NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-10-01KR93MXEF953420DTXT69WCMZ
Run Details
Model:
Gemma 4 31B
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
2m 12s
Cost:
$0.000121
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
0.08%
Matches word count
(details)
91.99%
Dialogue to Total Word Ratio
(details)
46.0364%
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
"The target is a six-year-old's birthday bash," Molly whispered. "A children's party? Really?" Bill asked. "High volume, low security, and the loot is concentrated in one pile," she replied. "What's the cover?" "We're the 'Entertainment Duo.' I'm a bubble artist, you're a balloon animal specialist." Bill sighed. "I can't do balloons, Molly." "Learn. Or you're the clown." "I'm not wearing a wig." "Wig, oversized shoes, the whole bit. It's the perfect camouflage." "Camouflage for what? Being a target for sticky fingers?" "Exactly. While the kids are distracted by a giant bubble, we swoop the gift table." "What about the parents?" "They'll be nursing cocktails and ignoring everything. It's a goldmine." "And the getaway?" "The bouncy castle is the exit point. We jump out the back, slide down the inflatable ramp, and vanish into the shrubs." "Is this legal?" "Bill, we're stealing Lego sets from first graders. Legal is the last thing on my mind." "Fine. But I'm not making a poodle." "You're making a poodle, Bill. Now get your nose red."
created_at
"2026-05-10T14:13:21.695Z"
5/10/2026, 2:13:21 PM
model
"google/gemma-4-31b-it-20260402"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
144
moderation_latency
(null)
generation_time
12194
tokens_prompt
77
tokens_completion
293
native_tokens_prompt
79
native_tokens_completion
292
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
0.00012123
router
(null)
provider_responses
0
endpoint_id
"4149ab03-3b69-45a0-b94c-6c253b8641a1"
id
"chatcmpl-RVZTEyWYhREJSvr64O4bhGgQ"
is_byok
false
latency
58
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-1778422401-hSuNImaypKnCWCZUTWn7"
session_id
(null)
api_type
"completions"
id
"gen-1778422401-JJSnxAL8onbiuEVCM5Qp"
upstream_id
"chatcmpl-RVZTEyWYhREJSvr64O4bhGgQ"
total_cost
0.00012123
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepInfra"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
0.08%
Matches word count
n/a
neededClean
false
words
171
91.99%
Dialogue to Total Word Ratio
Ratio: 95.38%, Deviation: 5.38%
neededClean
false
wordsTotal
173
wordsDialogue
165
46.0364%