Compare runs

Pick two or more runs to compare. Hermes-3-Llama-3.2 on an unnamed computer is the first; add another below.

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

The runs side by side: score, tasks passed, speed, tokens generated, each category and each task
RunHermes-3-Llama-3.2No computer named · Ollama v262Take out Hermes-3-Llama-3.2
Score—No score
Tasks passed13 of 44
Points13 of 64
Speed109 tok/s
Tokens4,937
Summarizing2/5
One-sentence summaryPassed103 tok/s
Meeting notes in three bulletsFailed109 tok/s
Review sentiment and complaintPassed107 tok/s
Faithful summary of a studyFailed110 tok/s
Action items from an email threadFailed110 tok/s
Extracting3/5
Fields from an email as JSONPassed110 tok/s
Every email address, onceNot run
A list as CSVFailed108 tok/s
The real deadlinePassed112 tok/s
Warnings and errors from a logPassed111 tok/s
Following instructions3/5
Exactly one wordPassed111 tok/s
Three lowercase linesFailed109 tok/s
Exact JSON shapePassed109 tok/s
Sort a listPassed108 tok/s
A name with three rulesFailed109 tok/s
Reasoning0/5
Unit priceNot run
Days of the weekNot run
Who owns the catNot run
Arrival timeNot run
Filling a tankNot run
Reading code0/4
What does it printNot run
Trace a loopNot run
Find the bugFailed108 tok/s
Run a query in your headNot run
Using tools1/5
Call one toolFailed110 tok/s
Don't call a tool when none is neededPassed110 tok/s
Two calls for two answersFailed108 tok/s
Chain two toolsFailed110 tok/s
Handle a failed call honestlyFailed109 tok/s
Building pages4/5
A small websitePassed109 tok/s
A pricing table with a togglePassed109 tok/s
An accessible sign-up formPassed108 tok/s
A to-do app that remembersPassed109 tok/s
A bar chart in SVGNot run
Building games0/2
Build 2048Not run
Build SnakeNot run
Writing code0/3
Merge intervalsNot run
An LRU cacheNot run
Evaluate arithmeticNot run
Fixing code0/2
Fix the bookings moduleNot run
Fix the CSV readerNot run
Planning and data0/3
A query over hidden dataNot run
Schedule five meetingsNot run
A replacement in ten calls or fewerNot run

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