Model comparison
Llama 3.1 405B vs Sakana Fugu-Ultra v1.1
Head-to-head evidence from 0 shared benchmark results across 0 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
Public leaderboard positions: Llama 3.1 405B #107 (Estimated); Sakana Fugu-Ultra v1.1 unranked (Not scored). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. Llama 3.1 405B and Sakana Fugu-Ultra v1.1 share 0 comparable benchmark results. 0 of 8 categories are comparable. 11 results are unique to Llama 3.1 405B; 0 to Sakana Fugu-Ultra v1.1.
Updated July 24, 2026- Shared results
- 0
- Llama 3.1 405B only
- 11
- Sakana Fugu-Ultra v1.1 only
- 0
- Comparable categories
- 0 / 8
Benchmark data for Llama 3.1 405B and Sakana Fugu-Ultra v1.1 is coming soon on BenchLM.
Confidence note. This is a partial-evidence comparison with 0 shared benchmark results across 0 evidence categories; 0 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.
Why this result
BenchLM does not have sourced benchmark coverage for Sakana Fugu-Ultra v1.1 yet. This comparison is currently limited to metadata such as context window, reasoning mode, and pricing where available.
Sakana Fugu-Ultra v1.1 is priced at $5.00 input / $30.00 output per 1M tokens, versus $0.00 input / $0.00 output per 1M tokens for Llama 3.1 405B. Sakana Fugu-Ultra v1.1 has the larger context window at 1M, compared with 128K for Llama 3.1 405B.
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | Llama 3.1 405B | Sakana Fugu-Ultra v1.1 | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | Llama 3.1 405B$0 input / $0 output | Sakana Fugu-Ultra v1.1$5 input / $30 output | Llama 3.1 405B has the lower combined listed price. |
| Generation speedtokens per second | Llama 3.1 405B29 tok/s | Sakana Fugu-Ultra v1.1Not available | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | Llama 3.1 405B2.19 s | Sakana Fugu-Ultra v1.1Not available | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | Llama 3.1 405B128K | Sakana Fugu-Ultra v1.11M | Sakana Fugu-Ultra v1.1 lists the larger context window. |
Benchmark Deep Dive
Agentic1 benchmarks
| Benchmark | Llama 3.1 405B | Sakana Fugu-Ultra v1.1 | Result |
|---|---|---|---|
| τ²-bench resultsSource | 19% | — | Not comparable |
Coding1 benchmarks
| Benchmark | Llama 3.1 405B | Sakana Fugu-Ultra v1.1 | Result |
|---|---|---|---|
| AA-SciCodeSource | 29.9% | — | Not comparable |
Reasoning2 benchmarks
Knowledge6 benchmarks
| Benchmark | Llama 3.1 405B | Sakana Fugu-Ultra v1.1 | Result |
|---|---|---|---|
| Artificial Analysis Intelligence IndexSource | 8.5% | — | Not comparable |
| AA-GPQA DiamondSource | 51.5% | — | Not comparable |
| AA-HLESource | 4.2% | — | Not comparable |
| AA-Omniscience IndexSource | -17.3% | — | Not comparable |
| AA-Omniscience AccuracySource | 22.3% | — | Not comparable |
| AA-Omniscience Hallucination RateSource | 51.0% | — | Not comparable |
Inst. Following1 benchmarks
| Benchmark | Llama 3.1 405B | Sakana Fugu-Ultra v1.1 | Result |
|---|---|---|---|
| AA-IFBenchSource | 39.0% | — | Not comparable |
Frequently Asked Questions (3)
Can I compare Llama 3.1 405B and Sakana Fugu-Ultra v1.1 on BenchLM yet?
Not fully yet. BenchLM is tracking both models, but the sourced benchmark breakdown for this comparison is still coming soon.
Why does this comparison show “coming soon”?
BenchLM only shows category winners and benchmark-level calls when we have sourced results that can be compared fairly. For these models, the public benchmark coverage is not complete enough yet.
What data is available for Llama 3.1 405B and Sakana Fugu-Ultra v1.1 today?
Llama 3.1 405B: $0.00 input / $0.00 output per 1M tokens Sakana Fugu-Ultra v1.1: $5.00 input / $30.00 output per 1M tokens Both model pages still include creator, context window, reasoning mode, and other metadata while benchmark coverage fills in.