NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-10-01KR8Y5JXPY37GMQR8VP5Q0T33
Run Details
Model:
Gemma 4 31B (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
4m 35s
Cost:
$0.003773
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 adjusted her oversized neon sunglasses, staring at the suburban bungalow where a fleet of clown cars had already parked. Beside her, Bill was struggling with a tiny, child-sized tuxedo that restricted his breathing and made him look like a very anxious penguin. They had spent three weeks studying the birthday boy's schedule, noting the precise moment the cake would distract the adults. The plan was simple: infiltrate the bouncy castle, secure the gift table, and vanish before the piƱata exploded. Bill wiped sweat from his brow, his eyes darting toward the perimeter guards, who were actually just three toddlers in dinosaur pajamas. Molly checked her stopwatch, noting that the chaos was reaching its peak. The scent of frosting and desperation hung heavy in the summer air. She nudged Bill, who was currently fighting a losing battle with his bow tie. He looked like he was about to faint from a combination of heatstroke and polyester-induced suffocation. They crouched lower in the hydrangea bushes, blending into the floral landscape. Molly whispered, looking intently at the flashing lights of the party. "Ready for the loot? Let's go now!" "I can't breathe, Molly. This suit is a total, absolute, shimmering death trap."
created_at
"2026-05-10T12:35:36.51Z"
5/10/2026, 12:35:36 PM
model
"google/gemma-4-31b-it-20260402"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
236
moderation_latency
(null)
generation_time
274806
tokens_prompt
77
tokens_completion
6992
native_tokens_prompt
82
native_tokens_completion
9902
native_tokens_completion_images
(null)
native_tokens_reasoning
6679
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
0.00377342
router
(null)
provider_responses
0
endpoint_id
"4149ab03-3b69-45a0-b94c-6c253b8641a1"
id
"chatcmpl-RoRhEm6xfLMyExyxvkM7oOqp"
is_byok
false
latency
54
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-1778416536-xdfuvf5Cy24BASeE4XDV"
session_id
(null)
api_type
"completions"
id
"gen-1778416536-RaBjiDKOzHSmX4FlWvXE"
upstream_id
"chatcmpl-RoRhEm6xfLMyExyxvkM7oOqp"
total_cost
0.00377342
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: 9.90%, Deviation: 0.10%
neededClean
false
wordsTotal
202
wordsDialogue
20
100.0000%