NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-10-01KR8YFKNF14EFP43ACARZGN7B
Run Details
Model:
Gemma 4 31B (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
1m 31s
Cost:
$0.001013
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
36.79%
Dialogue to Total Word Ratio
(details)
68.3935%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% 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
"Alright, Bill. The target is a six-year-old's birthday bash." "Why kids? That's low, even for us." "It's not low, it's strategic. The loot is concentrated in one single pile." "And the security?" "A sleepy golden retriever and a very stressed mother." "I can handle a dog. But what about the cake? Is it chocolate?" "Focus, Bill! We enter through the hedge, grab the Lego sets, and vanish before the piñata drops." "What if I want a piece of the piñata? I love the candy." "You're a professional thief, not a toddler." "I'm a professional thief who happens to like saltwater taffy." "Do you have the costumes ready?" "Two oversized clown suits. Why?" "Because we're blending in, Bill. No one suspects a clown." "I look ridiculous in polka dots." "You look like a distraction. Now, check the map. Where's the gift table?" "Right next to the juice boxes. I'm in." "Just don't get distracted by the bouncy castle." "I make no promises, Molly. I've always wanted to see how high I can bounce." "We are not bouncing, Bill. We are stealing." "Fine. But I'm taking a juice box and maybe one small toy." "No toys, Bill!" "Fine, just the juice."
created_at
"2026-05-10T12:41:04.952Z"
5/10/2026, 12:41:04 PM
model
"google/gemma-4-31b-it-20260402"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
271
moderation_latency
(null)
generation_time
91075
tokens_prompt
77
tokens_completion
2434
native_tokens_prompt
82
native_tokens_completion
2638
native_tokens_completion_images
(null)
native_tokens_reasoning
2132
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
0.0010131
router
(null)
provider_responses
0
endpoint_id
"4149ab03-3b69-45a0-b94c-6c253b8641a1"
id
"chatcmpl-RmV5BSRIEnoBGUAUEl0thuk3"
is_byok
false
latency
64
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-1778416864-oHVH6rlgEQRaW7iWkSHG"
session_id
(null)
api_type
"completions"
id
"gen-1778416864-pqOixcX6tWoV3IpHJXBS"
upstream_id
"chatcmpl-RmV5BSRIEnoBGUAUEl0thuk3"
total_cost
0.0010131
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
199
36.79%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
201
wordsDialogue
201
68.3935%