BenchLeader
Menu

Claude Opus 5.5 vs Gemini 4 Hydrogen

Full profiles: Claude Opus 5.5 (Anthropic) and Gemini 4 Hydrogen (Google): every benchmark, price and rank.

Updated · Data from 12 sources

As of 13 Nov 2026, Claude Opus 5.5 is ahead of Gemini 4 Hydrogen on quality (68.4 vs 63.4 on the BenchLeader Index), but Gemini 4 Hydrogen is 2.7× cheaper at $3.00 vs $8.00 per 1M tokens blended. Claude Opus 5.5 leads in every category we measure both in. Gemini 4 Hydrogen streams ~1.5× faster.

Key facts (as of 13 Nov 2026)

  • Claude Opus 5.5 scores 68.4 on the BenchLeader Index and Gemini 4 Hydrogen scores 63.4 (BenchLeader, 13 Nov 2026).
  • Claude Opus 5.5 costs $8.00 per 1M tokens blended (list price, 13 Nov 2026).
  • Gemini 4 Hydrogen costs $3.00 per 1M tokens blended (list price, 13 Nov 2026).
  • Gemini 4 Hydrogen streams ~1.5× faster than Claude Opus 5.5 (Artificial Analysis, 7-day median, 13 Nov 2026).
  • Of the 13 benchmarks both models have, Claude Opus 5.5 leads 10 (BenchLeader, 13 Nov 2026).
  • On Arena WebDev, Claude Opus 5.5 is rated 1815 and Gemini 4 Hydrogen 1704 (LMArena, as published by 13 Nov 2026).
Claude Opus 5.5 benchmarks max Anthropic Gemini 4 Hydrogen benchmarks high GoogleAdd a third model

Which to pick for…

The pick's numbers come first. Category scores on the BenchLeader scale (50 is the average model, 15 points one standard deviation). High confidence means a lead of half a standard deviation or more; under one point is called either.

Use casePickWhyConfidence
CodingClaude Opus 5.580 vs 69 category score; Arena WebDev 1815 vs 1704High
Agents & tool useEither62 vs 62 category score; Terminal-Bench 65.8% vs 56.4%Either
MathsClaude Opus 5.573 vs 68 category scoreMedium
ReasoningClaude Opus 5.572 vs 70 category score; HLE-Diamond (AA) 67.9% vs 54.9%Medium
KnowledgeClaude Opus 5.573 vs 69 category score; AA-Omniscience v1.1 48.1 vs 43.7Medium
Chat quality (human preference)–Only Gemini 4 Hydrogen has an Arena rating (68 category score)Not comparable
Lowest costGemini 4 Hydrogen$3.00 vs $8.00 per 1M blended; agentic coding session $0.120 vs $0.320–
Fastest first answerGemini 4 Hydrogen16.4 s (Gemini 4 Hydrogen (high)) vs 347.9 s (Claude Opus 5.5 (max)) to the first answer token–
High volume on a budgetNeither flagshipA smaller model is usually the better fit: Cheapest good LLMs, Fastest LLMs–

Key differences

  • Claude Opus 5.5 (max) leads on quality: 68.4 vs 63.4.
  • Claude Opus 5.5 (max) is stronger in coding, knowledge, maths, reasoning.
  • Gemini 4 Hydrogen (high) is stronger in agents & tools.
  • Gemini 4 Hydrogen (high) is 2.7× cheaper ($3.00 vs $8.00 per 1M blended).
  • Gemini 4 Hydrogen (high) streams 1.6× faster (180 vs 115 tokens per second).

At a glance

SpecClaude Opus 5.5Gemini 4 Hydrogen
DeveloperAnthropicGoogle
Released22 Sep 202612 Nov 2026
Context window (tokens)1,000,0001,048,576
Max output (tokens)128,000 (up to 300K on the Message Batches API (beta))–
Input typestext, image–
Reasoning effort settingslow, medium, high, xhigh, max–
Compared atClaude Opus 5.5 (max)Gemini 4 Hydrogen (high)
Open weightsNoNo
Price in / out / cached input per 1M$4.00 / $20.00 / $0.200$1.50 / $7.50 / $0.075
API model IDclaude-opus-5-5–
Where to use itClaude API, Amazon Bedrock, Google Cloud, Microsoft Foundry–

Limits, availability and announced prices from the vendors' own pages: platform.claude.com (checked 20 Oct 2026). Everything else is from the day's data.

