Benchmarks / Which Small AI Model Should You Run on a Mac? We Ran 312 Tests / Rewrite and proofread
rewrite-022
medium toneangry-to-polite
The prompt
user
Rewrite the message below so it is calm and polite, while staying clear about the problem and what the writer wants. 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. """ This is RIDICULOUS. I ordered a standing desk (order #A-48213) on March 2 and paid $389 for 2-day shipping. It's now March 11 and it STILL hasn't shown up. Your tracking page has said "label created" for a week. I want my $24.99 shipping fee refunded and the desk delivered THIS WEEK or I'm disputing the whole charge with my bank. Absolutely pathetic service. """
What we expected
{
"type": "tone",
"style": "angry-to-polite",
"source": "This is RIDICULOUS. I ordered a standing desk (order #A-48213) on March 2 and paid $389 for 2-day shipping. It's now March 11 and it STILL hasn't shown up. Your tracking page has said \"label created\" for a week. I want my $24.99 shipping fee refunded and the desk delivered THIS WEEK or I'm disputing the whole charge with my bank. Absolutely pathetic service.",
"facts": [
{
"name": "standing desk",
"any": [
"standing desk"
]
},
{
"name": "order A-48213",
"any": [
"a-48213"
]
},
{
"name": "March 2",
"any": [
"march 2"
]
},
{
"name": "$389",
"any": [
"$389"
]
},
{
"name": "2-day shipping",
"any": [
"2-day",
"two-day",
"2 day"
]
},
{
"name": "March 11",
"any": [
"march 11"
]
},
{
"name": "label created",
"any": [
"label created"
]
},
{
"name": "$24.99",
"any": [
"$24.99"
]
},
{
"name": "refund",
"any": [
"refund",
"refunded"
]
},
{
"name": "this week",
"any": [
"this week"
]
}
],
"banned": [
"ridiculous",
"pathetic"
],
"banned_re": [],
"no_caps": true,
"caps_ok": [],
"extra_numbers_ok": [],
"length_ratio": [
0.5,
3
],
"reference": "Hello,\n\nI ordered a standing desk (order #A-48213) on March 2 and paid $389 with 2-day shipping. As of today, March 11, it has not arrived, and the tracking page has shown \"label created\" for a week.\n\nI would appreciate a refund of the $24.99 shipping fee and delivery of the desk this week. If that isn't possible, I may need to dispute the charge with my bank, which I would prefer to avoid.\n\nThank you for your help."
}What each model answered
MiMo-V2.6 Distill 9B
✓ pass · score 92 (scripted checks 100, judges 8.3/10 from 3) · 5.04 s
Subject: Delivery delay for order #A-48213 Hello, I hope you're doing well. I'm writing to follow up on a standing desk I ordered on March 2 under order #A-48213. I paid $389, which included 2-day shipping. As of March 11, the desk still hasn't arrived. The tracking page has shown "label created" for about a week. Could you please look into this? I'd like the $24.99 shipping fee refunded, and I'd like the desk delivered this week. If I don't hear back, I'll need to take the matter further with my bank. Thank you for your help. Best regards, [Your name]
Judge medians: Tone match 10 · Faithfulness 6 · Naturalness 9
Scoring detail
{
"cleaned_words": 101,
"similarity_to_source": 0.4,
"facts_missing": [],
"banned_hits": [],
"new_numbers": [],
"length_ratio": 1.578,
"length_bounds": [
0.5,
3
],
"gate": 1,
"checks": {
"facts": 1,
"banned": 1,
"numbers": 1,
"changed": 1,
"length": 1
}
}Ornith-1.5 9B
✓ pass · score 100 (scripted checks 100, judges 10.0/10 from 3) · 3.63 s
Dear Customer Service, I am writing regarding my order #A-48213 for a standing desk, which I placed on March 2 and paid $389 for 2-day shipping. It is now March 11, and the order still has not arrived. The tracking page has shown a status of "label created" for the past week. Could you please help resolve this? I would like a refund of the $24.99 shipping fee and delivery of the desk this week. If this cannot be arranged, I will need to dispute the entire charge with my bank. Thank you for your attention to this matter.
Judge medians: Tone match 10 · Faithfulness 10 · Naturalness 10
Scoring detail
{
"cleaned_words": 99,
"similarity_to_source": 0.429,
"facts_missing": [],
"banned_hits": [],
"new_numbers": [],
"length_ratio": 1.547,
"length_bounds": [
0.5,
3
],
"gate": 1,
"checks": {
"facts": 1,
"banned": 1,
"numbers": 1,
"changed": 1,
"length": 1
}
}Granite 4.2 8B
✓ pass · score 87 (scripted checks 100, judges 7.3/10 from 3) · 2.87 s
Hello, I placed an order for a standing desk (order #A-48213) on March 2 and paid $389 for 2‑day shipping. It is now March 11, and the desk has not yet arrived. The tracking page has shown “label created” for about a week. Could you please either deliver the desk this week or refund the $24.99 shipping fee? I would appreciate your assistance with this matter. Thank you for your help.
