Model comparison
Mistral Large 3 vs Sakana Fugu-Ultra
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: Mistral Large 3 #113 (Supported); Sakana Fugu-Ultra unranked (Not scored). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. Mistral Large 3 and Sakana Fugu-Ultra share 0 comparable benchmark results. 0 of 8 categories are comparable. 16 results are unique to Mistral Large 3; 11 to Sakana Fugu-Ultra.
Updated July 23, 2026- Shared results
- 0
- Mistral Large 3 only
- 16
- Sakana Fugu-Ultra only
- 11
- Comparable categories
- 0 / 8
Benchmark data for Mistral Large 3 and Sakana Fugu-Ultra 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 has partial data for these models, but not enough overlapping benchmark coverage to produce a fair score-level comparison yet.
Sakana Fugu-Ultra has the larger context window at 1M, compared with 128K for Mistral Large 3.
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | Mistral Large 3 | Sakana Fugu-Ultra | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | Mistral Large 3$0.5 input / $1.5 output | Sakana Fugu-UltraNot available | A complete price comparison is not available. |
| Generation speedtokens per second | Mistral Large 348 tok/s | Sakana Fugu-UltraNot available | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | Mistral Large 31.04 s | Sakana Fugu-UltraNot available | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | Mistral Large 3128K | Sakana Fugu-Ultra1M | Sakana Fugu-Ultra lists the larger context window. |
Benchmark Deep Dive
Agentic5 benchmarks
Coding7 benchmarks
| Benchmark | Mistral Large 3 | Sakana Fugu-Ultra | Result |
|---|---|---|---|
| AA Coding IndexSource | 20.1% | — | Not comparable |
| AA-SciCodeSource | 36.2% | — | Not comparable |
| SWE-bench ProSource | — | 73.7% | Not comparable |
| Terminal-Bench 2.0Source | — | 82.1% | Not comparable |
| LiveCodeBench v6Source | — | 93.2% | Not comparable |
| LiveCodeBench ProSource | — | 90.8% | Not comparable |
| SciCodeSource | — | 58.7% | Not comparable |
Reasoning3 benchmarks
Knowledge9 benchmarks
| Benchmark | Mistral Large 3 | Sakana Fugu-Ultra | Result |
|---|---|---|---|
| Artificial Analysis Intelligence IndexSource | 15.9% | — | Not comparable |
| AA-GPQA DiamondSource | 68.0% | — | Not comparable |
| AA-HLESource | 4.1% | — | Not comparable |
| AA-Omniscience IndexSource | -39.4% | — | Not comparable |
| AA-Omniscience AccuracySource | 24.1% | — | Not comparable |
| AA-Omniscience Hallucination RateSource | 83.7% | — | Not comparable |
| GPQASource | — | 95.5% | Not comparable |
| GPQA-DSource | — | 95.5% | Not comparable |
| HLE w/o toolsSource | — | 50% | Not comparable |
Multimodal2 benchmarks
Inst. Following1 benchmarks
| Benchmark | Mistral Large 3 | Sakana Fugu-Ultra | Result |
|---|---|---|---|
| AA-IFBenchSource | 36.2% | — | Not comparable |
Frequently Asked Questions (3)
Can I compare Mistral Large 3 and Sakana Fugu-Ultra 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 Mistral Large 3 and Sakana Fugu-Ultra today?
Mistral Large 3: $0.50 input / $1.50 output per 1M tokens Sakana Fugu-Ultra: Pricing unavailable Both model pages still include creator, context window, reasoning mode, and other metadata while benchmark coverage fills in.
Self-host vs API cost
Estimates at 50,000 req/day · 1000 tokens/req average.
Related Comparisons
Explore More
Choose a model with this week’s evidence
Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.
One email each week. Unsubscribe anytime.