NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1KCXWEG8BRXCSY0RY9P6RD9
Run Details
Model:
DeepSeek V4 Flash 0731 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
21.4s
Cost:
$0.000090
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
60.65%
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
“You’re sure it was a scone?” Mabel slid a tray of golden croissants onto the cooling rack, her flour-dusted apron cinched tight. “Not just any scone. The one with the lavender glaze. I’d recognize it anywhere.” Nora tapped the glass case, leaving a faint fingerprint. “She bought two every Tuesday. Regular as clockwork.” “And you think that’s what did her in?” “I think someone swapped the lavender for something else. Hemlock’s got a bitter taste, but you’d never notice under all that sugar.” Mabel paused, wiping her hands on a dish towel. “Who would want to poison old Mrs. Pendleton? She gave free bread to the church.” “She also knew about the missing funds from the historical society. And she told me she’d found a receipt—in the bakery’s own trash.” “Our trash?” “Behind the shop. Someone here’s been baking more than sourdough.” A bell jingled as the door opened. Both women looked up, then back at each other. Mabel’s smile tightened. “Well,”
she said
, reaching for a pastry box, “we’d better make sure our next customer gets exactly what they ordered.”
created_at
"2026-09-03T10:27:13.505Z"
9/3/2026, 10:27:13 AM
model
"deepseek/deepseek-v4-flash-20260731"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
461
moderation_latency
(null)
generation_time
21383
tokens_prompt
78
tokens_completion
493
native_tokens_prompt
144
native_tokens_completion
434
native_tokens_completion_images
(null)
native_tokens_reasoning
169
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
0.00008964
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788431233-S0pfh0FS4SzV9pceaxam"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788431233-cIxguYSzP2tOyvnJzYwn"
upstream_id
"chatcmpl-REM4xDbs63ttF1mlgLFSev21"
provider_responses
0
endpoint_id
"c1980fff-0a72-4bce-8d62-a7d3fc582200"
id
"chatcmpl-REM4xDbs63ttF1mlgLFSev21"
is_byok
false
latency
65
model_permaslug
"deepseek/deepseek-v4-flash-20260731"
provider_name
"DeepInfra"
status
200
total_cost
0.00008964
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepInfra"
response_cache_source_id
(null)
data_region
"global"
workspace_id
"97e315e5-d303-487d-83c1-83180e8a13d4"
Evaluation details
Result
Evaluator
Details
Meta Data
60.65%
Count dialogue tags
n/a
neededClean
false
dialogueTags
0
"she said"