Unified MemoryBenchmarks / Which Small AI Model Should You Run on a Mac? We Ran 312 Tests / Rewrite and proofread
rewrite-019
easy tonecurt-to-warm
The prompt
user
Rewrite the message below so it sounds warm and friendly while keeping the same information. Keep every fact (names, dates, times, amounts, reference numbers) as given, and do not add new facts or numbers. Reply with only the rewritten message, with no preamble or explanation. """ Team offsite moved to Friday the 9th. Same place. Lunch provided. Be there by 9:30. """
What we expected
{
"type": "tone",
"style": "curt-to-warm",
"source": "Team offsite moved to Friday the 9th. Same place. Lunch provided. Be there by 9:30.",
"facts": [
{
"name": "offsite",
"any": [
"offsite",
"off-site"
]
},
{
"name": "Friday",
"any": [
"friday"
]
},
{
"name": "the 9th",
"any": [
"9th",
"ninth"
]
},
{
"name": "same place",
"any": [
"same place",
"same location",
"same venue",
"same spot",
"usual spot",
"usual place",
"usual venue",
"usual location"
]
},
{
"name": "lunch",
"any": [
"lunch"
]
},
{
"name": "9:30",
"any": [
"9:30"
]
}
],
"banned": [],
"banned_re": [],
"no_caps": false,
"caps_ok": [],
"extra_numbers_ok": [],
"length_ratio": [
1.2,
6
],
"reference": "Hi everyone! Quick update: our team offsite has moved to Friday the 9th. We'll be at the same place as before, and lunch will be provided, so come hungry. Please try to arrive by 9:30 so we can get started together. Looking forward to seeing you all there!"
}What each model answered
MiMo-V2.6 Distill 9B
✓ pass · score 92 (scripted checks 100, judges 8.3/10 from 3) · 1.33 s
Hi team, our offsite has moved to Friday the 9th. Same place, lunch provided, and please be there by 9:30.
Judge medians: Tone match 7 · Faithfulness 10 · Naturalness 8
Scoring detail
{
"cleaned_words": 20,
"similarity_to_source": 0.686,
"facts_missing": [],
"new_numbers": [],
"length_ratio": 1.333,
"length_bounds": [
1.2,
6
],
"gate": 1,
"checks": {
"facts": 1,
"numbers": 1,
"changed": 1,
"length": 1
}
}Ornith-1.5 9B
✓ pass · score 98 (scripted checks 100, judges 9.7/10 from 3) · 1.64 s
Hi everyone, We've moved our team offsite to Friday the 9th, and it will be at the same place as before. Lunch will be provided, so please plan to be there by 9:30. Looking forward to seeing you all!
Judge medians: Tone match 10 · Faithfulness 10 · Naturalness 9
Scoring detail
{
"cleaned_words": 39,
"similarity_to_source": 0.407,
"facts_missing": [],
"new_numbers": [],
"length_ratio": 2.6,
"length_bounds": [
1.2,
6
],
"gate": 1,
"checks": {
"facts": 1,
"numbers": 1,
"changed": 1,
"length": 1
}
}Granite 4.2 8B
✓ pass · score 95 (scripted checks 100, judges 9.0/10 from 3) · 1.64 s
Hi everyone, Just a quick note: the team offsite has been moved to Friday the 9th at the same location. We'll have lunch provided, so please plan to arrive by 9:30 a.m. See you there!
Judge medians: Tone match 10 · Faithfulness 8 · Naturalness 9
Scoring detail
{
"cleaned_words": 35,
"similarity_to_source": 0.36,
"facts_missing": [],
"new_numbers": [],
"length_ratio": 2.333,
"length_bounds": [
1.2,
6
],
"gate": 1,
"checks": {
"facts": 1,
"numbers": 1,
"changed": 1,
"length": 1
}
}Spark-X2.5 4B
✓ pass · score 95 (scripted checks 100, judges 9.0/10 from 3) · 0.80 s
We've moved our team offsite to Friday the 9th. It's the same place, and we'll be providing lunch. Please be there by 9:30.
Judge medians: Tone match 7 · Faithfulness 10 · Naturalness 10
Scoring detail
{
"cleaned_words": 23,
"similarity_to_source": 0.579,
"facts_missing": [],
"new_numbers": [],
"length_ratio": 1.533,
"length_bounds": [
1.2,
6
],
"gate": 1,
"checks": {
"facts": 1,
"numbers": 1,
"changed": 1,
"length": 1
}
}Mellum2.1 12B-A2.5B
✓ pass · score 83 (scripted checks 100, judges 6.7/10 from 3) · 0.56 s
Team offsite has been moved to Friday the 9th. The same location will be used, and lunch will be provided. Please arrive by 9:30.
Judge medians: Tone match 3 · Faithfulness 10 · Naturalness 7
Scoring detail
{
"cleaned_words": 24,
"similarity_to_source": 0.615,
"facts_missing": [],
"new_numbers": [],
"length_ratio": 1.6,
"length_bounds": [
1.2,
6
],
"gate": 1,
"checks": {
"facts": 1,
"numbers": 1,
"changed": 1,
"length": 1
}
}Ling-3.0-tiny (7.9B-A1.3B)
✗ fail · score 52 (scripted checks 44, judges 6.0/10 from 3) · 0.34 s
The team offsite has moved to Friday the 9th. Same place. Lunch provided. Please be there by 9:30.
Judge medians: Tone match 2 · Faithfulness 10 · Naturalness 6
Scoring detail
{
"cleaned_words": 18,
"similarity_to_source": 0.909,
"facts_missing": [],
"new_numbers": [],
"length_ratio": 1.2,
"length_bounds": [
1.2,
6
],
"gate": 0.5,
"checks": {
"facts": 1,
"numbers": 1,
"changed": 0,
"length": 1
}
}MiniCPM5 2B
✗ fail · score 34 (scripted checks 19, judges 5.0/10 from 3) · 0.51 s
Team offsite moved to Friday the 9th. Same place. Lunch provided. Be there by 9:30.
Judge medians: Tone match 0 · Faithfulness 10 · Naturalness 5
Scoring detail
{
"cleaned_words": 15,
"similarity_to_source": 1,
"facts_missing": [],
"new_numbers": [],
"length_ratio": 1,
"length_bounds": [
1.2,
6
],
"gate": 0.25,
"checks": {
"facts": 1,
"numbers": 1,
"changed": 0,
"length": 0
}
}K2-Horizon 0.9B
✗ fail · score 36 (scripted checks 19, judges 5.3/10 from 3) · 0.17 s
Team offsite moved to Friday the 9th. Same place. Lunch provided. Be there by 9:30.
Judge medians: Tone match 0 · Faithfulness 10 · Naturalness 6
Scoring detail
{
"cleaned_words": 15,
"similarity_to_source": 1,
"facts_missing": [],
"new_numbers": [],
"length_ratio": 1,
"length_bounds": [
1.2,
6
],
"gate": 0.25,
"checks": {
"facts": 1,
"numbers": 1,
"changed": 0,
"length": 0
}
}