Model

MoonshotAI: Kimi K2.5

Test

Dialogue tags

Scenario

Write 200 words with 90% dialogue

Run ID

2026-02-08-01KGZ07E64YXABNCA77HPJC349

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

AI
"You're joking," Bill said, adjusting his ski mask in the rearview mirror. "Do I look like I'm joking?" Molly snapped, unfolding a crayon-drawn map across the steering wheel. "The loot's in the living room, guarded by a sleeping dragon—sorry, golden retriever named Muffins." "We're really doing a bouncy castle heist?" "Black ops, Bill. We rappel through the side window while they play musical chairs. The target: forty-seven wrapped packages containing Lego Death Stars, Nintendo Switches, and three life-sized stuffed unicorns." "What about the parents?" "Distracted by the magician. I've got intel that he pulls a rabbit from a hat at exactly 3 PM. That's our fifteen-minute window." "Why not just grab the cake and run?" "Because, genius, the presents are worth eight grand. The birthday boy's dad runs a crypto scam. We're redistributing wealth." "To our bank accounts." "Obviously. Now strap on the utility belt. And remember—if anyone under four feet tall spots us, we're 'balloon safety inspectors.'" "What if they cry?" "Then you do the chicken dance. Distracts them every time. It's in the handbook, page twelve, right between 'lock-picking' and 'advanced cupcake theft.'" "I didn't get a handbook." "You slept through orientation. Again."
created_at"2026-02-08T16:09:50.696512+00:00" Sunday, February 8th, 2026 at 4:09:50 PM GMT+00:00
model"moonshotai/kimi-k2.5-0127" 
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency779
moderation_latency(null)
generation_time32566
tokens_prompt61
tokens_completion1565
native_tokens_prompt68
native_tokens_completion1565
native_tokens_completion_images(null)
native_tokens_reasoning1449
native_tokens_cached68
num_media_prompt(null)
num_input_audio_prompt(null)
num_media_completion0
num_search_results(null)
origin"https://ncbench.com/" 
is_byokfalse
finish_reason"stop" 
native_finish_reason"stop" 
usage0.0047018
router(null)
provider_responses
0
id"chatcmpl-6988b52d409d90d3b0774e0f" 
status200
is_byokfalse
latency779
endpoint_id"49762299-66fd-4514-b0ee-c9e11e231e3b" 
provider_name"Moonshot AI" 
model_permaslug"moonshotai/kimi-k2.5-0127" 
api_type"completions" 
id"gen-1770566957-YsFKm4LaX8J57q3xLlmk" 
upstream_id"chatcmpl-6988b52d409d90d3b0774e0f" 
total_cost0.0047018
cache_discount0.000034
upstream_inference_cost0
provider_name"Moonshot AI" 

Evaluation details

Result Evaluator Details Meta Data
99.9840% Matches word count n/a
neededCleanfalse
words202
99.9998% Dialogue to Total Word Ratio
Ratio: 89.60%, Deviation: 0.40%
neededCleanfalse
wordsTotal202
wordsDialogue181
99.9919%