Model vs model

phi-3-mini-128k-instruct vs acm_rewrite_qwen2-72B-Chat

A debate-ready pair page: current winner, strongest alternative, decisive benchmarks, and the warning that should travel with the claim.

Use case · Everyday chatbot
Winner · phi-3-mini-128k-instruct
Sources · All public sources

phi-3-mini-128k-instruct leads this compare set for everyday chatbot.

Thin verified coverage0 shared benchmarks are still too close to call, so the win stays conditional. This compare uses all public sources, with provider-official evidence labeled separately.

Left casephi-3-mini-128k-instruct wins 0 visible benchmarks · Reasoning / math / science · Coding

Right caseacm_rewrite_qwen2-72B-Chat wins 0 visible benchmarks · Chat / text · Coding

Warning to share0 shared benchmarks are still too close to call, so the win stays conditional. This compare uses all public sources, with provider-official evidence labeled separately.

Close calls0 shared benchmarks are still too close to call.

phi-3-mini-128k-instruct case

Reasoning / math / science
Coding

acm_rewrite_qwen2-72B-Chat case

Chat / text
Coding

What changes the outcome

phi-3-mini-128k-instruct: 33 visible benchmark gaps still leave room for the result to move.
acm_rewrite_qwen2-72B-Chat: 34 visible benchmark gaps still leave room for the result to move.

Why this result is surprising

The visible shared evidence is more decisive than usual for this compare set.
Very few shared benchmarks are decisively separating these models.

Why this is not a clean win

0 shared benchmarks are still too close to call, so the win stays conditional. This compare uses all public sources, with provider-official evidence labeled separately.
acm_rewrite_qwen2-72B-Chat remains the strongest alternative once you change use case, mode, or missing-evidence assumptions.

Open full compare workspace Open evidence page Open disagreement page

Advanced framings and X composerNeutral, contrarian, open-model, and skeptical variants

Neutral analystLead with the claim, then attach the reason and warning.phi-3-mini-128k-instruct leads this compare set for everyday chatbot.

ContrarianPush against the easy read and keep the strongest alternative live.Contrarian take: phi-3-mini-128k-instruct leads this compare set for everyday chatbot.

Open-model angleBias the framing toward the open-weight or transparent-evidence angle.Open-model angle: Model compare · phi-3-mini-128k-instruct vs acm_rewrite_qwen2-72B-Chat

Don't trust the headlineLead with the warning before you let the claim travel.Don't trust the headline: Model compare · phi-3-mini-128k-instruct vs acm_rewrite_qwen2-72B-Chat

Decisive benchmarks

6 of 40 benchmarks


Coding LB · % Code · Coding	12.7%n/a	39.1%n/a	n/a
Reasoning LB · % Text · Reasoning / math / science	24.2%n/a	42%n/a	n/a
Language LB · % Text · Chat / text	8.5%n/a	30%n/a	n/a
Instruction following LB · % Text · Chat / text	47.8%n/a	77.7%n/a	n/a
Coding generation LB · % Code · Coding	19.4%n/a	36%n/a	n/a
Coding completion LB · % Code · Coding	6%n/a	42.1%n/a	n/a

Coding

LB · %

Code · Coding

12.7%n/a

39.1%n/a

n/a

Reasoning

LB · %

Text · Reasoning / math / science

24.2%n/a

42%n/a

n/a

Language

LB · %

Text · Chat / text

8.5%n/a

30%n/a

n/a

Instruction following

LB · %

Text · Chat / text

47.8%n/a

77.7%n/a

n/a

Coding generation

LB · %

Code · Coding

19.4%n/a

36%n/a

n/a

Coding completion

LB · %

Code · Coding

6%n/a

42.1%n/a

n/a

phi-3-mini-128k-instruct vs acm_rewrite_qwen2-72B-Chat

phi-3-mini-128k-instruct leads this compare set for everyday chatbot.

phi-3-mini-128k-instruct case

acm_rewrite_qwen2-72B-Chat case

What changes the outcome

Why this result is surprising

Why this is not a clean win

Post the claim with the evidence attached.

Open or copy the stable surfaces

Use the exact public framing

Pick the voice before you post

Compose a post that keeps the warning attached

Decisive benchmarks

Loading model comparison.

phi-3-mini-128k-instruct vs acm_rewrite_qwen2-72B-Chat

phi-3-mini-128k-instruct leads this compare set for everyday chatbot.

phi-3-mini-128k-instruct case

acm_rewrite_qwen2-72B-Chat case

What changes the outcome

Why this result is surprising

Why this is not a clean win

Post the claim with the evidence attached.

Open or copy the stable surfaces

Use the exact public framing

Pick the voice before you post

Compose a post that keeps the warning attached

Decisive benchmarks