at
"2026-05-10T12:42:34.561Z"
5/10/2026, 12:42:34 PM
model
"google/gemma-4-31b-it-20260402"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
164
moderation_latency
(null)
generation_time
243832
tokens_prompt
77
tokens_completion
6386
native_tokens_prompt
82
native_tokens_completion
7676
native_tokens_completion_images
(null)
native_tokens_reasoning
6073
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
0.00292754
router
(null)
provider_responses
0
endpoint_id
"4149ab03-3b69-45a0-b94c-6c253b8641a1"
id
"chatcmpl-Roc7d2hFzzdlsbqxP4QQ8L19"
is_byok
false
latency
67
model_permaslug
"google/gemma-4-31b-it-20260402"
provider_name
"DeepInfra"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1778416954-8etBKF2OEOsK7qMBXMqV"
session_id
(null)
api_type
"completions"
id
"gen-1778416954-q6ZeHn0v1t0sNhYXuefc"
upstream_id
"chatcmpl-Roc7d2hFzzdlsbqxP4QQ8L19"
total_cost
0.00292754
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepInfra"
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: 50.73%, Deviation: 0.73%
neededClean
false
wordsTotal
205
wordsDialogue
104
99.9986%