NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-10-01KR8YXHD1JRGZ0PH5QVA5GEMR
Run Details
Model:
Gemma 4 31B (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
2m 8s
Cost:
$0.001260
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
81.27%
Matches word count
(details)
80.32%
Dialogue to Total Word Ratio
(details)
80.7961%
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, target is the living room," Molly said. "Why is there a bouncy castle in the driveway?" Bill asked. "Diversion. We enter through the kitchen, dodge the juice boxes, and hit the gift table." "Do I really have to wear the costume?" "Yes, the giant penguin. It blends in with the Arctic Adventure theme." "I can't breathe in this thing. It smells like old fish." "Suffer for the art, Bill. We grab the LEGO sets first, then the iPads." "What about the toddlers? They're vicious. I saw one bite a golden retriever yesterday." "We use the bubble machine. It's their only known weakness." "And the cake? Is the cake part of the haul?" "Focus, Bill! We're here for the high-value loot, not the frosting." "But it's a triple-chocolate fudge with sprinkles and a cherry on top." "If you touch that cake, I'm locking you in the bouncy castle until morning." "That's a low blow. Fine. Penguin mode engaged." "Now, check your watch. The piƱata drops in five minutes. That's our window," Molly whispered. "Wait, do I get a slice of cake after we escape?" "Move it, Bill!"
created_at
"2026-05-10T12:48:41.386Z"
5/10/2026, 12:48:41 PM
model
"google/gemma-4-31b-it-20260402"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
288
moderation_latency
(null)
generation_time
128163
tokens_prompt
77
tokens_completion
3025
native_tokens_prompt
82
native_tokens_completion
3289
native_tokens_completion_images
(null)
native_tokens_reasoning
2744
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
0.00126048
router
(null)
provider_responses
0
endpoint_id
"4149ab03-3b69-45a0-b94c-6c253b8641a1"
id
"chatcmpl-RszREuef3fVpINafXcjbslLL"
is_byok
false
latency
65
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-1778417321-6r5tGKcdejDmeyMBp1VR"
session_id
(null)
api_type
"completions"
id
"gen-1778417321-Dl65qPT702AqBfqyoeHK"
upstream_id
"chatcmpl-RszREuef3fVpINafXcjbslLL"
total_cost
0.00126048
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepInfra"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
81.27%
Matches word count
n/a
neededClean
false
words
188
80.32%
Dialogue to Total Word Ratio
Ratio: 96.84%, Deviation: 6.84%
neededClean
false
wordsTotal
190
wordsDialogue
184
80.7961%