Category by category

Category scores on the BenchLeader scale: 50 is the average evaluated model, 15 points is one standard deviation. A gap under one point is called level.

CategoryClaude Opus 5.5 (max)Gemini 4 Hydrogen (high)Leader
Reasoning72.069.6Claude Opus 5.5
Coding79.868.8Claude Opus 5.5
Agents & tools61.861.9level
Maths73.267.8Claude Opus 5.5
Knowledge72.568.5Claude Opus 5.5
Human preference–68.2not comparable
Multimodal70.2–not comparable
Long context67.1–not comparable

On one chart

Each domain on the index's own scale, where 50 is an average model. Click a domain to see the benchmarks behind it. Pick up to 5 models from the list.

2550 avg75ReasoningCodingAgents & toolsMathsKnowledgeClaude Opus 5.5, Reasoning: 72.0Claude Opus 5.5, Coding: 79.8Claude Opus 5.5, Agents & tools: 61.8Claude Opus 5.5, Maths: 73.2Claude Opus 5.5, Knowledge: 72.5Gemini 4 Hydrogen, Reasoning: 69.6Gemini 4 Hydrogen, Coding: 68.8Gemini 4 Hydrogen, Agents & tools: 61.9Gemini 4 Hydrogen, Maths: 67.8Gemini 4 Hydrogen, Knowledge: 68.5

Not drawn, measured for fewer than two of these models: Instruction following, Long context, Multimodal, Human preference.

Model, click to add or removeIndex

Where sources disagree

Across the 13 benchmarks both have, Claude Opus 5.5 leads 10, Gemini 4 Hydrogen leads 3. Every overall index that rates both puts Claude Opus 5.5 ahead.

Overall indexClaude Opus 5.5 (max)Gemini 4 Hydrogen (high)Leader
BenchLeader Index68.463.4Claude Opus 5.5
AA Intelligence Index v5.059.150.8Claude Opus 5.5
Vals Index70.1†68.5Claude Opus 5.5
Arena Text1507†1490Claude Opus 5.5

Each publisher runs its own tasks, harnesses and effort settings, so their overall verdicts can differ; BenchLeader reconciles them on one scale. † measured at another effort setting of the same model (the publisher did not test the one compared here).

Price, speed and latency

List prices blended at three input tokens per output token. Per-task prices use the token counts on the methodology page. Cost, tokens and time per benchmark task are measured: Artificial Analysis’ averages over its whole Intelligence Index run.

MeasureClaude Opus 5.5 (max)Gemini 4 Hydrogen (high)
Blended price per 1M tokens$8.00$3.00
Input / output per 1M$4.00 / $20.00$1.50 / $7.50
Cached input per 1M$0.200$0.075
Price per task: chat reply$0.0076$0.0029
Price per task: summarize a 30-page report$0.060$0.022
Price per task: code edit$0.054$0.020
Price per task: agentic coding session$0.320$0.120
Price per task: structured extraction$0.012$0.0045
Agentic coding session, input mostly cached$0.149$0.056
Cost per benchmark task (AA Index)$10.04$1.87
Output tokens per task (AA Index)173k85k
Of which reasoning120k48k
Time per task (AA Index)25 min8 min
Output speed115 tok/s180 tok/s
Time to first answer347.9 s16.4 s
Time to a complete answer711.4 s63.3 s

Per token is not per task: an average task of Artificial Analysis' Intelligence Index cost $10.04 on Claude Opus 5.5 (max) and $1.87 on Gemini 4 Hydrogen (high), and Claude Opus 5.5 (max) wrote 2.0× as many output tokens for the same work, which a per-token price hides.

Each model is compared at its best-ranked reasoning-effort setting. Claude Opus 5.5 (max) scores 68.4 and takes 348 s to its first answer token; Claude Opus 5.5 (xhigh) scores 65.4 in 79 s, Claude Opus 5.5 (high) scores 65.3 in 25 s. Gemini 4 Hydrogen (high) scores 63.4 and takes 16 s to its first answer token. Higher effort means more thinking before the answer: better scores, longer waits and more tokens billed. How reasoning effort changes scores and cost.

