Benchmark scores
Higher is better for all benchmark scores (SWE-bench, GPQA, HLE, Terminal-Bench, etc.). Green marks the model with the higher score.
LLM Comparison
Sakana Fugu vs Claude Opus 4.7 (Adaptive): benchmark scores, pricing & comparison.
Side-by-side Sakana Fugu vs Claude Opus 4.7 (Adaptive) comparison across SWE-bench, GPQA, HLE, Terminal-Bench, coding agent scores, token pricing, context window, and AskClash RWT. Green marks the winner on each benchmark.
Rank #7 vs #8AskClash overall scores 81.0 vs 78.5.
Pricing $5.00/$30.0 vs $5.00/$25.0Input and output token prices per 1M tokens when published.
Proprietary vs ProprietarySakana AI vs Anthropic.
Sakana Fugu vs Claude Opus 4.7 (Adaptive) benchmark comparison
Green cells highlight the winning model for each metric. Scores are cached from the AskClash LLM leaderboard snapshot.
| Metric | Sakana Fugu | Claude Opus 4.7 (Adaptive) |
|---|---|---|
| Overall Score | 81.0 | 78.5 |
| Leaderboard Rank | #7 | #8 |
| RWT | — | 8.5 |
| Coding Agent Index | — | 65.0 |
| HLE | 47.2 | 54.7 |
| GPQA | 95.5 | 94.2 |
| SWE-bench | — | 87.6 |
| SWE-Pro | 59.0 | 64.3 |
| Terminal-Bench | 80.2 | 69.4 |
| LiveCodeBench | 92.9 | — |
| OSWorld | — | 78.0 |
| MCP Atlas | — | 77.3 |
| Finance Agent | — | 64.4 |
| CharXiv | 85.1 | 91.0 |
| MMMU-Pro | — | 75.2 |
| ARC-AGI 2 | — | 75.8 |
| Tau2 | — | 88.6 |
| MRCR | 86.6 | — |
| Input Price (per 1M tokens) | $5.00 | $5.00 |
| Output Price (per 1M tokens) | $30.0 | $25.0 |
| Context Window | 1M | 1M |
| Benchmark Cells | 7 | 14 |
More Sakana Fugu and Claude Opus 4.7 (Adaptive) comparisons
Explore how Sakana Fugu and Claude Opus 4.7 (Adaptive) stack up against other top-ranked LLMs.
Claude Mythos Fable 5 vs Sakana FuguClaude Mythos Fable 5 vs Claude Opus 4.7 (Adaptive)Sakana Fugu Ultra vs Sakana FuguSakana Fugu Ultra vs Claude Opus 4.7 (Adaptive)Claude Opus 4.8 vs Sakana FuguClaude Opus 4.8 vs Claude Opus 4.7 (Adaptive)Claude Sonnet 5 vs Sakana FuguClaude Sonnet 5 vs Claude Opus 4.7 (Adaptive)GLM-5.2 vs Sakana FuguGLM-5.2 vs Claude Opus 4.7 (Adaptive)
How to read this comparison
Token pricing
Lower is better for input and output prices. Green marks the cheaper model per 1M tokens.
Coverage matters
Models with fewer disclosed benchmark cells may have inflated percentile scores. Check the benchmark cell count for context.
This comparison page is generated from the AskClash LLM leaderboard cache. Open the live leaderboard for real-time scores and interactive filtering.