Skip to main content

Model comparison

Gemini 2.5 Pro vs Sakana Fugu-Ultra

Data verified

Head-to-head evidence from 1 shared benchmark result across 1 category. Overall scores shown here use the public BenchAlign v5 ranking lane.

57.25/100
No comparison
N/A
0 category wins2 category wins

Public leaderboard positions: Gemini 2.5 Pro #70 (Supported); Sakana Fugu-Ultra unranked (Not scored). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. Gemini 2.5 Pro and Sakana Fugu-Ultra share 1 comparable benchmark result. 2 of 8 categories are comparable. 23 results are unique to Gemini 2.5 Pro; 10 to Sakana Fugu-Ultra.

Updated July 23, 2026
Shared results
1
Gemini 2.5 Pro only
23
Sakana Fugu-Ultra only
10
Comparable categories
2 / 8

Treat this as a split decision. Gemini 2.5 Pro makes more sense if you would rather avoid the extra latency and token burn of a reasoning model; Sakana Fugu-Ultra is the better fit if knowledge is the priority or you want the stronger reasoning-first profile.

Confidence note. This is a partial-evidence comparison with 1 shared benchmark result across 1 evidence category; 2 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.

Why this result

Gemini 2.5 Pro and Sakana Fugu-Ultra finish on the same BenchAlign overall score, so this is less about a single winner and more about where the edge shows up. The BenchAlign headline says tie; the benchmark table is where the real choice happens.

Sakana Fugu-Ultra is the reasoning model in the pair, while Gemini 2.5 Pro is not. That usually helps on harder chain-of-thought-heavy tests, but it can also mean more latency and more token spend in real use.

Category breakdown

Exact category averages are shown below. Not measured means BenchLM does not have enough sourced public coverage for that model and category.

Category scores and score margins for Gemini 2.5 Pro and Sakana Fugu-Ultra
CategoryGemini 2.5 ProΔSakana Fugu-Ultra
KnowledgeGemini 2.5 Pro27.4Margin 68.1Sakana Fugu-Ultra95.5
CodingGemini 2.5 Pro63.8Margin 0.7Sakana Fugu-Ultra64.5
AgenticGemini 2.5 ProNot measuredMarginNo overlapSakana Fugu-Ultra82.1
ReasoningGemini 2.5 ProNot measuredMarginNo overlapSakana Fugu-Ultra93.6
MathGemini 2.5 Pro11.6MarginNo overlapSakana Fugu-UltraNot measured
MultimodalGemini 2.5 ProNot measuredMarginNo overlapSakana Fugu-Ultra86.6

Decisive benchmark drivers

The largest measured benchmark gaps in this matchup, with exact reported values.

More
A · Gemini 2.5 ProB · Sakana Fugu-Ultra
  1. GPQA

    Knowledge
    Source ↗
    A 83%B 95.5%
    Winner: Sakana Fugu-UltraΔ 12.5
    GPQA: Gemini 2.5 Pro scored 83%; Sakana Fugu-Ultra scored 95.5%. Sakana Fugu-Ultra wins this benchmark.

Operational comparison

Runtime and commercial metrics are compared only when both models have a complete sourced value.

MetricGemini 2.5 ProSakana Fugu-UltraComparison
Input / output priceUSD per 1M tokensGemini 2.5 Pro$1.25 input / $10 outputSakana Fugu-UltraNot availableA complete price comparison is not available.
Generation speedtokens per secondGemini 2.5 Pro117 tok/sSakana Fugu-UltraNot availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenGemini 2.5 Pro21.19 sSakana Fugu-UltraNot availableA complete latency comparison is not available.
Context windowmaximum listed tokensGemini 2.5 Pro1MSakana Fugu-Ultra1MListed context windows are equal.

Benchmark Deep Dive

Agentic
BenchmarkGemini 2.5 ProSakana Fugu-UltraResult
AA Agentic IndexSource 7.1%Not comparable
τ²-bench resultsSource 54.1%Not comparable
Gert LabsSource 42.01%Not comparable
GDPval-AASource 8.3%Not comparable
GDPval-AASource 665Not comparable
Terminal-Bench 2.0Source 82.1%Not comparable
CodingSakana Fugu-Ultra wins
BenchmarkGemini 2.5 ProSakana Fugu-UltraResult
SWE-bench VerifiedSource 63.8%Not comparable
Vibe Code BenchSource 0.40%Not comparable
AA Coding IndexSource 33.3%Not comparable
AA-SciCodeSource 42.8%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
Reasoning
BenchmarkGemini 2.5 ProSakana Fugu-UltraResult
AA-LCRSource 66.0%Not comparable
CritPtSource 2.6%Not comparable
MRCRv2Source 93.6%Not comparable
KnowledgeSakana Fugu-Ultra wins
BenchmarkGemini 2.5 ProSakana Fugu-UltraResult
GPQASource 83%95.5%Sakana Fugu-Ultra leads
HLESource 18.8%Not comparable
Artificial Analysis Intelligence IndexSource 25.8%Not comparable
AA-GPQA DiamondSource 84.4%Not comparable
AA-HLESource 21.1%Not comparable
AA-Omniscience IndexSource -14.3%Not comparable
AA-Omniscience AccuracySource 39.0%Not comparable
AA-Omniscience Hallucination RateSource 87.4%Not comparable
GPQA-DSource 95.5%Not comparable
HLE w/o toolsSource 50%Not comparable
Math
BenchmarkGemini 2.5 ProSakana Fugu-UltraResult
FrontierMath v2 (Tiers 1-3)Source 14.138%Not comparable
FrontierMath v2 (Tier 4)Source 4.167%Not comparable
Multimodal
BenchmarkGemini 2.5 ProSakana Fugu-UltraResult
AA-MMMU-ProSource 74.9%Not comparable
Design Arena WebsiteSource 1197Not comparable
CharXivSource 86.6%Not comparable
Inst. Following
BenchmarkGemini 2.5 ProSakana Fugu-UltraResult
AA-IFBenchSource 48.7%Not comparable
Frequently Asked Questions (3)

Which is better, Gemini 2.5 Pro or Sakana Fugu-Ultra?

Gemini 2.5 Pro and Sakana Fugu-Ultra are tied on the BenchAlign overall score, so the right pick depends on which category matters most for your use case.

Which is better for knowledge tasks, Gemini 2.5 Pro or Sakana Fugu-Ultra?

Sakana Fugu-Ultra has the edge for knowledge tasks in this comparison, averaging 95.5 versus 27.4. Inside this category, GPQA is the benchmark that creates the most daylight between them.

Which is better for coding, Gemini 2.5 Pro or Sakana Fugu-Ultra?

Sakana Fugu-Ultra has the edge for coding in this comparison, averaging 64.5 versus 63.8. Gemini 2.5 Pro stays close enough that the answer can still flip depending on your workload.

Related Comparisons

Last updated: July 23, 2026

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.