Enter opens the highlighted result. Esc closes.

Mistral Small 4 vs Fugu Ultra

Mistral Small 4 costs 50.0x less per output token than Fugu Ultra ($0.60 vs $30.00 per million). Updated October 23, 2026; no benchmark has tested both models yet.

Replace Mistral Small 4 Replace Fugu Ultra
Mistral Small 4Mistral AI
Coding
No data
Overall
No data
Output $/M
$0.60
Fugu UltraSakana
Coding
No data
Overall
No data
Output $/M
$30.00
vs $0.60 vs $30.00 per 1M output tokens. Mistral Small 4 is 50.0x cheaper.

Mistral Small 4 or Fugu Ultra: which to pick

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

Pick Mistral Small 4 for output tokens 50.0x cheaper ($0.60 vs $30.00 per million).

Model AMistral Small 4Mistral AINot benchmarked1 independent benchmarkNo cost per solved taskModel BFugu UltraSakanaNot benchmarkedNo coding benchmarkNo cost per solved task

No benchmark has tested both yet. Mistral Small 4 has results on AA Coding Index, Vibe Code Bench (Vals AI) and SciCode; Fugu Ultra 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
Mistral Small 4 not benchmarked, Fugu Ultra 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
Mistral Small 4 $0.60 against Fugu Ultra $30.00 per million output tokens, 50.0x apart.
Context window
Mistral Small 4 takes 262K tokens, Fugu Ultra 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 Index5 boards measured
Coding benchmarks for Mistral Small 4 and Fugu Ultra
BenchmarkMistral Small 4Fugu UltraLeader
AA Coding Index26.6Not measuredOnly Mistral Small 4 measured
Vibe Code Bench (Vals AI)0.0%Not measuredOnly Mistral Small 4 measured
SciCode38.8%Not measuredOnly Mistral Small 4 measured
Terminal-Bench Hard (Artificial Analysis run)17.4%Not measuredOnly Mistral Small 4 measured
ALE-Bench497.6Not measuredOnly Mistral Small 4 measured
Neither model has a result on the other 38 boards here
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index1 board measured
Intelligence benchmarks for Mistral Small 4 and Fugu Ultra
BenchmarkMistral Small 4Fugu UltraLeader
AA Intelligence Index11.3Not measuredOnly Mistral Small 4 measured
Neither model has a result on the other 1 board here
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index2 boards measured
Agentic work benchmarks for Mistral Small 4 and Fugu Ultra
BenchmarkMistral Small 4Fugu UltraLeader
AA Agentic Index0.8Not measuredOnly Mistral Small 4 measured
τ²-Bench Telecom41.2%Not measuredOnly Mistral Small 4 measured
Neither model has a result on the other 40 boards here
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index3 boards measured
Reasoning benchmarks for Mistral Small 4 and Fugu Ultra
BenchmarkMistral Small 4Fugu UltraLeader
GPQA Diamond (Artificial Analysis run)76.9%Not measuredOnly Mistral Small 4 measured
Humanity's Last Exam (Artificial Analysis run)9.9%Not measuredOnly Mistral Small 4 measured
Kagi LLM Benchmark40.5%Not measuredOnly Mistral Small 4 measured
Neither model has a result on the other 20 boards here
GeneralDirectional onlyPublic boards, shown as published, kept out of the index4 boards measured
General benchmarks for Mistral Small 4 and Fugu Ultra
BenchmarkMistral Small 4Fugu UltraLeader
IFBench48.2%Not measuredOnly Mistral Small 4 measured
Long context reasoning (AA-LCR)49.7%Not measuredOnly Mistral Small 4 measured
DTBench70.9%Not measuredOnly Mistral Small 4 measured
LMCA20.6%Not measuredOnly Mistral Small 4 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

Mistral Small 4$0.0004Fits in one request
Fugu Ultra$0.020Fits in one request

Mistral Small 4 costs less

Repository review

50K input + 3K output tokens

Mistral Small 4$0.0093Fits in one request
Fugu Ultra$0.340Fits in one request

Mistral Small 4 costs less

Agent loop

200K input + 10K output tokens

Mistral Small 4$0.036Fits in one request
Fugu Ultra$1.30Fits in one request

Mistral Small 4 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 Mistral Small 4 and Fugu Ultra
SpecificationMistral Small 4Sakana Fugu Ultra
MakerMistral AISakana
WeightsOpen weightsNo public weights listed
ReleasedMarch 16, 2026June 24, 2026
Context window262K1M
Input $/Mtok$0.15$5.00
Output $/Mtok$0.60$30.00
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it10
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Mistral Small 4 better than Fugu Ultra for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Mistral Small 4 for output tokens 50.0x cheaper ($0.60 vs $30.00 per million).

Which is cheaper, Mistral Small 4 or Fugu Ultra?

Mistral Small 4 costs $0.15 per million input tokens and $0.60 per million output tokens; Fugu Ultra costs $5.00 and $30.00. Cost per solved task is known for neither of them.

Which has the bigger context window, Mistral Small 4 or Fugu Ultra?

Fugu Ultra, with 1M tokens against 262K.

Has any benchmark tested both Mistral Small 4 and Fugu Ultra?

No benchmark has tested both yet. Mistral Small 4 has results on AA Coding Index, Vibe Code Bench (Vals AI) and SciCode; Fugu Ultra has none yet. Compare them on price and context instead. Data as of October 23, 2026.

Compare next