The AI arena is free today

Open Superagent

GPT-6 Luna vs Phi-3.5-mini-instruct

GPT-6 Luna leads the LLM Stats Score 44.5 to -3.8. Phi-3.5-mini-instruct is 2.0x cheaper per token.

OpenAI · Microsoft · Updated for 2026

Which is better?

GPT-6 Luna leads the overall LLM Stats Score 44.5 to -3.8, ranking #41 overall.

On price, Phi-3.5-mini-instruct is roughly 2.0x cheaper per token on a blended 3:1 input/output basis, which adds up quickly at production volume.

GPT-6 Luna also accepts a larger context window (1,050,000 input tokens), making it the stronger choice for long documents and large codebases.

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

Choose GPT-6 Luna

  • overall performance matters — it scores 44.5 and ranks #41 on LLM Stats
  • your work emphasizes reasoning and coding — it leads those capability indexes
  • you process long inputs — it offers a 1,050,000 token context window
  • you want the most recent training data — it shipped Sep 2026

Choose Phi-3.5-mini-instruct

  • cost matters — it's about 2.0x cheaper per token
  • you need open weights you can self-host or fine-tune

At a glance

The differences that matter most.

Core performance indexes
44.5
#41
-3.8
#352
40.0
#58
-4.7
#348
31.4
#47
-6.8
#267
Cost, coverage & limits
Benchmark wins
Input price
$0.10 / M
$0.10 / M
Output price
$0.50 / M
$0.10 / M
Context window
1,050,000
128,000

Individual benchmarks

5 reported for GPT-6 Luna · 31 for Phi-3.5-mini-instruct

No common benchmarks found

GPT-6 Luna and Phi-3.5-mini-instructdon't have any common benchmark datasets to compare. They may have been evaluated on different testing suites.

Human preference

Blind head-to-head votes and playground preference scores

Pricing Analysis

Price comparison per million tokens

Phi-3.5-mini-instruct costs less

For input processing, GPT-6 Luna ($0.10/1M tokens) costs the same as Phi-3.5-mini-instruct ($0.10/1M tokens).

For output processing, GPT-6 Luna ($0.50/1M tokens) is 5.0x more expensive than Phi-3.5-mini-instruct ($0.10/1M tokens).

In conclusion, GPT-6 Luna is more expensive than Phi-3.5-mini-instruct.*

* Using a 3:1 ratio of input to output tokens

Lowest available price from all providers
Wed Sep 23 2026 • llm-stats.com
OpenAI
GPT-6 Luna
Input tokens$0.10
Output tokens$0.50
Best providerOpenAI
Microsoft
Phi-3.5-mini-instruct
Input tokens$0.10
Output tokens$0.10
Best providerAzure
Notice missing or incorrect data?Start an Issue

Context Window

Maximum input and output token capacity

GPT-6 Luna accepts 1,050,000 input tokens compared to Phi-3.5-mini-instruct's 128,000 tokens. Both models can generate responses up to 128,000 tokens.

OpenAI
GPT-6 Luna
Input1,050,000 tokens
Output128,000 tokens
Microsoft
Phi-3.5-mini-instruct
Input128,000 tokens
Output128,000 tokens
Wed Sep 23 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

GPT-6 Luna supports multimodal inputs, whereas Phi-3.5-mini-instruct does not.

GPT-6 Luna can handle both text and other forms of data like images, making it suitable for multimodal applications.

GPT-6 Luna

Text
Images
Audio
Video

Phi-3.5-mini-instruct

Text
Images
Audio
Video

License

Usage and distribution terms

GPT-6 Luna 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.

GPT-6 Luna

Proprietary

Closed source

Phi-3.5-mini-instruct

MIT

Open weights

Release Timeline

When each model was launched

GPT-6 Luna was released on 2026-09-22, while Phi-3.5-mini-instruct was released on 2024-08-23.

GPT-6 Luna is 25 months newer than Phi-3.5-mini-instruct.

GPT-6 Luna

Sep 22, 2026

0 days ago

2.1yr newer
Phi-3.5-mini-instruct

Aug 23, 2024

2.1 years ago

Knowledge Cutoff

When training data ends

GPT-6 Luna has a documented knowledge cutoff of 2026-05-18, while Phi-3.5-mini-instruct's cutoff date is not specified.

We can confirm GPT-6 Luna's training data extends to 2026-05-18, but cannot make a direct comparison without Phi-3.5-mini-instruct's cutoff date.

GPT-6 Luna

May 2026

Phi-3.5-mini-instruct

Provider Availability

GPT-6 Luna is available from OpenAI. Phi-3.5-mini-instruct is available from Azure.

GPT-6 Luna

openai logo
OpenAI
Input Price:Input: $0.10/1MOutput Price:Output: $0.50/1M

Phi-3.5-mini-instruct

azure logo
Azure
Input Price:Input: $0.10/1MOutput Price:Output: $0.10/1M
* Prices shown are per million tokens

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion

Judge for yourself.

Run your own prompts against GPT-6 Luna and Phi-3.5-mini-instruct side-by-side, then vote on the output you prefer.

GPT-6 Luna
✓ Preferred
Phi-3.5-mini-instruct
Open in Playground

FAQ

Common questions about GPT-6 Luna vs Phi-3.5-mini-instruct.

Which is better, GPT-6 Luna or Phi-3.5-mini-instruct?

GPT-6 Luna leads the LLM Stats Score 44.5 to -3.8. GPT-6 Luna is made by OpenAI 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 GPT-6 Luna compare to Phi-3.5-mini-instruct in benchmarks?

GPT-6 Luna scores DeepSWE 1.1: 66.6%, OSWorld 2.0: 52.7%, Agents' Last Exam: 50.9%, FrontierCode 1.1: 42.4%, AutomationBench v1.0.6: 20.7%. Phi-3.5-mini-instruct scores GSM8k: 86.2%, ARC-C: 84.6%, RULER: 84.1%, PIQA: 81.0%, OpenBookQA: 79.2%.

Is GPT-6 Luna cheaper than Phi-3.5-mini-instruct?

Both models cost $0.10 per million input tokens.

What are the context window sizes for GPT-6 Luna and Phi-3.5-mini-instruct?

GPT-6 Luna supports 1.1M 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 GPT-6 Luna and Phi-3.5-mini-instruct?

Key differences include LLM Stats Score (44.5 vs -3.8), context window (1.1M vs 128K), multimodal support (yes vs no), licensing (Proprietary vs MIT). See the full comparison above for benchmark-by-benchmark results.

Who makes GPT-6 Luna and Phi-3.5-mini-instruct?

GPT-6 Luna is developed by OpenAI and Phi-3.5-mini-instruct is developed by Microsoft.