Enter opens the highlighted result. Esc closes.

Qwen2.5 VL 72B Instruct vs Hy-MT2-30B-A3B

Hy-MT2-30B-A3B costs 3.4x less per output token than Qwen2.5 VL 72B Instruct ($0.295 vs $1.00 per million). Updated October 22, 2026; no benchmark has tested both models yet.

Replace Qwen2.5 VL 72B Instruct Replace Hy-MT2-30B-A3B
Qwen2.5 VL 72B InstructQwen
Coding
No data
Overall
No data
Output $/M
$1.00
Hy-MT2-30B-A3BTencent
Coding
No data
Overall
No data
Output $/M
$0.295
vs $1.00 vs $0.295 per 1M output tokens. Hy-MT2-30B-A3B is 3.4x cheaper.

Qwen2.5 VL 72B Instruct or Hy-MT2-30B-A3B: which to pick

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

Pick Qwen2.5 VL 72B Instruct for a larger context window (128K against 8K tokens).

Model AQwen2.5 VL 72B InstructQwenNot benchmarkedNo coding benchmarkNo cost per solved taskModel BHy-MT2-30B-A3BTencentNot benchmarkedNo coding benchmarkNo cost per solved task

No benchmark has tested both yet. Qwen2.5 VL 72B Instruct has results on OSWorld, Kagi LLM Benchmark and GeoBench; Hy-MT2-30B-A3B has none yet. 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.

At a glance

Coding index
Qwen2.5 VL 72B Instruct not benchmarked, Hy-MT2-30B-A3B 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
Qwen2.5 VL 72B Instruct $1.00 against Hy-MT2-30B-A3B $0.295 per million output tokens, 3.4x apart.
Context window
Qwen2.5 VL 72B Instruct takes 128K tokens, Hy-MT2-30B-A3B 8K.

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 Qwen2.5 VL 72B Instruct and Hy-MT2-30B-A3B
BenchmarkQwen2.5 VL 72B InstructHy-MT2-30B-A3BLeader
OSWorld5.0%Not measuredOnly 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 Qwen2.5 VL 72B Instruct and Hy-MT2-30B-A3B
BenchmarkQwen2.5 VL 72B InstructHy-MT2-30B-A3BLeader
Kagi LLM Benchmark36.0%Not measuredOnly 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 Qwen2.5 VL 72B Instruct and Hy-MT2-30B-A3B
BenchmarkQwen2.5 VL 72B InstructHy-MT2-30B-A3BLeader
GeoBench62.0%Not measuredOnly 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 Qwen2.5 VL 72B Instruct and Hy-MT2-30B-A3B
BenchmarkQwen2.5 VL 72B InstructHy-MT2-30B-A3BLeader
LMArena Vision1107Not measuredOnly Qwen2.5 VL 72B Instruct measured
LMArena Vision: English1115Not measuredOnly Qwen2.5 VL 72B Instruct measured
LMArena Vision: Chinese1107Not measuredOnly 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

Qwen2.5 VL 72B Instruct$0.0013Fits in one request
Hy-MT2-30B-A3B$0.0002Fits in one request

Hy-MT2-30B-A3B costs less

Repository review

50K input + 3K output tokens

Qwen2.5 VL 72B Instruct$0.043Fits in one request
Hy-MT2-30B-A3B$0.0046Exceeds the context window

Hy-MT2-30B-A3B costs less

Agent loop

200K input + 10K output tokens

Qwen2.5 VL 72B Instruct$0.170Exceeds the context window
Hy-MT2-30B-A3B$0.018Exceeds the context window

Hy-MT2-30B-A3B 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 Qwen2.5 VL 72B Instruct and Hy-MT2-30B-A3B
SpecificationQwen2.5 VL 72B InstructTencent Hy-MT2-30B-A3B
MakerQwenTencent
WeightsOpen weightsOpen weights
ReleasedFebruary 1, 2025August 20, 2026
Context window128K8K
Input $/Mtok$0.80$0.074
Output $/Mtok$1.00$0.295
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it00
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Qwen2.5 VL 72B Instruct better than Hy-MT2-30B-A3B for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Qwen2.5 VL 72B Instruct for a larger context window (128K against 8K tokens).

Which is cheaper, Qwen2.5 VL 72B Instruct or Hy-MT2-30B-A3B?

Qwen2.5 VL 72B Instruct costs $0.80 per million input tokens and $1.00 per million output tokens; Hy-MT2-30B-A3B costs $0.074 and $0.295. Cost per solved task is known for neither of them.

Which has the bigger context window, Qwen2.5 VL 72B Instruct or Hy-MT2-30B-A3B?

Qwen2.5 VL 72B Instruct, with 128K tokens against 8K.

Has any benchmark tested both Qwen2.5 VL 72B Instruct and Hy-MT2-30B-A3B?

No benchmark has tested both yet. Qwen2.5 VL 72B Instruct has results on OSWorld, Kagi LLM Benchmark and GeoBench; Hy-MT2-30B-A3B has none yet. Compare them on price and context instead. Data as of October 22, 2026.

Compare next