The AI arena is free today

Open Superagent

Aion 1.0 Instruct vs Claude 3.5 Haiku

Claude 3.5 Haiku leads the LLM Stats Score 4.5 to -6.6.

Microsoft · Anthropic · Updated for 2026

Which is better?

Claude 3.5 Haiku leads the overall LLM Stats Score 4.5 to -6.6, ranking #352 overall.

In the 2 individual benchmarks reported for both models, Claude 3.5 Haiku wins 2; this is a narrower head-to-head signal than the composite indexes.

Based on current LLM Stats indexes, shared benchmarks, pricing, and model metadata for 2026.

Choose Aion 1.0 Instruct

  • you want the most recent training data — it shipped Nov 2026
  • you need open weights you can self-host or fine-tune

Choose Claude 3.5 Haiku

  • overall performance matters — it scores 4.5 and ranks #352 on LLM Stats
  • your work emphasizes reasoning — it leads those capability indexes
  • you value its reported benchmark strengths — it wins 2 of 2 exact shared results

At a glance

The differences that matter most.

Core performance indexes
-6.6
#414
4.5
#352
-10.1
#411
4.6
#345
Cost, coverage & limits
Benchmark wins
0 of 2
2 of 2
Input price
— / M
$0.80 / M
Output price
— / M
$4.00 / M
Context window
—
200,000

Capability indexes

Additional strengths measured across groups of related public benchmarks

1 shared
Index
Aion 1.0 Instruct
Claude 3.5 Haiku
-7.6#357
10.7#278
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

9 reported for Aion 1.0 Instruct · 9 for Claude 3.5 Haiku

2 shared

Aion 1.0 Instruct outperforms in 0 benchmarks, while Claude 3.5 Haiku is better at 2 benchmarks (GPQA, MMLU-Pro).

Claude 3.5 Haiku significantly outperforms across most benchmarks.

Fri Nov 20 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Context Window

Maximum input and output token capacity

Only Claude 3.5 Haiku specifies input context (200,000 tokens). Only Claude 3.5 Haiku specifies output context (200,000 tokens).

Microsoft
Aion 1.0 Instruct
Input- tokens
Output- tokens
Anthropic
Claude 3.5 Haiku
Input200,000 tokens
Output200,000 tokens
Fri Nov 20 2026 • llm-stats.com

License

Usage and distribution terms

Aion 1.0 Instruct is licensed under MIT, while Claude 3.5 Haiku uses a proprietary license.

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

Aion 1.0 Instruct

MIT

Open weights

Claude 3.5 Haiku

Proprietary

Closed source

Release Timeline

When each model was launched

Aion 1.0 Instruct was released on 2026-11-18, while Claude 3.5 Haiku was released on 2024-10-22.

Aion 1.0 Instruct is 25 months newer than Claude 3.5 Haiku.

Aion 1.0 Instruct

Nov 18, 2026

1 days ago

2.1yr newer
Claude 3.5 Haiku

Oct 22, 2024

2.1 years ago

Knowledge Cutoff

When training data ends

Aion 1.0 Instruct has a documented knowledge cutoff of 2025-12-01, while Claude 3.5 Haiku's cutoff date is not specified.

We can confirm Aion 1.0 Instruct's training data extends to 2025-12-01, but cannot make a direct comparison without Claude 3.5 Haiku's cutoff date.

Aion 1.0 Instruct

Dec 2025

Claude 3.5 Haiku

—

Outputs Comparison

Notice missing or incorrect data?

Judge for yourself.

Run your own prompts against Aion 1.0 Instruct and Claude 3.5 Haiku side-by-side, then vote on the output you prefer.

Aion 1.0 Instruct
✓ Preferred
Claude 3.5 Haiku
Open in Playground

FAQ

Common questions about Aion 1.0 Instruct vs Claude 3.5 Haiku.

Which is better, Aion 1.0 Instruct or Claude 3.5 Haiku?

Claude 3.5 Haiku leads the LLM Stats Score 4.5 to -6.6. Aion 1.0 Instruct is made by Microsoft and Claude 3.5 Haiku is made by Anthropic. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does Aion 1.0 Instruct compare to Claude 3.5 Haiku in benchmarks?

Aion 1.0 Instruct scores IFEval: 83.9%, GSM8k: 74.9%, Multi-IF: 64.7%, MMLU: 55.1%, MATH-500: 48.0%. Claude 3.5 Haiku scores HumanEval: 88.1%, MGSM: 85.6%, DROP: 83.1%, MATH: 69.4%, MMLU-Pro: 65.0%.

What are the context window sizes for Aion 1.0 Instruct and Claude 3.5 Haiku?

Aion 1.0 Instruct supports an unknown number of tokens and Claude 3.5 Haiku supports 200K tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

What are the main differences between Aion 1.0 Instruct and Claude 3.5 Haiku?

Key differences include LLM Stats Score (-6.6 vs 4.5), licensing (MIT vs Proprietary). See the full comparison above for benchmark-by-benchmark results.

Who makes Aion 1.0 Instruct and Claude 3.5 Haiku?

Aion 1.0 Instruct is developed by Microsoft and Claude 3.5 Haiku is developed by Anthropic.