Noometry

Model comparison

Aion 3.5 vs Claude Sonnet 5

Claude Sonnet 5 has enough public results to be ranked (#26); Aion 3.5 does not yet, so treat this comparison as directional.

Last verified . 1 shared benchmarks.

Aion 3.5 AionLabs

57.9

Unranked Sparse

Claude Sonnet 5 Anthropic

54.5

Rank #26 Confirmed

Summary

  • They share 1 benchmark with published results for both. Aion 3.5 scores higher in 1 category and Claude Sonnet 5 in 0 categories; one gap is clear of the uncertainty.
  • The widest gap is in writing & preference, where Aion 3.5 leads 74.9 to 69.4.
  • Aion 3.5 is cheaper at $3 / $6 per million input/output tokens, against $2 / $10 for Claude Sonnet 5.
  • Claude Sonnet 5 accepts more context: 1M tokens versus 262K.

Side by side

Aion 3.5Claude Sonnet 5
ProviderAionLabsAnthropic
Noometry Index57.954.5
Released—2026-06-29
WeightsProprietaryProprietary
Context window262K1M
Max output33K128K
Input $ / M tokens$3$2
Output $ / M tokens$6$10
Results tracked151

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding Not comparable

Aion 3.5: —, Claude Sonnet 5: 55.5 (#20)

BenchmarkAion 3.5Claude Sonnet 5
DeepSWE—53.8%
FrontierCode—42.7%
CursorBench—34.1%
LMArena WebDev—1540
SciCode—53.6%
GSO—37.3%
WeirdML—68.8%
LMArena Coding—1483
ALE-Bench—1,463

Agentic & Tool Use Not comparable

Aion 3.5: —, Claude Sonnet 5: 42.7 (#16)

BenchmarkAion 3.5Claude Sonnet 5
APEX-Agents—54.5%
GBAEval—65.3%
LMArena Search—1194
Vending-Bench 2—6,378

Reasoning Not comparable

Aion 3.5: —, Claude Sonnet 5: 48.2 (#37)

BenchmarkAion 3.5Claude Sonnet 5
SimpleBench—60.6%
NYT Connections (extended)—75.1%
CritPt—16.9%
Chess Puzzles—35%
LMArena Hard Prompts—1461
Mystery Game Puzzles—35%
DTBench—92.5%
LMCA—50%
Surface Evolver Bench—60%
Bench to the Future 3—0.14
Epoch Capabilities Index—156.34
ForecastBench—61.1

Math Not comparable

Aion 3.5: —, Claude Sonnet 5: 66.1 (#21)

BenchmarkAion 3.5Claude Sonnet 5
FrontierMath (Tiers 1-3)—65.6%
FrontierMath Tier 4—29.3%
OTIS Mock AIME 2024-2025—94.7%
ProofBench—77%
LMArena Math—1467

Knowledge Not comparable

Aion 3.5: —, Claude Sonnet 5: 55.7 (#42)

BenchmarkAion 3.5Claude Sonnet 5
GPQA Diamond—90.5%
SimpleQA Verified—33.7%
LMArena Expert—1491

Multimodal Not comparable

Aion 3.5: —, Claude Sonnet 5: 42.4 (#26)

BenchmarkAion 3.5Claude Sonnet 5
LMArena Vision—1275
Blueprint-Bench 2—24.9%
LMArena Document—1466

Multilingual Not comparable

Aion 3.5: —, Claude Sonnet 5: 54.0 (#55)

BenchmarkAion 3.5Claude Sonnet 5
LMArena Non-English—1431
LMArena Chinese—1475
LMArena French—1457
LMArena German—1448
LMArena Japanese—1422
LMArena Korean—1411
LMArena Russian—1452
LMArena Spanish—1436

Instruction Following Not comparable

Aion 3.5: —, Claude Sonnet 5: 76.6 (#39)

BenchmarkAion 3.5Claude Sonnet 5
LMArena Instruction Following—1453

Long Context Not comparable

Aion 3.5: —, Claude Sonnet 5: 44.8 (#53)

BenchmarkAion 3.5Claude Sonnet 5
LMArena Longer Query—1464

Writing & Preference Aion 3.5 leads

Aion 3.5: 74.9, Claude Sonnet 5: 69.4 (#24)

BenchmarkAion 3.5Claude Sonnet 5
EQ-Bench Creative Writing19291794
LMArena Text—1443
LMArena Creative Writing—1416
EQ-Bench 4—1236
LMArena Multi-Turn—1454

Frequently asked questions

Is Aion 3.5 better than Claude Sonnet 5?

Claude Sonnet 5 has enough public results to be ranked (#26); Aion 3.5 does not yet, so treat this comparison as directional.

Which is cheaper, Aion 3.5 or Claude Sonnet 5?

Aion 3.5 is cheaper. It lists at $3 per million input tokens and $6 per million output tokens; Claude Sonnet 5 lists at $2 and $10.

Which has the bigger context window?

Claude Sonnet 5 does, with 1M tokens against 262K.

How many benchmarks do Aion 3.5 and Claude Sonnet 5 share?

1 benchmark has published results for both models. Aion 3.5 has 1 scored results on Noometry and Claude Sonnet 5 has 51.

Related comparisons

Go deeper