Every benchmark

136 benchmarks, grouped by category; each name links to the board and its leaders. † measured at another effort setting of the same model, shown for reference and not counted as a win.

MetricPublisherClaude Opus 5.5 (max)Gemini 4 Hydrogen (high)
BenchLeader IndexBenchLeader68.463.4
Agents & tools scoreBenchLeader61.861.9
Coding scoreBenchLeader79.868.8
Knowledge scoreBenchLeader72.568.5
Long context scoreBenchLeader67.1–
Maths scoreBenchLeader73.267.8
Multimodal scoreBenchLeader70.2–
Reasoning scoreBenchLeader72.069.6
Human preference scoreBenchLeader–68.2
Blended price $/MBenchLeader$8.00$3.00
Output speedBenchLeader115 tok/s180 tok/s
Time to first answerBenchLeader347.9 s16.4 s
Context windowBenchLeader1,000,000 tokens1,048,576 tokens
Reasoning
GPQA DiamondEpoch AI Benchmarking Hub90.6%–
SimpleBenchSimpleBench88.4%†–
Arena Hard PromptsArena (LMArena)1530†1514
LiveBench 2.0 ReasoningLiveBench92.2%†88.6%†
LiveBench 1.0 ReasoningLiveBench92.2%–
Humanity's Last Exam (AA)Artificial Analysis61.4%–
HLE-Diamond (AA)Artificial Analysis67.9%54.9%
ARC-AGI-1ARC Prize97.5%–
ARC-AGI-2ARC Prize91.7%–
CritPtArtificial Analysis31.7%–
CritPt v2 hard subset (AA)Artificial Analysis68.0%61.5%
MysteryMechanismVals AI49.5%†–
Chess PuzzlesEpoch AI Benchmarking Hub67.0%–
Mystery Game PuzzlesEpoch AI Benchmarking Hub71.0%–
LMCAEpoch AI Benchmarking Hub68.2%–
DTBenchEpoch AI Benchmarking Hub98.9%–
Coding
SciCodeSciCode66.9%–
FrontierCodeCognition54.6%†–
Arena CodingArena (LMArena)1548†1518
Arena WebDevArena (LMArena)18151704
LiveBench 2.0 CodingLiveBench87.1%†78.5%†
LiveBench 1.0 CodingLiveBench89.3%–
IOIVals AI95.1%†–
Code MigrationVals AI66.7%†–
Code Migration v1.1Vals AI81.0%†–
Show all 136 benchmarks
MetricPublisherClaude Opus 5.5 (max)Gemini 4 Hydrogen (high)
Coding
ProgramBenchVals AI18.5%†–
SWE-bench MultimodalVals AI70.2%†–
Vibe Code Bench 1-100Vals AI30.4%†–
Vibe Code Bench v1.1Vals AI90.3%†87.8%†
MirrorCodeEpoch AI Benchmarking Hub95.6%–
CursorBenchCursor57.8%–
ALE-BenchEpoch AI Benchmarking Hub2147.4†–
FrontierSWEEpoch AI Benchmarking Hub62.3%–
Terminal-Bench 4.0 (AA)Artificial Analysis59.6%54.0%
Startrise FrontendStartrise71.1%†–
GameBench 2 OverallDuelLab GameBench 287.6†–
GameBench 2 by reasoning settingDuelLab GameBench 294.9†–
Design Arena WebsiteDesign Arena1326†1316†
FrontierCode 1.1 (AA)Artificial Analysis52.2%–
FrontierCode 2.0 (AA)Artificial Analysis46.4%36.3%
Agents & tools
Terminal-BenchTerminal-Bench65.8%56.4%
Remote Labor IndexScale AI / CAIS21.3%†–
APEX-AgentsMercor73.5%–
Arena AgentArena (LMArena)19.5–
LiveBench Long AgenticLiveBench72.8%†61.8%†
LiveBench BrowserLiveBench88.4%†77.1%†
LiveBench Agentic CodingLiveBench71.7%–
Terminal-Bench 2.1 (Vals)Vals AI87.6%†–
MCP AtlasScale AI SEAL85.4%†–
HiL-BenchScale AI SEAL59.0%†–
GDPval-AA v2.1, normalised scoreArtificial Analysis68.3%–
GDPval-AA v2.1Artificial Analysis1866–
ITBench SRE (AA)Artificial Analysis38.2%–
Analyst Agent (AA)Artificial Analysis56.3%–
CUA-benchVals AI14.0%–
CyberBenchVals AI55.4%†–
Finance Agent v2Vals AI58.6%†–
Finance Agent v2.1Vals AI67.8%†65.1%†
Harvey's Legal Agent Benchmark v1.1Vals AI9.2%†11.3%†
