NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-10-01KR8ZGVPYPBGQ8QP8WNM3G18Q
Run Details
Model:
Gemma 4 26B (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
1m 37s
Cost:
$0.002999
Provider:
Cloudflare
Evaluation summary
Score
Evaluator
Details Link
99.92%
Matches word count
(details)
99.90%
Dialogue to Total Word Ratio
(details)
99.9117%
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 the crumpled, coffee-stained blueprint across the heavy wooden table, her eyes narrowing at the colorful, chaotic layout of the suburban living room. "The target is the Miller residence. Specifically, the playroom during the cake cutting." Bill polished his thick goggles with a frantic, nervous twitch that made his hands shake. "A high-stakes environment. What's the obstacle?" Molly tapped a jagged red circle on the map with her pen. "The bouncy castle. It's a tactical nightmare. The vibrations will trigger the sensors." Bill checked his lockpicks with trembling, sweaty hands. "Can we neutralize the toddler?" Molly rolled her eyes at his complete lack of professional discipline. "We aren't neutralizing children, Bill. We are avoiding them. Grab the presents." Bill's voice began to tremble with dread. "What if there's a clown? I can't handle the face paint." Molly slammed her fist hard against the table. "Focus! We enter through the patio. You grab Legos, I'll take cars." "And the stuffed animals?" "No! They're too soft for the bag." "But they're adorable." Molly glared intensely at him. "They're evidence! Grab the juice boxes so we can blend in." Bill adjusted his dark mask. "I'll wear the party hat."
created_at
"2026-05-10T12:59:14.536Z"
5/10/2026, 12:59:14 PM
model
"google/gemma-4-26b-a4b-it-20260403"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
660
moderation_latency
(null)
generation_time
96440
tokens_prompt
77
tokens_completion
7863
native_tokens_prompt
81
native_tokens_completion
9969
native_tokens_completion_images
(null)
native_tokens_reasoning
7535
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
0.0029988
router
(null)
provider_responses
0
endpoint_id
"e2a16fa6-1f65-413e-9ecb-93901089ddb1"
id
"id-1778417955103"
is_byok
false
latency
576
model_permaslug
"google/gemma-4-26b-a4b-it-20260403"
provider_name
"Cloudflare"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1778417954-Rl5RpbEtA0njiJG8SwCV"
session_id
(null)
api_type
"completions"
id
"gen-1778417954-y3p8HbBwDoxBTiHtA9EE"
upstream_id
"id-1778417955103"
total_cost
0.0029988
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Cloudflare"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
99.92%
Matches word count
n/a
neededClean
false
words
197
99.90%
Dialogue to Total Word Ratio
Ratio: 51.76%, Deviation: 1.76%
neededClean
false
wordsTotal
199
wordsDialogue
103
99.9117%