NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-10-01KR91C6Y8HV0FNSNTEZNDE6B0
Run Details
Model:
Gemma 4 31B (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
4m 40s
Cost:
$0.003117
Provider:
DeepInfra
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 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 smoothed out the grease-stained blueprint of the suburban backyard with a precision usually reserved for brain surgery. She pointed a manicured finger at the strategic placement of the bouncy castle, noting it as the primary distraction zone. Bill sat beside her, chewing loudly on a piece of lukewarm pizza while wearing a disguise that consisted mostly of an oversized Hawaiian shirt and sunglasses. He looked less like a professional infiltrator and more like a tourist who had lost his way to the beach. They had spent three hours calculating the exact trajectory of rogue toddlers to ensure a clean getaway. The target was a hoard of high-end building blocks and expensive remote-controlled drones. The security was minimal, consisting primarily of a golden retriever with a penchant for napping. Molly checked her watch, her eyes gleaming with a greed that was entirely disproportionate to the value of plastic toys. She adjusted her tactical tutu, ensuring the hidden pockets were reinforced for maximum loot capacity. Bill sighed, accidentally spraying a crumb of crust onto the greasy blueprint. "Is the coast clear now?" Molly whispered. Bill peeked. "Yes, the children are finally eating the birthday cake, so we must move very quickly."
created_at
"2026-05-10T13:31:39.344Z"
5/10/2026, 1:31:39 PM
model
"google/gemma-4-31b-it-20260402"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
170
moderation_latency
(null)
generation_time
279385
tokens_prompt
77
tokens_completion
7768
native_tokens_prompt
82
native_tokens_completion
8174
native_tokens_completion_images
(null)
native_tokens_reasoning
7454
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
0.00311678
router
(null)
provider_responses
0
endpoint_id
"4149ab03-3b69-45a0-b94c-6c253b8641a1"
id
"chatcmpl-RHsWNWGChJkTddF0xsX5VB0x"
is_byok
false
latency
45
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-1778419899-veGaAuPKjdwzXJlR48KE"
session_id
(null)
api_type
"completions"
id
"gen-1778419899-qlmkdbn6WB0y0AUXVIjm"
upstream_id
"chatcmpl-RHsWNWGChJkTddF0xsX5VB0x"
total_cost
0.00311678
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: 9.85%, Deviation: 0.15%
neededClean
false
wordsTotal
203
wordsDialogue
20
100.0000%