NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-10-01KR8Z3RA7KKVZ9BD6XC20JTV5
Run Details
Model:
Gemma 4 31B (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
3m 28s
Cost:
$0.002423
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
99.9982%
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 blueprint of the suburban living room across the greasy dashboard of their getaway van. It was a high-stakes operation targeting a six-year-old’s birthday bash. Bill stared intensely at the diagram, his face smeared with leftover cake from a previous scouting mission. He pointed a trembling finger at the primary objective: the oversized pile of brightly wrapped boxes near the refreshment table. The security was minimal, consisting mostly of a confused golden retriever and a distracted mother. Molly checked her stopwatch, calculating the precise moment the sugar-induced frenzy would peak. "Is the wig too much?" Bill asked nervously. Molly looked at his neon-green afro and sighed. "It is absolutely perfect, Bill. Trust me." "I feel ridiculous," Bill whispered. They planned to enter during the piñata disaster, utilizing the resulting confetti storm as tactical cover. The target was clear, the stakes were low, but the potential loot of Lego sets and remote-controlled cars was immense. Molly gripped the steering wheel, her eyes narrowing with predatory focus. "Execute the plan now," she commanded firmly. They slid the door open, stepping out into the sunshine with the grim determination of soldiers entering a war zone, if that war zone featured balloons.
created_at
"2026-05-10T12:52:05.071Z"
5/10/2026, 12:52:05 PM
model
"google/gemma-4-31b-it-20260402"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
399
moderation_latency
(null)
generation_time
208359
tokens_prompt
77
tokens_completion
5277
native_tokens_prompt
82
native_tokens_completion
6347
native_tokens_completion_images
(null)
native_tokens_reasoning
4943
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
0.00242252
router
(null)
provider_responses
0
endpoint_id
"4149ab03-3b69-45a0-b94c-6c253b8641a1"
id
"chatcmpl-RlAbAogGp6djMP0VDD9DuLM7"
is_byok
false
latency
49
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-1778417525-8qoWRefDQtSnpSOVDvOd"
session_id
(null)
api_type
"completions"
id
"gen-1778417525-ssd1fQbdcYoEPV0PZHoq"
upstream_id
"chatcmpl-RlAbAogGp6djMP0VDD9DuLM7"
total_cost
0.00242252
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: 9.22%, Deviation: 0.78%
neededClean
false
wordsTotal
206
wordsDialogue
19
99.9982%