The AI arena is free today

Open Superagent

GPT OSS 120B High vs MiniMax M1 40K

GPT OSS 120B High leads the LLM Stats Score 25.4 to 20.5.

OpenAI · MiniMax · Updated for 2026

Which is better?

GPT OSS 120B High leads the overall LLM Stats Score 25.4 to 20.5, ranking #161 overall.

In the 3 individual benchmarks reported for both models, GPT OSS 120B High wins 3; 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 OSS 120B High

  • overall performance matters — it scores 25.4 and ranks #161 on LLM Stats
  • your work emphasizes reasoning — it leads those capability indexes
  • you value its reported benchmark strengths — it wins 3 of 3 exact shared results
  • you want the most recent training data — it shipped Aug 2025

Choose MiniMax M1 40K

  • you are already invested in the MiniMax ecosystem

At a glance

The differences that matter most.

GPT OSS 120B High
OpenAI
MiniMax M1 40K
MiniMax
Core performance indexes
LLM Stats Score
25.4
#161
20.5
#197
Reasoning
25.6
#153
20.7
#186
Cost, coverage & limits
Benchmark wins
3 of 3
0 of 3
Input price
$0.10 / M
— / M
Output price
$0.50 / M
— / M
Context window
131,072
—

Capability indexes

Additional strengths measured across groups of related public benchmarks

1 shared
Index
GPT OSS 120B High
MiniMax M1 40K
Math
24.1#120
18.1#187
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

7 reported for GPT OSS 120B High · 16 for MiniMax M1 40K

3 shared

GPT OSS 120B High outperforms in 3 benchmarks (AIME 2025, GPQA, MMLU-Pro), while MiniMax M1 40K is better at 0 benchmarks.

GPT OSS 120B High significantly outperforms across most benchmarks.

Tue Sep 22 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Model Size

Parameter count comparison

339.2B diff

MiniMax M1 40K has 339.2B more parameters than GPT OSS 120B High, making it 290.4% larger.

OpenAI
GPT OSS 120B High
116.8Bparameters
MiniMax
MiniMax M1 40K
456.0Bparameters
116.8B
GPT OSS 120B High
456.0B
MiniMax M1 40K

Context Window

Maximum input and output token capacity

Only GPT OSS 120B High specifies input context (131,072 tokens). Only GPT OSS 120B High specifies output context (131,072 tokens).

OpenAI
GPT OSS 120B High
Input131,072 tokens
Output131,072 tokens
MiniMax
MiniMax M1 40K
Input- tokens
Output- tokens
Tue Sep 22 2026 • llm-stats.com

License

Usage and distribution terms

GPT OSS 120B High is licensed under Apache 2.0, while MiniMax M1 40K uses MIT.

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

GPT OSS 120B High

Apache 2.0

Open weights

MiniMax M1 40K

MIT

Open weights

Release Timeline

When each model was launched

GPT OSS 120B High was released on 2025-08-05, while MiniMax M1 40K was released on 2025-06-16.

GPT OSS 120B High is 2 months newer than MiniMax M1 40K.

GPT OSS 120B High

Aug 5, 2025

1.1 years ago

1mo newer
MiniMax M1 40K

Jun 16, 2025

1.3 years ago

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 GPT OSS 120B High and MiniMax M1 40K side-by-side, then vote on the output you prefer.

GPT OSS 120B High
✓ Preferred
MiniMax M1 40K
Open in Playground

FAQ

Common questions about GPT OSS 120B High vs MiniMax M1 40K.

Which is better, GPT OSS 120B High or MiniMax M1 40K?

GPT OSS 120B High leads the LLM Stats Score 25.4 to 20.5. GPT OSS 120B High is made by OpenAI and MiniMax M1 40K is made by MiniMax. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does GPT OSS 120B High compare to MiniMax M1 40K in benchmarks?

GPT OSS 120B High scores AIME 2025: 92.5%, MMMLU: 83.8%, LiveCodeBench v6: 81.9%, GPQA: 80.9%, MMLU-Pro: 80.7%. MiniMax M1 40K scores MATH-500: 96.0%, AIME 2024: 83.3%, MMLU-Pro: 80.6%, ZebraLogic: 80.1%, OpenAI-MRCR: 2 needle 128k: 76.1%.

What are the context window sizes for GPT OSS 120B High and MiniMax M1 40K?

GPT OSS 120B High supports 131K tokens and MiniMax M1 40K 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 OSS 120B High and MiniMax M1 40K?

Key differences include LLM Stats Score (25.4 vs 20.5), licensing (Apache 2.0 vs MIT). See the full comparison above for benchmark-by-benchmark results.

Who makes GPT OSS 120B High and MiniMax M1 40K?

GPT OSS 120B High is developed by OpenAI and MiniMax M1 40K is developed by MiniMax.

Related comparisons