The AI arena is free today

Open Superagent

Grok-1.5 vs Phi-3.5-mini-instruct

Grok-1.5 and Phi-3.5-mini-instruct are closely matched at -2.4 and -3.7 on the LLM Stats Score.

xAI · Microsoft · Updated for 2026

Which is better?

Grok-1.5 and Phi-3.5-mini-instruct are closely matched on the overall LLM Stats Score at -2.4 and -3.7.

In the 6 individual benchmarks reported for both models, Grok-1.5 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 Grok-1.5

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

Choose Phi-3.5-mini-instruct

  • you want the most recent training data — it shipped Aug 2024
  • you need open weights you can self-host or fine-tune

At a glance

The differences that matter most.

Grok-1.5
xAI
Phi-3.5-mini-instruct
Microsoft
Core performance indexes
LLM Stats Score
-2.4
#323
-3.7
#329
Reasoning
-1.9
#314
-4.6
#327
Coding
-0.8
#232
-6.8
#248
Cost, coverage & limits
Benchmark wins
6 of 6
0 of 6
Input price
— / M
$0.10 / M
Output price
— / M
$0.10 / M
Context window
—
128,000

Capability indexes

Additional strengths measured across groups of related public benchmarks

3 shared
Index
Grok-1.5
Phi-3.5-mini-instruct
Math
5.4#264
-1.1#293
Finance
5.2#163
1.0#182
Legal
5.2#148
1.0#169
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

9 reported for Grok-1.5 · 31 for Phi-3.5-mini-instruct

6 shared

Grok-1.5 outperforms in 6 benchmarks (GPQA, GSM8k, HumanEval, MATH, MMLU, MMLU-Pro), while Phi-3.5-mini-instruct is better at 0 benchmarks.

Grok-1.5 significantly outperforms across most benchmarks.

Mon Aug 31 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Context Window

Maximum input and output token capacity

Only Phi-3.5-mini-instruct specifies input context (128,000 tokens). Only Phi-3.5-mini-instruct specifies output context (128,000 tokens).

xAI
Grok-1.5
Input- tokens
Output- tokens
Microsoft
Phi-3.5-mini-instruct
Input128,000 tokens
Output128,000 tokens
Mon Aug 31 2026 • llm-stats.com

License

Usage and distribution terms

Grok-1.5 is licensed under a proprietary license, while Phi-3.5-mini-instruct uses MIT.

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

Grok-1.5

Proprietary

Closed source

Phi-3.5-mini-instruct

MIT

Open weights

Release Timeline

When each model was launched

Grok-1.5 was released on 2024-03-28, while Phi-3.5-mini-instruct was released on 2024-08-23.

Phi-3.5-mini-instruct is 5 months newer than Grok-1.5.

Grok-1.5

Mar 28, 2024

2.4 years ago

Phi-3.5-mini-instruct

Aug 23, 2024

2.0 years ago

4mo 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 Grok-1.5 and Phi-3.5-mini-instruct side-by-side, then vote on the output you prefer.

Grok-1.5
✓ Preferred
Phi-3.5-mini-instruct
Open in Playground

FAQ

Common questions about Grok-1.5 vs Phi-3.5-mini-instruct.

Which is better, Grok-1.5 or Phi-3.5-mini-instruct?

Grok-1.5 and Phi-3.5-mini-instruct are closely matched on the LLM Stats Score at -2.4 and -3.7. Grok-1.5 is made by xAI and Phi-3.5-mini-instruct is made by Microsoft. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does Grok-1.5 compare to Phi-3.5-mini-instruct in benchmarks?

Grok-1.5 scores GSM8k: 90.0%, DocVQA: 85.6%, MMLU: 81.3%, HumanEval: 74.1%, MMMU: 53.6%. Phi-3.5-mini-instruct scores GSM8k: 86.2%, ARC-C: 84.6%, RULER: 84.1%, PIQA: 81.0%, OpenBookQA: 79.2%.

What are the context window sizes for Grok-1.5 and Phi-3.5-mini-instruct?

Grok-1.5 supports an unknown number of tokens and Phi-3.5-mini-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 Grok-1.5 and Phi-3.5-mini-instruct?

Key differences include LLM Stats Score (-2.4 vs -3.7), licensing (Proprietary vs MIT). See the full comparison above for benchmark-by-benchmark results.

Who makes Grok-1.5 and Phi-3.5-mini-instruct?

Grok-1.5 is developed by xAI and Phi-3.5-mini-instruct is developed by Microsoft.

Related comparisons