The AI arena is free today

Open Superagent

Phi-3.5-MoE-instruct vs Qwen2.5-Coder 32B Instruct

Phi-3.5-MoE-instruct and Qwen2.5-Coder 32B Instruct are closely matched at 1.9 and 2.0 on the LLM Stats Score.

Microsoft · Alibaba Cloud / Qwen Team · Updated for 2026

Which is better?

Phi-3.5-MoE-instruct and Qwen2.5-Coder 32B Instruct are closely matched on the overall LLM Stats Score at 1.9 and 2.0.

In the 10 individual benchmarks reported for both models, Phi-3.5-MoE-instruct wins 6; this is a narrower head-to-head signal than the composite indexes.

Based on current LLM Stats indexes, shared benchmarks, pricing, and model metadata for 2026.

Choose Phi-3.5-MoE-instruct

  • you value its reported benchmark strengths — it wins 6 of 10 exact shared results

Choose Qwen2.5-Coder 32B Instruct

  • you want the most recent training data — it shipped Sep 2024

At a glance

The differences that matter most.

Core performance indexes
1.9
#317
2.0
#316
1.4
#310
2.0
#306
-3.8
#253
10.0
#165
Cost, coverage & limits
Benchmark wins
6 of 10
4 of 10
Input price
— / M
$0.09 / M
Output price
— / M
$0.09 / M
Context window
128,000

Capability indexes

Additional strengths measured across groups of related public benchmarks

3 shared
Index
Phi-3.5-MoE-instruct
Qwen2.5-Coder 32B Instruct
4.3#284
4.9#277
4.3#176
1.2#190
4.3#165
-0.4#185
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

31 reported for Phi-3.5-MoE-instruct · 15 for Qwen2.5-Coder 32B Instruct

10 shared

Phi-3.5-MoE-instruct outperforms in 6 benchmarks (ARC-C, HellaSwag, MATH, MMLU, TruthfulQA, Winogrande), while Qwen2.5-Coder 32B Instruct is better at 4 benchmarks (GSM8k, HumanEval, MBPP, MMLU-Pro).

Phi-3.5-MoE-instruct has a slight edge in benchmark performance.

Mon Sep 14 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Model Size

Parameter count comparison

28.0B diff

Phi-3.5-MoE-instruct has 28.0B more parameters than Qwen2.5-Coder 32B Instruct, making it 87.5% larger.

Microsoft
Phi-3.5-MoE-instruct
60.0Bparameters
Alibaba Cloud / Qwen Team
Qwen2.5-Coder 32B Instruct
32.0Bparameters
60.0B
Phi-3.5-MoE-instruct
32.0B
Qwen2.5-Coder 32B Instruct

Context Window

Maximum input and output token capacity

Only Qwen2.5-Coder 32B Instruct specifies input context (128,000 tokens). Only Qwen2.5-Coder 32B Instruct specifies output context (128,000 tokens).

Microsoft
Phi-3.5-MoE-instruct
Input- tokens
Output- tokens
Alibaba Cloud / Qwen Team
Qwen2.5-Coder 32B Instruct
Input128,000 tokens
Output128,000 tokens
Mon Sep 14 2026 • llm-stats.com

License

Usage and distribution terms

Phi-3.5-MoE-instruct is licensed under MIT, while Qwen2.5-Coder 32B Instruct uses Apache 2.0.

License differences may affect how you can use these models in commercial or open-source projects.

Phi-3.5-MoE-instruct

MIT

Open weights

Qwen2.5-Coder 32B Instruct

Apache 2.0

Open weights

Release Timeline

When each model was launched

Phi-3.5-MoE-instruct was released on 2024-08-23, while Qwen2.5-Coder 32B Instruct was released on 2024-09-19.

Qwen2.5-Coder 32B Instruct is 1 month newer than Phi-3.5-MoE-instruct.

Phi-3.5-MoE-instruct

Aug 23, 2024

2.1 years ago

Qwen2.5-Coder 32B Instruct

Sep 19, 2024

2.0 years ago

3w newer

Knowledge Cutoff

When training data ends

Neither model specifies a knowledge cutoff date.

Unable to compare the recency of their training data.

No cutoff dates available

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion

Judge for yourself.

Run your own prompts against Phi-3.5-MoE-instruct and Qwen2.5-Coder 32B Instruct side-by-side, then vote on the output you prefer.

Phi-3.5-MoE-instruct
✓ Preferred
Qwen2.5-Coder 32B Instruct
Open in Playground

FAQ

Common questions about Phi-3.5-MoE-instruct vs Qwen2.5-Coder 32B Instruct.

Which is better, Phi-3.5-MoE-instruct or Qwen2.5-Coder 32B Instruct?

Phi-3.5-MoE-instruct and Qwen2.5-Coder 32B Instruct are closely matched on the LLM Stats Score at 1.9 and 2.0. Phi-3.5-MoE-instruct is made by Microsoft and Qwen2.5-Coder 32B Instruct is made by Alibaba Cloud / Qwen Team. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does Phi-3.5-MoE-instruct compare to Qwen2.5-Coder 32B Instruct in benchmarks?

Phi-3.5-MoE-instruct scores ARC-C: 91.0%, OpenBookQA: 89.6%, GSM8k: 88.7%, PIQA: 88.6%, RULER: 87.1%. Qwen2.5-Coder 32B Instruct scores HumanEval: 92.7%, GSM8k: 91.1%, MBPP: 90.2%, HellaSwag: 83.0%, Winogrande: 80.8%.

What are the context window sizes for Phi-3.5-MoE-instruct and Qwen2.5-Coder 32B Instruct?

Phi-3.5-MoE-instruct supports an unknown number of tokens and Qwen2.5-Coder 32B Instruct supports 128K tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

What are the main differences between Phi-3.5-MoE-instruct and Qwen2.5-Coder 32B Instruct?

Key differences include LLM Stats Score (1.9 vs 2.0), licensing (MIT vs Apache 2.0). See the full comparison above for benchmark-by-benchmark results.

Who makes Phi-3.5-MoE-instruct and Qwen2.5-Coder 32B Instruct?

Phi-3.5-MoE-instruct is developed by Microsoft and Qwen2.5-Coder 32B Instruct is developed by Alibaba Cloud / Qwen Team.