NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-06-01-01KT1G0EKBXHS7KQAD5SM0ZW69
Run Details
Model:
MiniMax M3
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
31.8s
Cost:
$0.000767
Provider:
Minimax
Evaluation summary
Score
Evaluator
Details Link
100.00%
Count dialogue tags
(details)
Model input
User/Human
You are an expert novel writer in the cozy mystery genre. Write a scene of about 200 words, with dialogue between two characters. The dialogue should be unattributed, meaning the speaker is not explicitly mentioned. The scene should be set in a small town bakery. Only return the story, nothing else.
Model response
Messages
Meta
AI
The smell of cinnamon and yeast hung in the air, warm and familiar, a comforting backdrop to the unease settling between them. Morning sunlight slanted through the front window, catching flour dust motes drifting above the display case. "You're sure you saw her take it?" "I didn't say take. I said pocket. There's a difference." "A difference that matters to the police, perhaps." "It should matter to you. She was standing right here, ordering a dozen lemon bars while that brooch sat in the velvet case the whole time." "And you think I didn't notice?" "I think you noticed everything. That's why your hands are shaking." A pause. The old clock behind the register ticked softly. Outside, Mrs. Hadley's terrier barked at a passing bicycle. "She said she was collecting for the church restoration fund." "She did." "And you believed her?" "I believe everyone until they give me reason not to. It's served me well enough for forty years of baking." "Until today." The bell above the door chimed softly. Both fell quiet, watching the woman from the hardware store step inside, her eyes darting toward the case beneath the counter.
created_at
"2026-06-01T11:44:50.955Z"
6/1/2026, 11:44:50 AM
model
"minimax/minimax-m3-20260531"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1378
moderation_latency
(null)
generation_time
31599
tokens_prompt
81
tokens_completion
780
native_tokens_prompt
237
native_tokens_completion
603
native_tokens_completion_images
(null)
native_tokens_reasoning
474
native_tokens_cached
114
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
0.00076734
router
(null)
provider_responses
0
endpoint_id
"6851b352-a7e2-45ad-a69e-67ed1208a416"
id
"066ca3b32494f4f99d32c2dc09f3ad0c"
is_byok
false
latency
1378
model_permaslug
"minimax/minimax-m3-20260531"
provider_name
"Minimax"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.16.0; linux; x64))"
http_referer
(null)
request_id
"req-1780314291-zp8oV9dRKXxZMHUV4at4"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1780314291-lK3rJOPmVrK8wuwYI8qt"
upstream_id
"066ca3b32494f4f99d32c2dc09f3ad0c"
total_cost
0.00076734
cache_discount
0.00005472
upstream_inference_cost
0
provider_name
"Minimax"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Count dialogue tags
n/a
neededClean
false
dialogueTags
(empty)