The AI arena is free today

Open Superagent

EXAONE 4.5 33B vs GPT OSS 120B High

Both models are evenly matched across the benchmarks.

LG AI Research · OpenAI · Updated for 2026

Which is better?

EXAONE 4.5 33B outperforms in 2 benchmarks (AIME 2025, MMLU-Pro), while GPT OSS 120B High is better at 2 benchmarks (GPQA, LiveCodeBench v6). Both models are evenly matched across the benchmarks.

Based on current benchmark, pricing, and model metadata for 2026.

Choose EXAONE 4.5 33B

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

Choose GPT OSS 120B High

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

At a glance

The differences that matter most.

Benchmark wins
2 of 4
2 of 4
Input price
— / M
$0.10 / M
Output price
— / M
$0.50 / M
Context window
131,072
Released
Apr 2026
Aug 2025
License
Proprietary
Apache 2.0

Performance Benchmarks

Comparative analysis across standard metrics

4 benchmarks

EXAONE 4.5 33B outperforms in 2 benchmarks (AIME 2025, MMLU-Pro), while GPT OSS 120B High is better at 2 benchmarks (GPQA, LiveCodeBench v6).

Both models are evenly matched across the benchmarks.

Thu Aug 27 2026 • llm-stats.com

Arena Performance

Playground indexes and blind preference scores

Model Size

Parameter count comparison

83.8B diff

GPT OSS 120B High has 83.8B more parameters than EXAONE 4.5 33B, making it 253.9% larger.

LG AI Research
EXAONE 4.5 33B
33.0Bparameters
OpenAI
GPT OSS 120B High
116.8Bparameters
33.0B
EXAONE 4.5 33B
116.8B
GPT OSS 120B High

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).

LG AI Research
EXAONE 4.5 33B
Input- tokens
Output- tokens
OpenAI
GPT OSS 120B High
Input131,072 tokens
Output131,072 tokens
Thu Aug 27 2026 • llm-stats.com

Input Capabilities

Supported data types and modalities

EXAONE 4.5 33B supports multimodal inputs, whereas GPT OSS 120B High does not.

EXAONE 4.5 33B can handle both text and other forms of data like images, making it suitable for multimodal applications.

EXAONE 4.5 33B

Text
Images
Audio
Video

GPT OSS 120B High

Text
Images
Audio
Video

License

Usage and distribution terms

EXAONE 4.5 33B is licensed under a proprietary license, while GPT OSS 120B High uses Apache 2.0.

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

EXAONE 4.5 33B

Proprietary

Closed source

GPT OSS 120B High

Apache 2.0

Open weights

Release Timeline

When each model was launched

EXAONE 4.5 33B was released on 2026-04-09, while GPT OSS 120B High was released on 2025-08-05.

EXAONE 4.5 33B is 8 months newer than GPT OSS 120B High.

EXAONE 4.5 33B

Apr 9, 2026

4 months ago

8mo newer
GPT OSS 120B High

Aug 5, 2025

1.1 years ago

Knowledge Cutoff

When training data ends

EXAONE 4.5 33B has a documented knowledge cutoff of 2024-12-01, while GPT OSS 120B High's cutoff date is not specified.

We can confirm EXAONE 4.5 33B's training data extends to 2024-12-01, but cannot make a direct comparison without GPT OSS 120B High's cutoff date.

EXAONE 4.5 33B

Dec 2024

GPT OSS 120B High

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion

Judge for yourself.

Run your own prompts against EXAONE 4.5 33B and GPT OSS 120B High side-by-side, then vote on the output you prefer.

EXAONE 4.5 33B
✓ Preferred
GPT OSS 120B High
Open in Playground

FAQ

Common questions about EXAONE 4.5 33B vs GPT OSS 120B High.

Which is better, EXAONE 4.5 33B or GPT OSS 120B High?

Both models are evenly matched across the benchmarks. EXAONE 4.5 33B is made by LG AI Research and GPT OSS 120B High is made by OpenAI. The best choice depends on your use case — compare their benchmark scores, pricing, and capabilities above.

How does EXAONE 4.5 33B compare to GPT OSS 120B High in benchmarks?

EXAONE 4.5 33B scores AIME 2025: 92.9%, AIME 2026: 92.6%, IFEval: 89.6%, AI2D: 89.0%, MathVista-Mini: 85.0%. GPT OSS 120B High scores AIME 2025: 92.5%, MMMLU: 83.8%, LiveCodeBench v6: 81.9%, GPQA: 80.9%, MMLU-Pro: 80.7%.

What are the context window sizes for EXAONE 4.5 33B and GPT OSS 120B High?

EXAONE 4.5 33B supports an unknown number of tokens and GPT OSS 120B High supports 131K tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

What are the main differences between EXAONE 4.5 33B and GPT OSS 120B High?

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

Who makes EXAONE 4.5 33B and GPT OSS 120B High?

EXAONE 4.5 33B is developed by LG AI Research and GPT OSS 120B High is developed by OpenAI.