NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-10-01KR92X7T4M8GQYH432TREYWJQ
Run Details
Model:
Gemma 4 31B (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
2m 48s
Cost:
$0.001363
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
43.38%
Matches word count
(details)
53.20%
Dialogue to Total Word Ratio
(details)
48.2893%
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
"Listen, Bill, the perimeter is soft," Molly whispered. "Soft? It's a bounce house, Molly." "Exactly. High bounce, low security. We enter through the balloon arch." "Won't we pop something? I have a phobia of loud pops." "Stay light on your feet. Once inside, we hit the gift table." "What if the kids see us? They're ruthless." "We'll wear oversized clown shoes. Total camouflage." "Clown shoes? I can't run in those!" "You aren't running, you're sashaying. Now, do you have the distraction?" "The glitter bomb?" "Yes, the glitter bomb. When the cake comes out, you trigger it." "Is that legal?" "We're stealing limited edition Lego sets, Bill. Nothing here is legal." "Fair point. What about the juice boxes? Can we snag some?" "Leave the juice. Focus on the iPads." "I just think a little apple juice wouldn't hurt the operation." "Focus, Bill! On my mark, we breach the play-place." "Do I get a party hat? I feel naked without a hat." "Just shut up and grab the bags." "Fine, but I'm taking a cupcake." "Bill, we are professionals!" "Professionals with low blood sugar!" "Bill!"
created_at
"2026-05-10T13:58:25.868Z"
5/10/2026, 1:58:25 PM
model
"google/gemma-4-31b-it-20260402"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
307
moderation_latency
(null)
generation_time
167840
tokens_prompt
77
tokens_completion
3117
native_tokens_prompt
82
native_tokens_completion
3559
native_tokens_completion_images
(null)
native_tokens_reasoning
2830
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
0.00136308
router
(null)
provider_responses
0
endpoint_id
"4149ab03-3b69-45a0-b94c-6c253b8641a1"
id
"chatcmpl-RfGcxCCU9Na8wGzizYM6ghmQ"
is_byok
false
latency
125
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-1778421505-KqmVSQ6rqdBFZdq6T2Cd"
session_id
(null)
api_type
"completions"
id
"gen-1778421505-FHxvv9j3SBmDrHqXFdy9"
upstream_id
"chatcmpl-RfGcxCCU9Na8wGzizYM6ghmQ"
total_cost
0.00136308
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
183
53.20%
Dialogue to Total Word Ratio
Ratio: 98.91%, Deviation: 8.91%
neededClean
false
wordsTotal
184
wordsDialogue
182
48.2893%