NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-10-01KR91BBMW83TN8MQZ7R7B3D30
Run Details
Model:
Gemma 4 31B (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
5m 2s
Cost:
$0.003271
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
43.38%
Matches word count
(details)
99.20%
Dialogue to Total Word Ratio
(details)
71.2883%
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 unfolded the blueprint of the living room with surgical precision, tracing the narrow route to the gift table. "We hit the table at 14:00 hours," she whispered with a focused gaze. Bill frowned, chewing on a toothpick and looking deeply skeptical. "Why so early?" "The cake is a distraction, Bill! While the kids scream over frosting, we swoop in." Bill glanced at the front yard, where a suspicious man in a rainbow wig stood menacingly. "I don't like the clown. He looks shifty." "Ignore him. The Millennium Falcon is priority one." Bill struggled with his disguise, a giant, oversized teddy bear suit that smelled strongly of old mothballs and failure. "I can't breathe in this thing, Molly." "Suffering is part of the craft. Now, what’s the signal?" "A loud sneeze?" "No! We agreed on a whistle." "I'm just a bear!" Molly sighed, rubbing her temples in utter frustration as she stared at her partner. "Fine. Sneeze twice for 'clear,' once for 'too many toddlers.'" "What if I just sneeze normally?" "Then we're both going to juvenile hall." Bill adjusted his fuzzy head, nearly knocking over a lamp. "Fair point. Do we get cake?" "Focus, Bill! We are professionals. Now." "I love red velvet," Bill insisted with a goofy grin. Molly glared. "Just get in the suit."
created_at
"2026-05-10T13:31:11.396Z"
5/10/2026, 1:31:11 PM
model
"google/gemma-4-31b-it-20260402"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
190
moderation_latency
(null)
generation_time
302000
tokens_prompt
77
tokens_completion
7773
native_tokens_prompt
82
native_tokens_completion
8581
native_tokens_completion_images
(null)
native_tokens_reasoning
7426
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
0.00327144
router
(null)
provider_responses
0
endpoint_id
"4149ab03-3b69-45a0-b94c-6c253b8641a1"
id
"chatcmpl-R6j2BbbPnVCLty0spTml0JXX"
is_byok
false
latency
59
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-1778419871-VVtpnOyC101pJ75TOwgF"
session_id
(null)
api_type
"completions"
id
"gen-1778419871-mEMQn3q20oCmbPaHIBUD"
upstream_id
"chatcmpl-R6j2BbbPnVCLty0spTml0JXX"
total_cost
0.00327144
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepInfra"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
43.38%
Matches word count
n/a
neededClean
false
words
217
99.20%
Dialogue to Total Word Ratio
Ratio: 53.00%, Deviation: 3.00%
neededClean
false
wordsTotal
217
wordsDialogue
115
71.2883%