Enter opens the highlighted result. Esc closes.

Qwen2.5 VL 72B Instruct vs Fugu Ultra v2

Qwen2.5 VL 72B Instruct costs 30.0x less per output token than Fugu Ultra v2 ($1.00 vs $30.00 per million). Updated October 23, 2026; no benchmark has tested both models yet.

Replace Qwen2.5 VL 72B Instruct Replace Fugu Ultra v2
Qwen2.5 VL 72B InstructQwen
Coding
No data
Overall
No data
Output $/M
$1.00
Fugu Ultra v2Sakana
Coding
No data
Overall
No data
Output $/M
$30.00
vs $1.00 vs $30.00 per 1M output tokens. Qwen2.5 VL 72B Instruct is 30.0x cheaper.

Qwen2.5 VL 72B Instruct or Fugu Ultra v2: 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 output tokens 30.0x cheaper ($1.00 vs $30.00 per million).

Model AQwen2.5 VL 72B InstructQwenNot benchmarkedNo coding benchmarkNo cost per solved taskModel BFugu Ultra v2SakanaNot 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; Fugu Ultra v2 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, Fugu Ultra v2 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 Fugu Ultra v2 $30.00 per million output tokens, 30.0x apart.
Context window
Qwen2.5 VL 72B Instruct takes 128K tokens, Fugu Ultra v2 1M.

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 Fugu Ultra v2
BenchmarkQwen2.5 VL 72B InstructFugu Ultra v2Leader
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 Fugu Ultra v2
BenchmarkQwen2.5 VL 72B InstructFugu Ultra v2Leader
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 Fugu Ultra v2
BenchmarkQwen2.5 VL 72B InstructFugu Ultra v2Leader
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 Fugu Ultra v2
BenchmarkQwen2.5 VL 72B InstructFugu Ultra v2Leader
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
Fugu Ultra v2$0.020Fits in one request

Qwen2.5 VL 72B Instruct costs less

Repository review

50K input + 3K output tokens

Qwen2.5 VL 72B Instruct$0.043Fits in one request
Fugu Ultra v2$0.340Fits in one request

Qwen2.5 VL 72B Instruct costs less

Agent loop

200K input + 10K output tokens

Qwen2.5 VL 72B Instruct$0.170Exceeds the context window
Fugu Ultra v2$1.30Fits in one request

Qwen2.5 VL 72B Instruct 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 Fugu Ultra v2
SpecificationQwen2.5 VL 72B InstructSakana Fugu Ultra v2
MakerQwenSakana
WeightsOpen weightsNo public weights listed
ReleasedFebruary 1, 2025September 11, 2026
Context window128K1M
Input $/Mtok$0.80$5.00
Output $/Mtok$1.00$30.00
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 Fugu Ultra v2 for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Qwen2.5 VL 72B Instruct for output tokens 30.0x cheaper ($1.00 vs $30.00 per million).

Which is cheaper, Qwen2.5 VL 72B Instruct or Fugu Ultra v2?

Qwen2.5 VL 72B Instruct costs $0.80 per million input tokens and $1.00 per million output tokens; Fugu Ultra v2 costs $5.00 and $30.00. Cost per solved task is known for neither of them.

Which has the bigger context window, Qwen2.5 VL 72B Instruct or Fugu Ultra v2?

Fugu Ultra v2, with 1M tokens against 128K.

Has any benchmark tested both Qwen2.5 VL 72B Instruct and Fugu Ultra v2?

No benchmark has tested both yet. Qwen2.5 VL 72B Instruct has results on OSWorld, Kagi LLM Benchmark and GeoBench; Fugu Ultra v2 has none yet. Compare them on price and context instead. Data as of October 23, 2026.

Compare next