llmboard.aiAI model intelligence
Home

Model Rankings

OverallOpen ModelsAgentCodingReasoningMathKnowledgeInstruction FollowingTextVision
Image GenerationImage Editing
Video GenerationImage to VideoVideo Editing
Text to SpeechSpeech to Text
Embeddings

Efficiency

Chat Token PricingImage PricingVideo PricingAudio Pricing
Chat Speed & LatencyProvider Reliability

Benchmarks

GPQAMMLU-ProAIME 2025SWE-Bench VerifiedMMLUHumanity's Last ExamLiveCodeBenchMATHHumanEvalMMMU-Pro
All Benchmarks

Tools

Model Directory

Scoring & Data

Scoring & Data
1464 models816 benchmarks

Leaderboard Center

Overall RankingCodingCore BenchmarksPrice & ValueRuntime Performance

Modalities

All ModelsImage GenerationImage EditingVideo GenerationImage-to-VideoVideo EditingText-to-SpeechSpeech-to-TextEmbeddings

Data & Methods

Scoring MethodAll Benchmarks
llmboard.aiCopyright 2026 llmboard.ai

Microsoft model product

Aion 1.0

3B-parameter open-weights small language model from Microsoft for on-device tasks such as summarization, rewriting, chat, document comprehension, and tool calling.

Updated Nov 22, 2026. Default version: Aion 1.0 Instruct

LLMBoard Score0.0Aion 1.0 Instruct
Coverage40%9 benchmark families
Context windowN/ATokens
Official input priceN/AOfficial price unavailable

On this page

  • Capability
  • Benchmarks
  • Arena
  • Pricing
  • Runtime
  • Specification
  • Versions
  • Similar models
  • About
  • FAQ

Aion 1.0 Capability Profile

This profile uses the model's current scored version. Arena ratings and prices are shown separately.

Aion 1.0 Instruct LLMBoard score breakdown

Aion 1.0 Benchmark Results

Benchmark scores for Aion 1.0 Instruct.

9 rows
Columns

Show columns

Sort by
Benchmark
Score
Rank
Participants
Percentile
Evidence
Evaluated
BenchmarkMulti-IFScore64.70%Rank23Participants27Percentile15.38%EvidenceCEvaluatedNov 21, 2026
BenchmarkMATH-500Score48.00%Rank34Participants34Percentile0.00%EvidenceCEvaluatedNov 21, 2026
BenchmarkGSM8kScore74.91%Rank42Participants49Percentile14.58%EvidenceCEvaluatedNov 21, 2026
BenchmarkIFBenchScore32.00%Rank46Participants48Percentile4.26%EvidenceCEvaluatedNov 21, 2026
BenchmarkIFEvalScore83.90%Rank48Participants72Percentile33.80%EvidenceCEvaluatedNov 21, 2026
BenchmarkMMMLUScore45.51%Rank51Participants52Percentile1.96%EvidenceCEvaluatedNov 21, 2026
BenchmarkMMLUScore55.15%Rank103Participants105Percentile1.92%EvidenceCEvaluatedNov 21, 2026
BenchmarkMMLU-ProScore33.35%Rank140Participants143Percentile2.11%EvidenceCEvaluatedNov 21, 2026
BenchmarkGPQAScore28.18%Rank258Participants268Percentile3.75%EvidenceCEvaluatedNov 21, 2026

Aion 1.0 Arena Results

Preference and agent-evaluation results for the default version.

No Arena results

The default version does not have a matching Arena result yet.

Aion 1.0 Pricing

Official vendor API pricing appears first, followed by individual provider offers.

Official API
N/A
Official provider
N/A
Lowest third-party
N/A
Tracked offerings
0
No provider prices

The default version has no current input or output token prices.

Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.

Aion 1.0 Runtime Performance

Provider-specific output speed and catalog latency for Aion 1.0 Instruct. Runtime does not affect the capability score.

No runtime data

No provider-specific speed or latency record is linked to the default version yet.

Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.

Aion 1.0 Specifications

Technical details for the model's default version.

Version
Aion 1.0 Instruct
Released
Nov 18, 2026
Knowledge cutoff
Dec 1, 2025
Parameters
2.3B
Context window
N/A
Max output
N/A
Inputs
text
Outputs
text
Open weights
Yes
License
MIT

Aion 1.0 Versions

Available versions of this model. The score column identifies the version used in the overall ranking.

1 row
Columns

Show columns

Sort by
Version
Released
LLMBoard
Parameters
Context
Max output
Open weights
License
VersionAion 1.0 InstructReleasedNov 18, 2026LLMBoard0.00Parameters2.3BContextN/AMax outputN/AOpen weightsYesLicenseMIT

Models similar to Aion 1.0

Recommendations prioritize the same model type and family, then the closest LLMBoard score.

#3530.00
MI

Phi 3.5 mini

Microsoft

0.00 LLMBoard

Details
#3540.00
MI

Phi 3.5 vision

Microsoft

0.00 LLMBoard

Details
#3550.00
MI

Phi 4 Mini

Microsoft

0.00 LLMBoard

Details
#325+2.85
MI

Phi 3.5 MoE

Microsoft

2.85 LLMBoard

Details
#322+4.02
MI

Phi 4 multimodal

Microsoft

4.02 LLMBoard

Details
#313+6.23
MI

Phi 4

Microsoft

6.23 LLMBoard

Details

What is Aion 1.0?

Key information about Aion 1.0 and its available data.

0 Instruct is a dense causal decoder model from the Microsoft Windows Applied Sciences Group, published under the MIT license. It has a 32,768-token context window and supports English, German, Spanish, Portuguese, Italian, French, Chinese, and Japanese.

Data as of 2026-11-21.

FAQ

Common questions about Aion 1.0.

When was Aion 1.0 released?

Aion 1.0's default version was released on Nov 18, 2026.

How much does Aion 1.0 cost?

No official standard PAYG price is currently available for Aion 1.0.

Who created Aion 1.0?

Aion 1.0 was created by Microsoft.

What is the context window for Aion 1.0?

A context window is not available for the default version.

Is Aion 1.0 open weight?

Yes. The default version is marked as open weight under MIT.

How many API providers offer Aion 1.0?

No provider offering is currently linked to the default version.

Browse runtime rankings