Judge medians: Tone match 9 · Faithfulness 3 · Naturalness 10
Scoring detail
{
"cleaned_words": 71,
"similarity_to_source": 0.489,
"facts_missing": [],
"banned_hits": [],
"new_numbers": [],
"length_ratio": 1.109,
"length_bounds": [
0.5,
3
],
"gate": 1,
"checks": {
"facts": 1,
"banned": 1,
"numbers": 1,
"changed": 1,
"length": 1
}
}Spark-X2.5 4B
✓ pass · score 100 (scripted checks 100, judges 10.0/10 from 3) · 2.23 s
I am writing to express my concern regarding my recent order. I placed a standing desk order (order #A-48213) on March 2 and paid $389 with 2-day shipping. As of March 11, the desk has not yet arrived, and the tracking page has indicated "label created" for a week. I would like to request a refund for the $24.99 shipping fee and have the desk delivered this week. If this issue is not resolved, I will need to dispute the entire charge with my bank.
Judge medians: Tone match 10 · Faithfulness 10 · Naturalness 10
Scoring detail
{
"cleaned_words": 85,
"similarity_to_source": 0.51,
"facts_missing": [],
"banned_hits": [],
"new_numbers": [],
"length_ratio": 1.328,
"length_bounds": [
0.5,
3
],
"gate": 1,
"checks": {
"facts": 1,
"banned": 1,
"numbers": 1,
"changed": 1,
"length": 1
}
}Mellum2.1 12B-A2.5B
✗ fail · score 73 (scripted checks 80, judges 6.5/10 from 2) · 1.33 s
This is ridiculous. I ordered a standing desk (order #A-48213) on March 2 and paid $389 for 2‑day shipping. It is now March 11 and it still has not arrived. Your tracking page has shown “label created” for a week. I want my $24.99 shipping fee refunded and the desk delivered this week, or I will dispute the whole charge with my bank. Your service is pathetic.
Judge medians: Tone match 0.5 · Faithfulness 10 · Naturalness 9
Scoring detail
{
"cleaned_words": 67,
"similarity_to_source": 0.809,
"facts_missing": [],
"banned_hits": [
"ridiculous",
"pathetic"
],
"new_numbers": [],
"length_ratio": 1.047,
"length_bounds": [
0.5,
3
],
"gate": 1,
"checks": {
"facts": 1,
"banned": 0,
"numbers": 1,
"changed": 1,
"length": 1
}
}Ling-3.0-tiny (7.9B-A1.3B)
✓ pass · score 95 (scripted checks 100, judges 9.0/10 from 3) · 1.03 s
I am writing to express my concern regarding order #A-48213, placed on March 2 for a standing desk, which I paid $389 for with 2-day shipping. As of March 11, the desk has still not arrived, and the tracking page shows "label created" for a week. I would like my $24.99 shipping fee refunded and the desk delivered this week. If this is not resolved, I will be disputing the charge with my bank.
Judge medians: Tone match 9 · Faithfulness 10 · Naturalness 8
Scoring detail
{
"cleaned_words": 74,
"similarity_to_source": 0.507,
"facts_missing": [],
"banned_hits": [],
"new_numbers": [],
"length_ratio": 1.156,
"length_bounds": [
0.5,
3
],
"gate": 1,
"checks": {
"facts": 1,
"banned": 1,
"numbers": 1,
"changed": 1,
"length": 1
}
}MiniCPM5 2B
✓ pass · score 92 (scripted checks 100, judges 8.3/10 from 3) · 1.62 s
I am writing to let you know that my standing desk, ordered under reference #A-48213 on March 2, was paid for at $389 with 2-day shipping. As of March 11, the desk has not yet arrived, and my tracking page still shows "label created." I would like to request a refund of the $24.99 shipping fee and the delivery of the desk this week. If this is not provided, I may need to dispute the charge with my bank. I appreciate your attention to this matter.
Judge medians: Tone match 10 · Faithfulness 7 · Naturalness 8
Scoring detail
{
"cleaned_words": 86,
"similarity_to_source": 0.347,
"facts_missing": [],
"banned_hits": [],
"new_numbers": [],
"length_ratio": 1.344,
"length_bounds": [
0.5,
3
],
"gate": 1,
"checks": {
"facts": 1,
"banned": 1,
"numbers": 1,
"changed": 1,
"length": 1
}
}K2-Horizon 0.9B
✗ fail · score 49 (scripted checks 35, judges 6.3/10 from 3) · 0.51 s
This is RIDICULOUS. I ordered a standing desk (order #A-48213) on March 2 and paid $389 for 2-day shipping. It's now March 11 and it STILL hasn't shown up. Your tracking page has said "label created" for a week. I want my $24.99 shipping fee refunded and the desk delivered THIS WEEK or I'm disputing the whole charge with my bank.
Judge medians: Tone match 1 · Faithfulness 10 · Naturalness 8
Scoring detail
{
"cleaned_words": 61,
"similarity_to_source": 0.976,
"facts_missing": [],
"banned_hits": [
"ridiculous",
"ALLCAPS:RIDICULOUS,STILL,THIS,WEEK"
],
"new_numbers": [],
"length_ratio": 0.953,
"length_bounds": [
0.5,
3
],
"gate": 0.5,
"checks": {
"facts": 1,
"banned": 0,
"numbers": 1,
"changed": 0,
"length": 1
}
}