NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-10-01KR8YHGNEQ8JHYS0RY35X1T4A
Run Details
Model:
Gemma 4 31B (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
6m 13s
Cost:
$0.004452
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
100.0000%
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 spread a crayon-drawn blueprint across the kitchen table, her expression as grim as a funeral director. "The target is the Lego sets by the cake," she whispered with sharp intensity. Bill scratched his chin, looking confused. "Do we need disguises?" Molly snapped, her voice cracking with impatience. "Obviously. We're going in as clowns." "I can't do the red nose. It makes me sneeze." She glared at him, imagining the glorious chaos of the heist. "Sneeze quietly, Bill. What's the extraction plan?" "We run once the piƱata bursts," he suggested, staring blankly at the wall. "You amateur," she sighed, shaking her head. "I'll release the balloons, and you bag the gifts." Bill looked skeptical, shifting his weight from side to side. "What if there's a guard dog?" "It's a puppy, Bill. Give it a treat." "Will it like me?" he asked, hope gleaming in his eyes. Molly rubbed her temples, wondering why she partnered with this man. "Focus on the toys. We hit at 3:00." "I'm worried about the bouncy castle," Bill admitted, his voice trembling. "What if I get stuck?" "Then you're the distraction," Molly replied, gesturing toward the pile of oversized costumes. "Now put on the giant shoes."
created_at
"2026-05-10T12:42:07.413Z"
5/10/2026, 12:42:07 PM
model
"google/gemma-4-31b-it-20260402"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
259
moderation_latency
(null)
generation_time
372130
tokens_prompt
77
tokens_completion
9173
native_tokens_prompt
82
native_tokens_completion
11687
native_tokens_completion_images
(null)
native_tokens_reasoning
8873
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
0.00445172
router
(null)
provider_responses
0
endpoint_id
"29b94af5-d8f8-419a-9cf1-ae1f2831142b"
is_byok
false
latency
89
model_permaslug
"google/gemma-4-31b-it-20260402"
provider_name
"Venice"
status
429
1
endpoint_id
"4149ab03-3b69-45a0-b94c-6c253b8641a1"
id
"chatcmpl-R3erU0J2eHDMTvu6ygYtJdUT"
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-1778416927-mVbCmPUKtFJUXI8kAbF4"
session_id
(null)
api_type
"completions"
id
"gen-1778416927-YUH5A6YJDK75zDOpqkVa"
upstream_id
"chatcmpl-R3erU0J2eHDMTvu6ygYtJdUT"
total_cost
0.00445172
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepInfra"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
200
100.00%
Dialogue to Total Word Ratio
Ratio: 49.75%, Deviation: 0.25%
neededClean
false
wordsTotal
201
wordsDialogue
100
100.0000%