GPT-OSS 120B vs K-Exaone

Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.

GPT-OSS 120B and K-Exaone finish on the same overall score, so this is less about a single winner and more about where the edge shows up. The headline says tie; the benchmark table is where the real choice happens.

K-Exaone is the reasoning model in the pair, while GPT-OSS 120B is not. That usually helps on harder chain-of-thought-heavy tests, but it can also mean more latency and more token spend in real use. K-Exaone gives you the larger context window at 256K, compared with 128K for GPT-OSS 120B.

Quick Verdict

Treat this as a split decision. GPT-OSS 120B makes more sense if you would rather avoid the extra latency and token burn of a reasoning model; K-Exaone is the better fit if coding is the priority or you need the larger 256K context window.

Agentic

Coming soon

Comparable scores for this category are coming soon. One or both models do not have sourced results here yet.

43%
Terminal-Bench 2.0
Coming soon
50%
BrowseComp
Coming soon
43%
OSWorld-Verified
Coming soon

Coding

K-Exaone

GPT-OSS 120B

30

K-Exaone

49.4

43%
HumanEval
Coming soon
29%
SWE-bench Verified
49.4%
25%
LiveCodeBench
Coming soon
31%
SWE-bench Pro
Coming soon
33.3%
SWE-Rebench
Coming soon

Multimodal & Grounded

Coming soon

Comparable scores for this category are coming soon. One or both models do not have sourced results here yet.

42%
MMMU-Pro
Coming soon
57%
OfficeQA Pro
Coming soon

Reasoning

Coming soon

Comparable scores for this category are coming soon. One or both models do not have sourced results here yet.

47%
MuSR
Coming soon
73%
BBH
Coming soon
58%
LongBench v2
Coming soon
59%
MRCRv2
Coming soon

Knowledge

Coming soon

Comparable scores for this category are coming soon. One or both models do not have sourced results here yet.

90%
MMLU
Coming soon
80.9%
GPQA
Coming soon
48%
SuperGPQA
Coming soon
90%
MMLU-Pro
Coming soon
5%
HLE
Coming soon
49%
FrontierScience
Coming soon
49%
SimpleQA
Coming soon

Instruction Following

Coming soon

Comparable scores for this category are coming soon. One or both models do not have sourced results here yet.

79%
IFEval
Coming soon

Multilingual

Coming soon

Comparable scores for this category are coming soon. One or both models do not have sourced results here yet.

72%
MGSM
Coming soon
70%
MMLU-ProX
Coming soon

Mathematics

Coming soon

Comparable scores for this category are coming soon. One or both models do not have sourced results here yet.

51%
AIME 2023
Coming soon
53%
AIME 2024
Coming soon
52%
AIME 2025
Coming soon
47%
HMMT Feb 2023
Coming soon
49%
HMMT Feb 2024
Coming soon
48%
HMMT Feb 2025
Coming soon
50%
BRUMO 2025
Coming soon
71%
MATH-500
Coming soon

Frequently Asked Questions

Which is better, GPT-OSS 120B or K-Exaone?

GPT-OSS 120B and K-Exaone are tied on overall score, so the right pick depends on which category matters most for your use case.

Which is better for coding, GPT-OSS 120B or K-Exaone?

K-Exaone has the edge for coding in this comparison, averaging 49.4 versus 30. Inside this category, SWE-bench Verified is the benchmark that creates the most daylight between them.

Last updated: March 18, 2026

Weekly LLM Benchmark Digest

Get notified when new models drop, benchmark scores change, or the leaderboard shifts. One email per week.

Free. No spam. Unsubscribe anytime. We only store derived location metadata for consent routing.