NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-10-01KR8Y52N2HQV1K80ZBHWC6JVV
Run Details
Model:
Gemma 4 31B
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
9.3s
Cost:
$0.000103
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
99.98%
Matches word count
(details)
82.86%
Dialogue to Total Word Ratio
(details)
91.4198%
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 blueprints of the suburban living room across the kitchen table with the intensity of a general plotting an invasion. She had meticulously mapped out the perimeter, identifying the strategic locations of the cake table and the high-risk zone near the bouncy castle. Bill stood beside her, wearing a tactical turtleneck that was slightly too tight for his frame, while chewing nervously on a piece of string. He eyed the diagram of the gift pile, which Molly had circled in aggressive red ink. The target was a mountain of plastic building blocks and plush unicorns, unguarded save for a distracted father and a golden retriever. Molly pointed a laser pointer at the ventilation duct, explaining the entry point. She insisted that stealth was paramount to avoid the sticky fingers of thirty sugar-crazed toddlers. Bill shifted his weight, worrying about the logistical challenge of transporting twelve oversized teddy bears without a getaway vehicle. He looked at her with genuine concern. "Is the glitter-bomb decoy ready?" Bill whispered. "Obviously," Molly snapped. She tapped a small metallic sphere on the table, imagining the chaos that would ensue when the children discovered a shimmering distraction. The heist was perfectly timed for the piƱata massacre.
created_at
"2026-05-10T12:35:19.851Z"
5/10/2026, 12:35:19 PM
model
"google/gemma-4-31b-it-20260402"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1500
moderation_latency
(null)
generation_time
9204
tokens_prompt
77
tokens_completion
326
native_tokens_prompt
79
native_tokens_completion
243
native_tokens_completion_images
(null)
native_tokens_reasoning
0
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
0.00010261
router
(null)
provider_responses
0
endpoint_id
"4149ab03-3b69-45a0-b94c-6c253b8641a1"
id
"chatcmpl-RpCApfIiER6jddIcaCyHx7bF"
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-1778416519-ZIjGF9onkiQ00qqB4MVB"
session_id
(null)
api_type
"completions"
id
"gen-1778416519-Vvt7heovpQ5UaTNkrA1j"
upstream_id
"chatcmpl-RpCApfIiER6jddIcaCyHx7bF"
total_cost
0.00010261
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepInfra"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
99.98%
Matches word count
n/a
neededClean
false
words
202
82.86%
Dialogue to Total Word Ratio
Ratio: 3.41%, Deviation: 6.59%
neededClean
false
wordsTotal
205
wordsDialogue
7
91.4198%