The AI arena is free today

Open Superagent

GPT-6.1 Terra vs Phi-3.5-MoE-instruct

GPT-6.1 Terra leads the LLM Stats Score 47.5 to 1.4.

OpenAI · Microsoft · Updated for 2026

Which is better?

GPT-6.1 Terra leads the overall LLM Stats Score 47.5 to 1.4, ranking #36 overall.

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

Choose GPT-6.1 Terra

  • overall performance matters — it scores 47.5 and ranks #36 on LLM Stats
  • your work emphasizes reasoning and coding — it leads those capability indexes
  • you want the most recent training data — it shipped Oct 2026

Choose Phi-3.5-MoE-instruct

  • you need open weights you can self-host or fine-tune

At a glance

The differences that matter most.

GPT-6.1 Terra
OpenAI
Phi-3.5-MoE-instruct
Microsoft
Core performance indexes
LLM Stats Score
47.5
#36
1.4
#354
Reasoning
49.0
#19
1.0
#347
Coding
37.1
#30
-3.9
#288
Cost, coverage & limits
Benchmark wins
—
—
Input price
$1.00 / M
— / M
Output price
$5.00 / M
— / M
Context window
1,050,000
—

Individual benchmarks

8 reported for GPT-6.1 Terra · 31 for Phi-3.5-MoE-instruct

No common benchmarks found

GPT-6.1 Terra and Phi-3.5-MoE-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

Context Window

Maximum input and output token capacity

Only GPT-6.1 Terra specifies input context (1,050,000 tokens). Only GPT-6.1 Terra specifies output context (128,000 tokens).

OpenAI
GPT-6.1 Terra
Input1,050,000 tokens
Output128,000 tokens
Microsoft
Phi-3.5-MoE-instruct
Input- tokens
Output- tokens
Fri Oct 30 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

GPT-6.1 Terra supports multimodal inputs, whereas Phi-3.5-MoE-instruct does not.

GPT-6.1 Terra can handle both text and other forms of data like images, making it suitable for multimodal applications.

GPT-6.1 Terra

Text
Images
Audio
Video

Phi-3.5-MoE-instruct

Text
Images
Audio
Video

License

Usage and distribution terms

GPT-6.1 Terra is licensed under a proprietary license, while Phi-3.5-MoE-instruct uses MIT.

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

GPT-6.1 Terra

Proprietary

Closed source

Phi-3.5-MoE-instruct

MIT

Open weights

Release Timeline

When each model was launched

GPT-6.1 Terra was released on 2026-10-26, while Phi-3.5-MoE-instruct was released on 2024-08-23.

GPT-6.1 Terra is 26 months newer than Phi-3.5-MoE-instruct.

GPT-6.1 Terra

Oct 26, 2026

4 days ago

2.2yr newer
Phi-3.5-MoE-instruct

Aug 23, 2024

2.2 years ago

Knowledge Cutoff

When training data ends

GPT-6.1 Terra has a documented knowledge cutoff of 2026-06-01, while Phi-3.5-MoE-instruct's cutoff date is not specified.

We can confirm GPT-6.1 Terra's training data extends to 2026-06-01, but cannot make a direct comparison without Phi-3.5-MoE-instruct's cutoff date.

GPT-6.1 Terra

Jun 2026

Phi-3.5-MoE-instruct

—

Outputs Comparison

Notice missing or incorrect data?

Judge for yourself.

Run your own prompts against GPT-6.1 Terra and Phi-3.5-MoE-instruct side-by-side, then vote on the output you prefer.

GPT-6.1 Terra
✓ Preferred
Phi-3.5-MoE-instruct
Open in Playground

FAQ

Common questions about GPT-6.1 Terra vs Phi-3.5-MoE-instruct.

Which is better, GPT-6.1 Terra or Phi-3.5-MoE-instruct?

GPT-6.1 Terra leads the LLM Stats Score 47.5 to 1.4. GPT-6.1 Terra is made by OpenAI and Phi-3.5-MoE-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-6.1 Terra compare to Phi-3.5-MoE-instruct in benchmarks?

GPT-6.1 Terra scores HealthBench Consensus: 95.1%, HealthBench Professional: 62.7%, Agents' Last Exam: 60.0%, Terminal-Bench-Science 0.1: 58.3%, MentalHealthBench: 55.5%. Phi-3.5-MoE-instruct scores ARC-C: 91.0%, OpenBookQA: 89.6%, GSM8k: 88.7%, PIQA: 88.6%, RULER: 87.1%.

What are the context window sizes for GPT-6.1 Terra and Phi-3.5-MoE-instruct?

GPT-6.1 Terra supports 1.1M tokens and Phi-3.5-MoE-instruct supports an unknown number of tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

What are the main differences between GPT-6.1 Terra and Phi-3.5-MoE-instruct?

Key differences include LLM Stats Score (47.5 vs 1.4), multimodal support (yes vs no), licensing (Proprietary vs MIT). See the full comparison above for benchmark-by-benchmark results.

Who makes GPT-6.1 Terra and Phi-3.5-MoE-instruct?

GPT-6.1 Terra is developed by OpenAI and Phi-3.5-MoE-instruct is developed by Microsoft.

Related comparisons