Aion-2.0 Benchmark Scores & Performance

Benchmark analysis of Aion-2.0 by Aion Labs across 32 sourced tests on BenchLM.

According to BenchLM.ai, Aion-2.0 ranks #66 out of 123 models with an overall score of 58/100. While not a frontier model, it offers specific advantages depending on the use case.

Aion-2.0 is a proprietary model with a 128K token context window. It processes queries without explicit chain-of-thought reasoning, offering faster response times and lower token usage.

Its strongest category is Instruction Following (#12), while its weakest is Coding (#71). This performance profile makes it a well-rounded choice across a range of tasks.

Creator

Aion Labs

Source Type

Proprietary

Reasoning

Non-Reasoning

Context Window

128K

Overall Score

58#66 of 123

Arena Elo

1231

Knowledge Benchmarks

MMLU
78
GPQA
77
SuperGPQA
75
OpenBookQA
75
MMLU-Pro
67
HLE
5
FrontierScience
66

Coding Benchmarks

HumanEval
66
SWE-bench Verified
35
LiveCodeBench
29
SWE-bench Pro
37

Mathematics Benchmarks

AIME 2023
74
AIME 2024
76
AIME 2025
75
HMMT Feb 2023
70
HMMT Feb 2024
72
HMMT Feb 2025
71
BRUMO 2025
73
MATH-500
71

Reasoning Benchmarks

SimpleQA
76
MuSR
74
BBH
76
LongBench v2
64
MRCRv2
65

Agentic Benchmarks

Terminal-Bench 2.0
48
BrowseComp
60
OSWorld-Verified
50

Multimodal & Grounded Benchmarks

MMMU-Pro
61
OfficeQA Pro
72

Instruction Following Benchmarks

IFEval
93

Multilingual Benchmarks

MGSM
80
MMLU-ProX
77

Frequently Asked Questions

How does Aion-2.0 perform overall in AI benchmarks?

Aion-2.0 ranks #66 out of 123 models with an overall score of 58. It is created by Aion Labs and features a 128K context window.

Is Aion-2.0 good for knowledge and understanding?

Aion-2.0 ranks #63 out of 123 models in knowledge and understanding benchmarks with an average score of 54. There are stronger options in this category.

Is Aion-2.0 good for coding and programming?

Aion-2.0 ranks #71 out of 123 models in coding and programming benchmarks with an average score of 33.2. There are stronger options in this category.

Is Aion-2.0 good for mathematics?

Aion-2.0 ranks #66 out of 123 models in mathematics benchmarks with an average score of 72.1. There are stronger options in this category.

Is Aion-2.0 good for reasoning and logic?

Aion-2.0 ranks #60 out of 123 models in reasoning and logic benchmarks with an average score of 70.3. There are stronger options in this category.

Is Aion-2.0 good for agentic tool use and computer tasks?

Aion-2.0 ranks #69 out of 123 models in agentic tool use and computer tasks benchmarks with an average score of 51.7. There are stronger options in this category.

Is Aion-2.0 good for multimodal and grounded tasks?

Aion-2.0 ranks #67 out of 123 models in multimodal and grounded tasks benchmarks with an average score of 66. There are stronger options in this category.

Is Aion-2.0 good for instruction following?

Aion-2.0 ranks #12 out of 123 models in instruction following benchmarks with an average score of 93. There are stronger options in this category.

Is Aion-2.0 good for multilingual tasks?

Aion-2.0 ranks #62 out of 123 models in multilingual tasks benchmarks with an average score of 78.1. There are stronger options in this category.

What is the context window size of Aion-2.0?

Aion-2.0 has a context window of 128K, which determines how much text it can process in a single interaction.

Last updated: March 12, 2026

Weekly LLM Updates

New model releases, benchmark scores, and leaderboard changes. Every Friday.

Free. Your signup is stored with a derived country code for compliance routing.