The AI arena is free today

Open Superagent

GPT-5 Medium vs IBM Granite 4.2 30B

GPT-5 Medium leads the LLM Stats Score 30.2 to 24.0.

OpenAI · IBM · Updated for 2026

Which is better?

GPT-5 Medium leads the overall LLM Stats Score 30.2 to 24.0, ranking #109 overall.

The models split the 2 individual benchmarks reported for both models evenly.

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

Choose GPT-5 Medium

  • overall performance matters — it scores 30.2 and ranks #109 on LLM Stats
  • your work emphasizes reasoning — it leads those capability indexes

Choose IBM Granite 4.2 30B

  • you want the most recent training data — it shipped Aug 2026
  • you need open weights you can self-host or fine-tune

At a glance

The differences that matter most.

Core performance indexes
30.2
#109
24.0
#156
29.1
#113
21.8
#165
Cost, coverage & limits
Benchmark wins
1 of 2
1 of 2
Input price
$1.25 / M
— / M
Output price
$10.00 / M
— / M
Context window
400,000

Individual benchmarks

2 reported for GPT-5 Medium · 18 for IBM Granite 4.2 30B

2 shared

GPT-5 Medium outperforms in 1 benchmarks (GPQA), while IBM Granite 4.2 30B is better at 1 benchmark (AIME 2025).

Both models are evenly matched across the 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 GPT-5 Medium specifies input context (400,000 tokens). Only GPT-5 Medium specifies output context (128,000 tokens).

OpenAI
GPT-5 Medium
Input400,000 tokens
Output128,000 tokens
IBM
IBM Granite 4.2 30B
Input- tokens
Output- tokens
Mon Aug 31 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

GPT-5 Medium supports multimodal inputs, whereas IBM Granite 4.2 30B does not.

GPT-5 Medium can handle both text and other forms of data like images, making it suitable for multimodal applications.

GPT-5 Medium

Text
Images
Audio
Video

IBM Granite 4.2 30B

Text
Images
Audio
Video

License

Usage and distribution terms

GPT-5 Medium is licensed under a proprietary license, while IBM Granite 4.2 30B uses Apache 2.0.

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

GPT-5 Medium

Proprietary

Closed source

IBM Granite 4.2 30B

Apache 2.0

Open weights

Release Timeline

When each model was launched

GPT-5 Medium was released on 2025-08-07, while IBM Granite 4.2 30B was released on 2026-08-25.

IBM Granite 4.2 30B is 13 months newer than GPT-5 Medium.

GPT-5 Medium

Aug 7, 2025

1.1 years ago

IBM Granite 4.2 30B

Aug 25, 2026

5 days ago

1.0yr newer

Knowledge Cutoff

When training data ends

GPT-5 Medium has a documented knowledge cutoff of 2024-09-30, while IBM Granite 4.2 30B's cutoff date is not specified.

We can confirm GPT-5 Medium's training data extends to 2024-09-30, but cannot make a direct comparison without IBM Granite 4.2 30B's cutoff date.

GPT-5 Medium

Sep 2024

IBM Granite 4.2 30B

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion

Judge for yourself.

Run your own prompts against GPT-5 Medium and IBM Granite 4.2 30B side-by-side, then vote on the output you prefer.

GPT-5 Medium
✓ Preferred
IBM Granite 4.2 30B
Open in Playground

FAQ

Common questions about GPT-5 Medium vs IBM Granite 4.2 30B.

Which is better, GPT-5 Medium or IBM Granite 4.2 30B?

GPT-5 Medium leads the LLM Stats Score 30.2 to 24.0. GPT-5 Medium is made by OpenAI and IBM Granite 4.2 30B is made by IBM. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does GPT-5 Medium compare to IBM Granite 4.2 30B in benchmarks?

GPT-5 Medium scores AIME 2025: 88.9%, GPQA: 88.1%. IBM Granite 4.2 30B scores RULER 64k: 90.0%, AIME 2025: 89.2%, HMMT25: 89.2%, RULER 128k: 81.4%, MMLU-Pro: 77.6%.

What are the context window sizes for GPT-5 Medium and IBM Granite 4.2 30B?

GPT-5 Medium supports 400K tokens and IBM Granite 4.2 30B 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 Medium and IBM Granite 4.2 30B?

Key differences include LLM Stats Score (30.2 vs 24.0), multimodal support (yes vs no), licensing (Proprietary vs Apache 2.0). See the full comparison above for benchmark-by-benchmark results.

Who makes GPT-5 Medium and IBM Granite 4.2 30B?

GPT-5 Medium is developed by OpenAI and IBM Granite 4.2 30B is developed by IBM.