Harvey's Legal Agent Benchmark v1Vals AI3.8%†–
Legal Research BenchVals AI50.5%†53.9%†
Robo-benchVals AI14.6%–
SREBenchVals AI33.6%†–
Tax Agent BenchVals AI44.5%†52.3%†
Terminal-Bench 4.0 (Vals)Vals AI65.2%†54.0%†
Terminal-Bench ScienceVals AI47.1%†–
Time Horizon Index: KSPVals AI91.3%†–
Web Search IndexVals AI53.8%†–
Arena SearchArena (LMArena)1213†–
PostTrainBenchEpoch AI Benchmarking Hub43.8%–
Vending-Bench 2Andon Labs9235.3†–
AutomationBenchArtificial Analysis69.5%74.4%
GDP.pdf (AA)Artificial Analysis26.2%30.0%
Harvey LAB-AA v1.1Harvey4.2%–
AA-Briefcase v1.1Artificial Analysis18011497
GDPxGDPx by SemiAnalysis12.0%–
Design Arena AgenticDesign Arena1332†–
Terminal-Bench-Science 0.1 (AA)Artificial Analysis59.0%41.4%
CWE-Bench (AA)Artificial Analysis58.3%–
DeepSec-Bench (AA)Artificial Analysis26.9%–
CyberGym end-to-end (AA)Artificial Analysis0.8%–
FACTS SearchGoogle88.4%†–
Maths
FrontierMath Tiers 1–3Epoch AI Benchmarking Hub91.2%–
FrontierMath Tier 4Epoch AI Benchmarking Hub95.0%–
OTIS Mock AIMEEpoch AI Benchmarking Hub100.0%–
ProofBenchVals AI100.0%–
LiveBench MathematicsLiveBench97.1%–
Arena MathsArena (LMArena)1514†1495
Knowledge
SimpleQA VerifiedEpoch AI Benchmarking Hub72.2%–
LiveBench 2.0 Data AnalysisLiveBench80.3%†83.2%†
LiveBench ResearchLiveBench88.9%†86.8%†
LiveBench 1.0 Data AnalysisLiveBench80.3%–
AA-Omniscience v1.1Artificial Analysis48.143.7
PRBench LegalScale AI SEAL47.6%†–
BioMysteryBenchVals AI79.3%†–
ClaimBenchVals AI100.0%†–
Excel Modeling BenchmarkVals AI75.9%†–
Excel Modeling Benchmark v1.1Vals AI75.8%†75.8%†
MedCodeVals AI49.8%†–
MedScribeVals AI91.4%†–
Public Benefits Bench v1.1Vals AI70.6%†–
EBR-benchEpoch AI Benchmarking Hub71.4%–
GDP.pdfEpoch AI Benchmarking Hub30.6%–
AA-Omniscience v1.1: accuracyArtificial Analysis65.5%48.2%
AA-Omniscience v1.1: non-hallucinationArtificial Analysis49.7%91.3%
HealthBench Professional (AA)OpenAI59.9%–
Instruction following
LiveBench LanguageLiveBench86.3%–
LiveBench Instruction FollowingLiveBench65.7%–
Arena Instruction FollowingArena (LMArena)1518†1503
Human preference
Arena TextArena (LMArena)1507†1490
EQ-Bench 4EQ-Bench1340†–
Arena Creative WritingArena (LMArena)1517†1492
Arena Multi-turnArena (LMArena)1502†1476
Arena Longer QueriesArena (LMArena)1520†1514
Multimodal
Arena VisionArena (LMArena)1324†–
LiveBench DesignLiveBench83.3%†77.3%†
MMMU-ProArtificial Analysis87.7%–
SAGEVals AI91.3%†–
Blueprint-Bench 2Epoch AI Benchmarking Hub51.2%†–
Code2Video-AAArtificial Analysis1536–
AA-3DArtificial Analysis1202–
Long context
AA-LCR v1.1Artificial Analysis84.7%–
MLCRArtificial Analysis27.8%21.1%†
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub168.5†–
LiveBench 2.0LiveBench83.4%†77.0%†
LiveBench 1.0LiveBench83.2%–
AA Intelligence Index v5.0Artificial Analysis59.150.8
AA Intelligence Index v4.3.2Artificial Analysis57.6–
AA Progress Index v1Artificial Analysis350–
Vals IndexVals AI70.1†68.5†
Vals Finance IndexVals AI65.3%†66.1%†
Vals RSI IndexVals AI37.3%–
Vals Science IndexVals AI58.6%†–
Vals Router IndexVals AI64.2%†–
AA Cyber IndexArtificial Analysis28.7–
Safety & honesty
FORTRESSScale AI SEAL5.8%–

