Unified MemoryBenchmarks / Which Small AI Model Should You Run on a Mac? We Ran 312 Tests / Sort and triage
triage-047
medium review
The prompt
user
TASK: REVIEW
Product: Nomad Leakproof Travel Mug
Rating: 4/5 stars
Title: I wanted to hate this
Review: I'm a total skeptic of "leakproof" anything and fully expected to write an angry review. Nope. I've thrown it in my laptop bag upside down every day for a month and not a single drop. Coffee is still hot at lunch. I stand corrected.
Reply with only a JSON object: {"label": "<positive|negative|mixed>"}What we expected
{
"label": "positive"
}What each model answered
MiMo-V2.6 Distill 9B
✓ pass · score 100 · 0.55 s
{"label": "positive"}Scoring detail
{
"label": {
"got": "positive",
"expected": "positive",
"correct": true
}
}Ornith-1.5 9B
✓ pass · score 100 · 0.49 s
{"label": "positive"}Scoring detail
{
"label": {
"got": "positive",
"expected": "positive",
"correct": true
}
}Granite 4.2 8B
✓ pass · score 100 · 0.56 s
{"label": "positive"}Scoring detail
{
"label": {
"got": "positive",
"expected": "positive",
"correct": true
}
}Spark-X2.5 4B
✓ pass · score 100 · 0.32 s
{"label": "positive"}Scoring detail
{
"label": {
"got": "positive",
"expected": "positive",
"correct": true
}
}Mellum2.1 12B-A2.5B
✓ pass · score 100 · 0.23 s
{"label": "positive"}Scoring detail
{
"label": {
"got": "positive",
"expected": "positive",
"correct": true
}
}Ling-3.0-tiny (7.9B-A1.3B)
✓ pass · score 100 · 0.18 s
{"label": "positive"}Scoring detail
{
"label": {
"got": "positive",
"expected": "positive",
"correct": true
}
}MiniCPM5 2B
✓ pass · score 100 · 0.28 s
{"label": "positive"}Scoring detail
{
"label": {
"got": "positive",
"expected": "positive",
"correct": true
}
}K2-Horizon 0.9B
✗ fail · score 0 · 0.11 s
{"label": "negative"}Scoring detail
{
"label": {
"got": "negative",
"expected": "positive",
"correct": false
}
}