The 5-hour limit has been exceeded, so I have to wait 4 hours. However, it kindly provides guidance … I like this one better because it is user-oriented, offering friendly guidance for beginners and general users.
Fugu Ultra
Sakana AI · Fugu. Released Jun 15, 2026.
Fugu Ultra is a model from Sakana AI in the Fugu family, released Jun 15, 2026. evals.report tracks 7 reported Fugu Ultra benchmark scores across SWE-bench Pro, Terminal-Bench 2.1, Humanity's Last Exam, GPQA Diamond, CharXiv, SciCode, LiveCodeBench — each shown with its benchmark, metric, source status, and date, and never combined into a single ranking.
Benchmark results 7
Compare this model| Benchmark | Category | Score | Metric | Status | Date | |
|---|---|---|---|---|---|---|
| SWE-bench Pro | Coding | 73.7% | % resolved | Verified | Jun 15, 2026 | Details |
| Terminal-Bench 2.1 | Agents | 82.1% | task success | Verified | Jun 15, 2026 | Details |
| Humanity's Last Exam | Reasoning | 50.0% | accuracy | Verified | Jun 15, 2026 | Details |
| GPQA Diamond | Reasoning | 95.5% | accuracy | Verified | Jun 15, 2026 | Details |
| CharXiv | Multimodal | 86.6% | accuracy | Verified | Jun 15, 2026 | Details |
| SciCode | Coding | 58.7% | accuracy | Verified | Jun 15, 2026 | Details |
| LiveCodeBench | Coding | 93.2% | Pass@1 | Verified | Jun 15, 2026 | Details |
In the wild 7
See allReal-world feedback on Fugu Ultra from people using it on actual prompts — praise and criticism alike, each linked to its source. Qualitative, never scored.
Report tone
Report type
Topic
It discovered 27 bugs that Fable 5 couldn't find and fixed all of them. The code quality is impeccable … it implemented about 70,000 lines of new features, resolved 4 issues, and created 7 PRs.
Task Introduced Fugu into a repo previously worked on with Claude Fable 5; ~1 hour of use.
it is incredibly slow: my typical coding tests (shaders, interactive scenes) take 30 minutes to run. And the results are... fine. It does not match Fable in real use.
Task Coding tests (shaders, interactive scenes) on Fugu Ultra-high; each ~30 min.
My First Test with Sakana Fugu Ultra … SVG of Xbox Controller.
Task First test — generating an SVG of an Xbox controller.
The game was pretty bad and notably worse than GPT 5.5. … GPT 5.5 by contrast did a pretty good job and required no follow ups.
Task Asked it to build a Three.js replica of Rocket League via Codex.
In terms of model speed and performance, Fugu on Opencode won … inverted directional turn, wonky camera, no sfx, not identical to Crossy Road game.
Task Head-to-head vs Claude Opus 4.8: a single-file Three.js Crossy Road game.
OMG! Fugu Ultra is ridiculously good at these 3D renders.
Task Generating 3D renders.