NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-10-01KR90K62BZGMDW779M3E6SEDF
Run Details
Model:
Gemma 4 31B
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
16.5s
Cost:
$0.000076
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
60.65%
Matches word count
(details)
Model input
User/Human
Please write the opening scene of a murder mystery where each sentence has exactly 20 words. Please make sure that each sentence has the same length. Only return the opening itself.
Model response
Messages
Meta
AI
The rain drummed a rhythmic beat against the cold glass while Arthur sat alone in his vast, silent library. A single candle flickered on the mahogany desk, casting long, dancing shadows across the walls of the old room. He held a glass of amber scotch, staring at the sealed letter that had arrived by courier this morning. The wax seal was a deep crimson, bearing a crest that had not been seen for twenty long years. Suddenly, the heavy oak door creaked open, revealing a figure draped in a cloak of midnight black and grey. The stranger stepped forward into the light, holding a silver dagger that dripped with a thick, dark red fluid. Arthur gasped as the blade sank deep into his chest, silencing his final scream before he hit the floor. The killer leaned down to whisper a secret that would haunt the surviving family for many long, bitter decades.
created_at
"2026-05-10T13:17:59.25Z"
5/10/2026, 1:17:59 PM
model
"google/gemma-4-31b-it-20260402"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
347
moderation_latency
(null)
generation_time
6003
tokens_prompt
46
tokens_completion
219
native_tokens_prompt
50
native_tokens_completion
183
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
0.00007604
router
(null)
provider_responses
0
endpoint_id
"69279254-6a96-4e9d-abc6-ea76e6bf8e97"
is_byok
false
latency
10046
model_permaslug
"google/gemma-4-31b-it-20260402"
provider_name
"Novita"
status
504
1
endpoint_id
"4149ab03-3b69-45a0-b94c-6c253b8641a1"
id
"chatcmpl-RE2cYx0QjbVwKChVh9E66NZU"
is_byok
false
latency
63
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-1778419079-7h7NK3lfZguV6PK1qwDe"
session_id
(null)
api_type
"completions"
id
"gen-1778419079-Yd4Q0GKlmIZrhfZSPFWy"
upstream_id
"chatcmpl-RE2cYx0QjbVwKChVh9E66NZU"
total_cost
0.00007604
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepInfra"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
60.65%
Matches word count
n/a
neededClean
false
sentences
8
wordCounts
0
19
1
19
2
19
3
19
4
19
5
19
6
19
7
19