Fugu Max: benchmark results

Sakana AI's Fugu Max (v1.0), a multi-agent orchestration system served as a single model through Sakana's OpenAI-compatible API, released September 11, 2026. No downloadable weights. Provider: Other. Released 2026-09-11. Access: API.

Aggregate Rating 1780 ± 46, rank #126 of 10524 rated models, from 21 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Tinybird AI SQL Benchmark - First-Attempt Success Rate100Questions answered with a valid query on the first attempt (94.5
SvelteBench100Average pass@1 (%)93.7
ObviousBench99.31Answer pass³ (%)89.9
Enkrypt AI - Insecure Code Risk8Risk Score84.1
Tinybird AI SQL Benchmark - Exactness52.69Result exactness vs human reference queries (0-100)74.7
Tinybird AI SQL Benchmark - Success Rate100Questions answered with a valid query within 3 retries (%)71.9
LLM Agronomy Benchmark (FBN) - Image Weed72Image Identification Accuracy (%, 50 questions)69.1
Enkrypt AI - Risk Score27.5Risk Score67.6
Enkrypt AI - Bias Risk78.81Risk Score65.2
LLM Agronomy Benchmark (FBN) - V1 Questions86.7Category Accuracy (%)61
LLM Agronomy Benchmark (FBN) - Soil and Water91.2Category Accuracy (%)50
LLM Agronomy Benchmark (FBN) - Image Pest58Image Identification Accuracy (%, 50 questions)48.7

Interactive version: theaggregate.ai/model?slug=fugu-max · How It Works · Data refreshed daily, snapshot 2026-11-22.