The AI arena is free today

Open Superagent

GPT-5.1 Codex vs MAI-Thinking-1

GPT-5.1 Codex and MAI-Thinking-1 are closely matched at 29.6 and 33.1 on the LLM Stats Score.

OpenAI · Microsoft · Updated for 2026

Which is better?

GPT-5.1 Codex and MAI-Thinking-1 are closely matched on the overall LLM Stats Score at 29.6 and 33.1.

In the 2 individual benchmarks reported for both models, GPT-5.1 Codex wins 2; 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 GPT-5.1 Codex

  • you value its reported benchmark strengths — it wins 2 of 2 exact shared results

Choose MAI-Thinking-1

  • you want the most recent training data — it shipped Jun 2026

At a glance

The differences that matter most.

GPT-5.1 Codex
OpenAI
MAI-Thinking-1
Microsoft
Core performance indexes
LLM Stats Score
29.6
#126
33.1
#100
Reasoning
29.8
#118
33.9
#91
Coding
21.0
#91
19.4
#103
Agents
10.5
#114
12.8
#96
Cost, coverage & limits
Benchmark wins
2 of 2
0 of 2
Input price
$1.25 / M
— / M
Output price
$10.00 / M
— / M
Context window
400,000
—

Individual benchmarks

3 reported for GPT-5.1 Codex · 23 for MAI-Thinking-1

2 shared

GPT-5.1 Codex outperforms in 2 benchmarks (SWE-Bench Verified, Terminal-Bench 2.0), while MAI-Thinking-1 is better at 0 benchmarks.

GPT-5.1 Codex significantly outperforms across most benchmarks.

Wed Sep 09 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Context Window

Maximum input and output token capacity

Only GPT-5.1 Codex specifies input context (400,000 tokens). Only GPT-5.1 Codex specifies output context (128,000 tokens).

OpenAI
GPT-5.1 Codex
Input400,000 tokens
Output128,000 tokens
Microsoft
MAI-Thinking-1
Input- tokens
Output- tokens
Wed Sep 09 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

GPT-5.1 Codex supports multimodal inputs, whereas MAI-Thinking-1 does not.

GPT-5.1 Codex can handle both text and other forms of data like images, making it suitable for multimodal applications.

GPT-5.1 Codex

Text
Images
Audio
Video

MAI-Thinking-1

Text
Images
Audio
Video

License

Usage and distribution terms

Both models are licensed under proprietary licenses.

Both models have usage restrictions defined by their respective organizations.

GPT-5.1 Codex

Proprietary

Closed source

MAI-Thinking-1

Proprietary

Closed source

Release Timeline

When each model was launched

GPT-5.1 Codex was released on 2025-11-19, while MAI-Thinking-1 was released on 2026-06-02.

MAI-Thinking-1 is 7 months newer than GPT-5.1 Codex.

GPT-5.1 Codex

Nov 19, 2025

9 months ago

MAI-Thinking-1

Jun 2, 2026

3 months ago

6mo newer

Knowledge Cutoff

When training data ends

GPT-5.1 Codex has a documented knowledge cutoff of 2024-09-30, while MAI-Thinking-1's cutoff date is not specified.

We can confirm GPT-5.1 Codex's training data extends to 2024-09-30, but cannot make a direct comparison without MAI-Thinking-1's cutoff date.

GPT-5.1 Codex

Sep 2024

MAI-Thinking-1

—

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion→

Judge for yourself.

Run your own prompts against GPT-5.1 Codex and MAI-Thinking-1 side-by-side, then vote on the output you prefer.

GPT-5.1 Codex
✓ Preferred
MAI-Thinking-1
Open in Playground

FAQ

Common questions about GPT-5.1 Codex vs MAI-Thinking-1.

Which is better, GPT-5.1 Codex or MAI-Thinking-1?

GPT-5.1 Codex and MAI-Thinking-1 are closely matched on the LLM Stats Score at 29.6 and 33.1. GPT-5.1 Codex is made by OpenAI and MAI-Thinking-1 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-5.1 Codex compare to MAI-Thinking-1 in benchmarks?

GPT-5.1 Codex scores SWE-Bench Verified: 73.7%, SWE-Lancer: 66.3%, Terminal-Bench 2.0: 52.8%. MAI-Thinking-1 scores LongFact: 98.0%, AIME 2025: 97.0%, AIME 2026: 94.5%, GraphWalks: 90.0%, AIR-Bench: 88.0%.

What are the context window sizes for GPT-5.1 Codex and MAI-Thinking-1?

GPT-5.1 Codex supports 400K tokens and MAI-Thinking-1 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-5.1 Codex and MAI-Thinking-1?

Key differences include LLM Stats Score (29.6 vs 33.1), multimodal support (yes vs no). See the full comparison above for benchmark-by-benchmark results.

Who makes GPT-5.1 Codex and MAI-Thinking-1?

GPT-5.1 Codex is developed by OpenAI and MAI-Thinking-1 is developed by Microsoft.

Related comparisons