GPT OSS 120B High vs K-EXAONE-236B-A23B
GPT OSS 120B High and K-EXAONE-236B-A23B are closely matched at 25.4 and 26.2 on the LLM Stats Score. GPT OSS 120B High is 3.5x cheaper per token.
OpenAI · LG AI Research · Updated for 2026
Which is better?
GPT OSS 120B High and K-EXAONE-236B-A23B are closely matched on the overall LLM Stats Score at 25.4 and 26.2.
In the 6 individual benchmarks reported for both models, K-EXAONE-236B-A23B wins 4; this is a narrower head-to-head signal than the composite indexes.
On price, GPT OSS 120B High is roughly 3.5x cheaper per token on a blended 3:1 input/output basis, which adds up quickly at production volume.
GPT OSS 120B High also accepts a larger context window (131,072 input tokens), making it the stronger choice for long documents and large codebases.
Based on current LLM Stats indexes, shared benchmarks, pricing, and model metadata for 2026.
Choose GPT OSS 120B High
- cost matters — it's about 3.5x cheaper per token
- you process long inputs — it offers a 131,072 token context window
- you need open weights you can self-host or fine-tune
Choose K-EXAONE-236B-A23B
- you value its reported benchmark strengths — it wins 4 of 6 exact shared results
- you want the most recent training data — it shipped Dec 2025
At a glance
The differences that matter most.
Capability indexes
Additional strengths measured across groups of related public benchmarks
Individual benchmarks
7 reported for GPT OSS 120B High · 6 for K-EXAONE-236B-A23B
GPT OSS 120B High outperforms in 2 benchmarks (IFBench, LiveCodeBench v6), while K-EXAONE-236B-A23B is better at 4 benchmarks (AIME 2025, MMLU-Pro, MMMLU, t2-bench).
K-EXAONE-236B-A23B shows notably better performance in the majority of benchmarks.
Human preference
Blind head-to-head votes and playground preference scores
Pricing Analysis
Price comparison per million tokens
For input processing, GPT OSS 120B High ($0.10/1M tokens) is 6.0x cheaper than K-EXAONE-236B-A23B ($0.60/1M tokens).
For output processing, GPT OSS 120B High ($0.50/1M tokens) is 2.0x cheaper than K-EXAONE-236B-A23B ($1.00/1M tokens).
In conclusion, K-EXAONE-236B-A23B is more expensive than GPT OSS 120B High.*
* Using a 3:1 ratio of input to output tokens
Model Size
Parameter count comparison
K-EXAONE-236B-A23B has 119.2B more parameters than GPT OSS 120B High, making it 102.1% larger.
Context Window
Maximum input and output token capacity
GPT OSS 120B High accepts 131,072 input tokens compared to K-EXAONE-236B-A23B's 32,768 tokens. GPT OSS 120B High can generate longer responses up to 131,072 tokens, while K-EXAONE-236B-A23B is limited to 32,768 tokens.
License
Usage and distribution terms
GPT OSS 120B High is licensed under Apache 2.0, while K-EXAONE-236B-A23B uses a proprietary license.
License differences may affect how you can use these models in commercial or open-source projects.
Apache 2.0
Open weights
Proprietary
Closed source
Release Timeline
When each model was launched
GPT OSS 120B High was released on 2025-08-05, while K-EXAONE-236B-A23B was released on 2025-12-31.
K-EXAONE-236B-A23B is 5 months newer than GPT OSS 120B High.
Aug 5, 2025
1.2 years ago
Dec 31, 2025
9 months ago
4mo newerKnowledge Cutoff
When training data ends
K-EXAONE-236B-A23B has a documented knowledge cutoff of 2025-10-01, while GPT OSS 120B High's cutoff date is not specified.
We can confirm K-EXAONE-236B-A23B's training data extends to 2025-10-01, but cannot make a direct comparison without GPT OSS 120B High's cutoff date.
—
Oct 2025
Provider Availability
GPT OSS 120B High is available from OpenAI, Fireworks. K-EXAONE-236B-A23B is available from FriendliAI.
GPT OSS 120B High
K-EXAONE-236B-A23B
Outputs Comparison
Judge for yourself.
Run your own prompts against GPT OSS 120B High and K-EXAONE-236B-A23B side-by-side, then vote on the output you prefer.
FAQ
Common questions about GPT OSS 120B High vs K-EXAONE-236B-A23B.