Aion 3.5 Mini vs Qwen2.5 VL 72B Instruct

Qwen2.5 VL 72B Instruct costs 1.4x less per output token than Aion 3.5 Mini ($1.00 vs $1.40 per million). Updated October 22, 2026; no benchmark has tested both models yet.

Replace Aion 3.5 Mini Replace Qwen2.5 VL 72B Instruct

A Aion 3.5 MiniAion Labs

Coding: No data
Overall: No data
Output $/M: $1.40

Qwen2.5 VL 72B InstructQwen

Coding: No data
Overall: No data
Output $/M: $1.00

vs $1.40 vs $1.00 per 1M output tokens. Qwen2.5 VL 72B Instruct is 1.4x cheaper.

Aion 3.5 Mini or Qwen2.5 VL 72B Instruct: which to pick

Neither model has a coding score yet, so the two cannot be ranked on coding.

Pick Aion 3.5 Mini for a larger context window (262K against 128K tokens).

Model AAion 3.5 MiniAion LabsNot benchmarkedNo coding benchmarkNo cost per solved task Model BQwen2.5 VL 72B InstructQwenNot benchmarkedNo coding benchmarkNo cost per solved task

No benchmark has tested both yet. Aion 3.5 Mini has none yet; Qwen2.5 VL 72B Instruct on OSWorld, Kagi LLM Benchmark and GeoBench. Compare them on price and context instead.

Which one for your work

Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.

Coding
Vibe Coding Index, six public coding benchmarks
No call
Neither has a coding score yet.
One side not measured
Long documents
Listed context window
Aion 3.5 Mini
Aion 3.5 Mini takes 262K tokens against 128K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Qwen2.5 VL 72B Instruct
Aion 3.5 Mini $0.0014, Qwen2.5 VL 72B Instruct $0.0013 per turn.
List prices

At a glance

Coding index: Aion 3.5 Mini not benchmarked, Qwen2.5 VL 72B Instruct not benchmarked.
Widest category: None yet: no category has been tested on both models.
Widest single gap: None yet: no benchmark has tested both models.
Output price: Aion 3.5 Mini $1.40 against Qwen2.5 VL 72B Instruct $1.00 per million output tokens, 1.4x apart.
Context window: Aion 3.5 Mini takes 262K tokens, Qwen2.5 VL 72B Instruct 128K.

Benchmark by benchmark

Every board either model has a result on, a category to a fold; bars are each result on a 0 to 100 scale. Only one model is measured on each, so no row names a leader.

Agentic workDirectional onlyPublic boards, shown as published, kept out of the index1 board measured

Agentic work benchmarks for Aion 3.5 Mini and Qwen2.5 VL 72B Instruct
Benchmark	Aion 3.5 Mini	Qwen2.5 VL 72B Instruct	Leader
OSWorld	Not measured	5.0%	Only Qwen2.5 VL 72B Instruct measured
Neither model has a result on the other 41 boards here

ReasoningDirectional onlyPublic boards, shown as published, kept out of the index1 board measured

Reasoning benchmarks for Aion 3.5 Mini and Qwen2.5 VL 72B Instruct
Benchmark	Aion 3.5 Mini	Qwen2.5 VL 72B Instruct	Leader
Kagi LLM Benchmark	Not measured	36.0%	Only Qwen2.5 VL 72B Instruct measured
Neither model has a result on the other 22 boards here

KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index1 board measured

Knowledge benchmarks for Aion 3.5 Mini and Qwen2.5 VL 72B Instruct
Benchmark	Aion 3.5 Mini	Qwen2.5 VL 72B Instruct	Leader
GeoBench	Not measured	62.0%	Only Qwen2.5 VL 72B Instruct measured
Neither model has a result on the other 19 boards here

GeneralDirectional onlyPublic boards, shown as published, kept out of the index3 boards measured

General benchmarks for Aion 3.5 Mini and Qwen2.5 VL 72B Instruct
Benchmark	Aion 3.5 Mini	Qwen2.5 VL 72B Instruct	Leader
LMArena Vision	Not measured	1107	Only Qwen2.5 VL 72B Instruct measured
LMArena Vision: English	Not measured	1115	Only Qwen2.5 VL 72B Instruct measured
LMArena Vision: Chinese	Not measured	1107	Only Qwen2.5 VL 72B Instruct measured
Neither model has a result on the other 45 boards here

What each workload costs

Three fixed token mixes at each model's listed price, so per-token rates become a bill.

Chat turn

1K input + 500 output tokens

Aion 3.5 Mini$0.0014Fits in one request

Qwen2.5 VL 72B Instruct$0.0013Fits in one request

Qwen2.5 VL 72B Instruct costs less

Repository review

50K input + 3K output tokens

Aion 3.5 Mini$0.039Fits in one request

Qwen2.5 VL 72B Instruct$0.043Fits in one request

Aion 3.5 Mini costs less

Agent loop

200K input + 10K output tokens

Aion 3.5 Mini$0.154Fits in one request

Qwen2.5 VL 72B Instruct$0.170Exceeds the context window

Aion 3.5 Mini costs less

Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.

Specification differences

The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.

Specifications of Aion 3.5 Mini and Qwen2.5 VL 72B Instruct
Specification	AionLabs Aion 3.5 Mini	Qwen2.5 VL 72B Instruct
Maker	Aion Labs	Qwen
Weights	No public weights listed	Open weights
Released	September 23, 2026	February 1, 2025
Context window	262K	128K
Input $/Mtok	$0.70	$0.80
Output $/Mtok	$1.40	$1.00
Coding index	Not benchmarked	Not benchmarked
Independent measurements behind it	0	0
Cost per solved task	Not computable	Not computable
Source	OpenRouter listing	OpenRouter listing

Questions

Is Aion 3.5 Mini better than Qwen2.5 VL 72B Instruct for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Aion 3.5 Mini for a larger context window (262K against 128K tokens).

Which is cheaper, Aion 3.5 Mini or Qwen2.5 VL 72B Instruct?

Aion 3.5 Mini costs $0.70 per million input tokens and $1.40 per million output tokens; Qwen2.5 VL 72B Instruct costs $0.80 and $1.00. Cost per solved task is known for neither of them.

Which has the bigger context window, Aion 3.5 Mini or Qwen2.5 VL 72B Instruct?

Aion 3.5 Mini, with 262K tokens against 128K.

Has any benchmark tested both Aion 3.5 Mini and Qwen2.5 VL 72B Instruct?

No benchmark has tested both yet. Aion 3.5 Mini has none yet; Qwen2.5 VL 72B Instruct on OSWorld, Kagi LLM Benchmark and GeoBench. Compare them on price and context instead. Data as of October 22, 2026.