resyn

Compare runs

Pick two or more runs to compare. Qwen3.5-0.8B-Autocomplete on an unnamed computer is the first; add another below.

Runs of the same model, or on the same computer, the newest first.

RunQwen3.5-0.8B-AutocompleteNo computer named · Ollama v262Take out
Score—No score
Tasks passed13 of 44
Points13 of 64
Speed309 tok/s
Tokens33,077
Summarizing1/5
One-sentence summary191 tok/s
Meeting notes in three bullets279 tok/s
Review sentiment and complaint317 tok/s
Faithful summary of a study275 tok/s
Action items from an email thread260 tok/s
Extracting3/5
Fields from an email as JSON321 tok/s
Every email address, once
A list as CSV319 tok/s
The real deadline314 tok/s
Warnings and errors from a log327 tok/s
Following instructions3/5
Exactly one word145 tok/s
Three lowercase lines228 tok/s
Exact JSON shape236 tok/s
Sort a list317 tok/s
A name with three rules221 tok/s
Reasoning0/5
Unit price
Days of the week
Who owns the cat
Arrival time
Filling a tank
Reading code1/4
What does it print
Trace a loop
Find the bug284 tok/s
Run a query in your head
Using tools5/5
Call one tool308 tok/s
Don't call a tool when none is needed323 tok/s
Two calls for two answers318 tok/s
Chain two tools309 tok/s
Handle a failed call honestly304 tok/s
Building pages0/5
A small website311 tok/s
A pricing table with a toggle311 tok/s
An accessible sign-up form301 tok/s
A to-do app that remembers307 tok/s
A bar chart in SVG
Building games0/2
Build 2048
Build Snake
Writing code0/3
Merge intervals
An LRU cache
Evaluate arithmetic
Fixing code0/2
Fix the bookings module
Fix the CSV reader
Planning and data0/3
A query over hidden data
Schedule five meetings
A replacement in ten calls or fewer

A check marks the best of each row. tok/s is tokens a second: how fast the model writes. How the score works.