Sakana Fugu

Sakana Fugu is a reasoning model from Sakana AI. 6 benchmarks count toward its score, in 3 categories.

partialShows if the model has enough results for an index.
IndexOverall score out of 100.Unranked
CoverageShare of the index weight with results.45%
SpeedOutput tokens per second.
Input / 1MUS dollars per 1M input tokens.N/A
Output / 1MUS dollars per 1M output tokens.N/A
ContextMaximum tokens in one request.1M
EloLMArena rating and rank.N/A

The index is a score out of 100. The ± range shows how much it can change.

CapabilitiesScore per category, out of 100.

Out of 100
AgenticMulti-step tasks with tools.
N/A
CodingCode writing and repair.
64.7
ReasoningLogic problems and puzzles.
N/A
MultimodalTasks with images and text.
63.0
KnowledgeFacts and expert knowledge.
67.6
MultilingualTasks in many languages.
N/A
InstructionTasks with strict rules in the prompt.
N/A
MathMath problems.
N/A

Results

6 counted
BenchmarkThe test name.CategoryThe capability that the test measures.ResultThe score from the publisher.IndexThis result as a score out of 100.RunThe settings of the run.DateDate of the result.Published byThe source of the result.
Graduate-Level Google-Proof Q&AKnowledge95.5%66.4David Rein et al.
GPQA DiamondKnowledge95.5%66.4David Rein et al.
LiveCodeBench v6Coding92.9%61.6LiveCodeBench maintainers
LiveCodeBench ProCoding87.8%LiveCodeBench Pro authors
MRCRv2Reasoning86.6%OpenAI
CharXiv ReasoningMultimodal85.1%63.0CharXiv authors
Scientific Code BenchmarkCoding60.1%71.3Benchmark authors
SWE-bench ProCoding59.0%61.1Xiang Deng et al.
Humanity's Last Exam without toolsKnowledge47.2%68.8OpenAI

6 benchmarks count, from 7 of 9 results. A grey row does not count. Too few models took that benchmark.

Sources

BenchLM benchmark aggregationUsed with attribution; per-benchmark results credited to their original authors

More from Sakana AI

Fugu CyberUnrankedSakana Fugu-UltraUnrankedSakana Fugu-Ultra v1.1UnrankedSakana NamazuUnranked