NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-25-01KMJ8GRZCFTC4MERQFMHN7E44
Run Details
Model:
Qwen3 235B A22B Instruct 2507
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
4.8s
Cost:
$0.000044
Provider:
WandB
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
0.0000%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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
Moonlight glinted off Bill’s round spectacles as he crouched behind a plastic fire hydrant-shaped lawn ornament. Molly adjusted her cat burglar mask, which suspiciously resembled a poorly drawn raccoon. Around them, streamers flapped like surrender flags in the breeze and a deflating clown balloon bobbed in slow despair. The target: Chuckles the Clown’s Ultimate Birthday Barn, where thirty sugar-addled children had just surrendered their gifts to a mountain of poorly wrapped chaos near the ball pit. Bill unrolled a blueprint sketched on the back of a pizza coupon. “Thermal scans confirm maximum glitter concentration near cake table,” he whispered, tapping a point with a retractable laser pen that also dispensed breath mints. Molly squinted. “You brought a glitter detector?” “Standard issue since the Kindergarten Jewel Heist of ’22. Never again,” he shuddered. “Now, we breach at 7:48, during the piñata ritual. Chaos is our co-conspirator.” They synchronized their watches—one adorned with cartoon dinosaurs, the other with glow-in-the-dark dinosaurs. Molly tested the lock on the side door, which opened with a cheerful “Yippee!” and a flashing light. “Security’s weak. But the real danger is the bounce house. It’s a trap.” Bill nodded solemnly. “Last thief who entered emerged wearing a tutu and emotionally fulfilled.” At 7:47, they slipped inside, gloved hands ready, hearts steady—until the automated voice shouted, “WELCOME TO CHUCKLES! PLEASE ENJOY FREE MINI CUPCAKES!” “Distract me not with carbs,” Molly hissed. “I’m trying!” Bill whispered back. Mission: Present Purge had begun.
created_at
"2026-03-25T10:26:51.504Z"
3/25/2026, 10:26:51 AM
model
"qwen/qwen3-235b-a22b-07-25"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
76
moderation_latency
(null)
generation_time
4788
tokens_prompt
77
tokens_completion
438
native_tokens_prompt
72
native_tokens_completion
372
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)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
usage
0.0000444
router
(null)
provider_responses
0
endpoint_id
"c9f927db-d559-49eb-9846-80862c5e3b4e"
id
"chatcmpl-91020f0dc59dcc5f"
is_byok
false
latency
41
model_permaslug
"qwen/qwen3-235b-a22b-07-25"
provider_name
"WandB"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.0; linux; x64))"
http_referer
(null)
api_type
"completions"
id
"gen-1774434411-579yLZuDpva040yCODsv"
upstream_id
"chatcmpl-91020f0dc59dcc5f"
total_cost
0.0000444
cache_discount
(null)
upstream_inference_cost
0
provider_name
"WandB"
Evaluation details
Result
Evaluator
Details
Meta Data
0.00%
Matches word count
n/a
neededClean
false
words
244
0.00%
Dialogue to Total Word Ratio
Ratio: 31.33%, Deviation: 21.33%
neededClean
false
wordsTotal
249
wordsDialogue
78
0.0000%