Enter opens the highlighted result. Esc closes.

Qwen3.5-9B vs Fugu Max

Qwen3.5-9B costs 40.0x less per output token than Fugu Max ($0.15 vs $6.00 per million). Updated October 22, 2026; no benchmark has tested both models yet.

Replace Qwen3.5-9B Replace Fugu Max
Qwen3.5-9BQwen
Coding
No data
Overall
No data
Output $/M
$0.15
Fugu MaxSakana
Coding
No data
Overall
No data
Output $/M
$6.00
vs $0.15 vs $6.00 per 1M output tokens. Qwen3.5-9B is 40.0x cheaper.

Qwen3.5-9B or Fugu Max: which to pick

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

Pick Qwen3.5-9B for output tokens 40.0x cheaper ($0.15 vs $6.00 per million).

Model AQwen3.5-9BQwenNot benchmarkedNo coding benchmarkNo cost per solved taskModel BFugu MaxSakanaNot benchmarkedNo coding benchmarkNo cost per solved task

No benchmark has tested both yet. Qwen3.5-9B has results on AA Coding Index, SciCode and Terminal-Bench Hard (Artificial Analysis run); Fugu Max 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
Qwen3.5-9B not benchmarked, Fugu Max 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
Qwen3.5-9B $0.15 against Fugu Max $6.00 per million output tokens, 40.0x apart.
Context window
Qwen3.5-9B takes 262K tokens, Fugu Max 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.

CodingDirectional onlySix of these boards feed the Vibe Coding Index4 boards measured
Coding benchmarks for Qwen3.5-9B and Fugu Max
BenchmarkQwen3.5-9BFugu MaxLeader
AA Coding Index23.5Not measuredOnly Qwen3.5-9B measured
SciCode29.5%Not measuredOnly Qwen3.5-9B measured
Terminal-Bench Hard (Artificial Analysis run)24.2%Not measuredOnly Qwen3.5-9B measured
Terminal-Bench9.2%Not measuredOnly Qwen3.5-9B measured
Neither model has a result on the other 39 boards here
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index2 boards measured
Intelligence benchmarks for Qwen3.5-9B and Fugu Max
BenchmarkQwen3.5-9BFugu MaxLeader
AA Intelligence Index13.3Not measuredOnly Qwen3.5-9B measured
Epoch Capabilities Index139.3Not measuredOnly Qwen3.5-9B measured
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index1 board measured
Agentic work benchmarks for Qwen3.5-9B and Fugu Max
BenchmarkQwen3.5-9BFugu MaxLeader
τ²-Bench Telecom86.8%Not measuredOnly Qwen3.5-9B measured
Neither model has a result on the other 41 boards here
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index3 boards measured
Reasoning benchmarks for Qwen3.5-9B and Fugu Max
BenchmarkQwen3.5-9BFugu MaxLeader
GPQA Diamond (Artificial Analysis run)80.6%Not measuredOnly Qwen3.5-9B measured
Humanity's Last Exam (Artificial Analysis run)14.9%Not measuredOnly Qwen3.5-9B measured
GPQA Diamond (Epoch AI run)79.0%Not measuredOnly Qwen3.5-9B measured
Neither model has a result on the other 20 boards here
MathDirectional onlyPublic boards, shown as published, kept out of the index2 boards measured
Math benchmarks for Qwen3.5-9B and Fugu Max
BenchmarkQwen3.5-9BFugu MaxLeader
OTIS Mock AIME61.7%Not measuredOnly Qwen3.5-9B measured
MathArena13.0%Not measuredOnly Qwen3.5-9B measured
Neither model has a result on the other 12 boards here
GeneralDirectional onlyPublic boards, shown as published, kept out of the index4 boards measured
General benchmarks for Qwen3.5-9B and Fugu Max
BenchmarkQwen3.5-9BFugu MaxLeader
IFBench66.7%Not measuredOnly Qwen3.5-9B measured
Long context reasoning (AA-LCR)70.0%Not measuredOnly Qwen3.5-9B measured
DTBench71.2%Not measuredOnly Qwen3.5-9B measured
LMCA24.5%Not measuredOnly Qwen3.5-9B measured
Neither model has a result on the other 44 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

Qwen3.5-9B$0.0002Fits in one request
Fugu Max$0.0050Fits in one request

Qwen3.5-9B costs less

Repository review

50K input + 3K output tokens

Qwen3.5-9B$0.0054Fits in one request
Fugu Max$0.118Fits in one request

Qwen3.5-9B costs less

Agent loop

200K input + 10K output tokens

Qwen3.5-9B$0.021Fits in one request
Fugu Max$0.460Fits in one request

Qwen3.5-9B 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 Qwen3.5-9B and Fugu Max
SpecificationQwen3.5-9BSakana Fugu Max
MakerQwenSakana
WeightsOpen weightsNo public weights listed
ReleasedMarch 10, 2026September 11, 2026
Context window262K1M
Input $/Mtok$0.10$2.00
Output $/Mtok$0.15$6.00
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it00
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Qwen3.5-9B better than Fugu Max for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Qwen3.5-9B for output tokens 40.0x cheaper ($0.15 vs $6.00 per million).

Which is cheaper, Qwen3.5-9B or Fugu Max?

Qwen3.5-9B costs $0.10 per million input tokens and $0.15 per million output tokens; Fugu Max costs $2.00 and $6.00. Cost per solved task is known for neither of them.

Which has the bigger context window, Qwen3.5-9B or Fugu Max?

Fugu Max, with 1M tokens against 262K.

Has any benchmark tested both Qwen3.5-9B and Fugu Max?

No benchmark has tested both yet. Qwen3.5-9B has results on AA Coding Index, SciCode and Terminal-Bench Hard (Artificial Analysis run); Fugu Max has none yet. Compare them on price and context instead. Data as of October 22, 2026.

Compare next