Data as of 2026-11-13. Best configuration of each model; every score links to its source on the model pages.

DuelLab GameBench 2, release gb2-20261110-2acac640a228 (https://benchmarks.duellab.org/releases/gb2-20261110-2acac640a228/), CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Scores mapped to BenchLeader model names; not endorsed by DuelLab.

What changed

  • Gemini 4 Hydrogen (high): 10 new results (Arena Text, Arena Hard Prompts, Arena Coding…).
  • Claude Opus 5.5 (max): 1 new result (PostTrainBench); 1 score revision.
  • Claude Opus 5.5 (max): 1 new result (MirrorCode); 1 score revision.
  • Claude Opus 5.5 (max): BenchLeader Index 69.3 → 68.8.
  • Claude Opus 5.5 (max): 2 score revisions.
  • Claude Opus 5.5 (max): 1 score revision.
  • Claude Opus 5.5 (max): 1 score revision.
  • Claude Opus 5.5 (max): 2 score revisions.
  • Claude Opus 5.5 (max): 2 score revisions.
  • Claude Opus 5.5 (max): 1 score revision.

Rankings: Best LLM overall · Best LLM for coding · Best LLM for agents · Best cheap LLMs

Claude Opus 5.5 vs Gemini 4 Hydrogen: questions

Is Claude Opus 5.5 better than Gemini 4 Hydrogen?
Claude Opus 5.5 (max) leads on quality: 68.4 vs 63.4. The BenchLeader Index combines every independent quality benchmark; Claude Opus 5.5 (max) is ahead overall as of 13 Nov 2026, but check the category scores for your use.
Claude Opus 5.5 vs Gemini 4 Hydrogen: which is cheaper, and will that change?
Gemini 4 Hydrogen is cheaper today: $3.00 against $8.00 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
Is Claude Opus 5.5 or Gemini 4 Hydrogen better for coding?
Claude Opus 5.5 scores higher in coding (80 vs 69 on the category index, where 50 is average). On Arena WebDev, the top shared coding benchmark, it is 1815 for Claude Opus 5.5 against 1704 for Gemini 4 Hydrogen.
Which is faster, Claude Opus 5.5 or Gemini 4 Hydrogen?
Gemini 4 Hydrogen streams ~1.5× faster (180 vs 115 output tokens per second, Artificial Analysis 7-day median).
Is Claude Opus 5.5 or Gemini 4 Hydrogen better for agents and tool use?
They are level in agentic tasks (62 vs 62 on the category index). On Terminal-Bench, the top shared agents & tools benchmark, it is 65.8% for Claude Opus 5.5 against 56.4% for Gemini 4 Hydrogen.
More questions (4)
Which is better for long documents?
Both take about 1M tokens: Claude Opus 5.5 1,000,000, Gemini 4 Hydrogen 1,048,576.
Which has lower latency?
Gemini 4 Hydrogen answers first: 16.4 s against 347.9 s to the first answer token, as Artificial Analysis measures it. Reasoning effort drives most of this: a higher setting thinks longer before it answers.
Do independent benchmarks agree on Claude Opus 5.5 vs Gemini 4 Hydrogen?
Across the 13 benchmarks both have, Claude Opus 5.5 leads 10, Gemini 4 Hydrogen leads 3. Every overall index that rates both puts Claude Opus 5.5 ahead.
When was Gemini 4 Hydrogen released?
Gemini 4 Hydrogen was released on 12 Nov 2026.