Claude Opus 5 vs Gemini 4 Hydrogen
Full profiles: Claude Opus 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 and Gemini 4 Hydrogen are neck and neck on quality (64.9 vs 63.4 on the BenchLeader Index, inside the ±2.7 margin), and Gemini 4 Hydrogen is 3.3× cheaper at $3.00 vs $10.00 per 1M tokens blended. Choose Claude Opus 5 for agents & tools (64 vs 62) and maths (70 vs 68); choose Gemini 4 Hydrogen for fast first answers (16.4 s vs 53.0 s) and knowledge (69 vs 65), reasoning (70 vs 66), and coding (69 vs 68), where it also streams ~2× faster.
Key facts (as of 13 Nov 2026)
- Claude Opus 5 scores 64.9 on the BenchLeader Index and Gemini 4 Hydrogen scores 63.4 (BenchLeader, 13 Nov 2026).
- Claude Opus 5 costs $10.00 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 ~2× faster than Claude Opus 5 (Artificial Analysis, 7-day median, 13 Nov 2026).
- Of the 20 benchmarks both models have, Gemini 4 Hydrogen leads 15 (BenchLeader, 13 Nov 2026).
- On Arena WebDev, Claude Opus 5 is rated 1691 and Gemini 4 Hydrogen 1704 (LMArena, as published by 13 Nov 2026).
Claude Opus 5 benchmarks 
Gemini 4 Hydrogen benchmarks 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 case | Pick | Why | Confidence |
|---|---|---|---|
| Coding | Gemini 4 Hydrogen | 69 vs 68 category score; Arena WebDev 1704 vs 1691 | Medium |
| Agents & tool use | Claude Opus 5 | 64 vs 62 category score; Terminal-Bench 52.1% vs 56.4% | Medium |
| Maths | Claude Opus 5 | 70 vs 68 category score; Arena Maths 1515 vs 1495 | Medium |
| Reasoning | Gemini 4 Hydrogen | 70 vs 66 category score; HLE-Diamond (AA) 54.9% vs 44.8% | Medium |
| Knowledge | Gemini 4 Hydrogen | 69 vs 65 category score; AA-Omniscience v1.1 43.7 vs 37.6 | Medium |
| Chat quality (human preference) | Either | 68 vs 68 on Arena votes | Either |
| Lowest cost | Gemini 4 Hydrogen | $3.00 vs $10.00 per 1M blended; agentic coding session $0.120 vs $0.400 | – |
| Fastest first answer | Gemini 4 Hydrogen | 16.4 s (Gemini 4 Hydrogen (high)) vs 53.0 s (Claude Opus 5 (max)) to the first answer token | – |
| High volume on a budget | Neither flagship | A smaller model is usually the better fit: Cheapest good LLMs, Fastest LLMs | – |
Key differences
- Claude Opus 5 (max) and Gemini 4 Hydrogen (high) are neck and neck on quality (64.9 vs 63.4, within the ±2.7 margin).
- Claude Opus 5 (max) is stronger in agents & tools, maths.
- Gemini 4 Hydrogen (high) is stronger in coding, human preference, knowledge, reasoning.
- Gemini 4 Hydrogen (high) is 3.3× cheaper ($3.00 vs $10.00 per 1M blended).
- Gemini 4 Hydrogen (high) streams 2.2× faster (180 vs 82 tokens per second).
At a glance
| Spec | Claude Opus 5 | Gemini 4 Hydrogen |
|---|---|---|
| Developer | Anthropic | |
| Released | 24 Jul 2026 | 12 Nov 2026 |
| Context window (tokens) | 1,000,000 | 1,048,576 |
| Compared at | Claude Opus 5 (max) | Gemini 4 Hydrogen (high) |
| Open weights | No | No |
| Price in / out / cached input per 1M | $5.00 / $25.00 / $0.500 | $1.50 / $7.50 / $0.075 |
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.
| Category | Claude Opus 5 (max) | Gemini 4 Hydrogen (high) | Leader |
|---|---|---|---|
| Reasoning | 66.1 | 69.6 | Gemini 4 Hydrogen |
| Coding | 67.5 | 68.8 | Gemini 4 Hydrogen |
| Agents & tools | 64.0 | 61.9 | Claude Opus 5 |
| Maths | 69.8 | 67.8 | Claude Opus 5 |
| Knowledge | 64.7 | 68.5 | Gemini 4 Hydrogen |
| Human preference | 68.1 | 68.2 | level |
| Multimodal | 67.2 | – | not comparable |
| Long context | 64.3 | – | 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.
Not drawn, measured for fewer than two of these models: Instruction following, Long context, Multimodal.
Where sources disagree
Across the 20 benchmarks both have, Claude Opus 5 leads 5, Gemini 4 Hydrogen leads 15. Every overall index that rates both puts Gemini 4 Hydrogen ahead.
| Overall index | Claude Opus 5 (max) | Gemini 4 Hydrogen (high) | Leader |
|---|---|---|---|
| BenchLeader Index | 64.9 | 63.4 | neck and neck |
| AA Intelligence Index v5.0 | 44.2 | 50.8 | Gemini 4 Hydrogen |
| Arena Text | 1489 | 1490 | Gemini 4 Hydrogen |
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.
| Measure | Claude Opus 5 (max) | Gemini 4 Hydrogen (high) |
|---|---|---|
| Blended price per 1M tokens | $10.00 | $3.00 |
| Input / output per 1M | $5.00 / $25.00 | $1.50 / $7.50 |
| Cached input per 1M | $0.500 | $0.075 |
| Price per task: chat reply | $0.0095 | $0.0029 |
| Price per task: summarize a 30-page report | $0.075 | $0.022 |
| Price per task: code edit | $0.068 | $0.020 |
| Price per task: agentic coding session | $0.400 | $0.120 |
| Price per task: structured extraction | $0.015 | $0.0045 |
| Agentic coding session, input mostly cached | $0.198 | $0.056 |
| Cost per benchmark task (AA Index) | $11.82 | $1.87 |
| Output tokens per task (AA Index) | 118k | 85k |
| Of which reasoning | 73k | 48k |
| Time per task (AA Index) | 24 min | 8 min |
| Output speed | 82 tok/s | 180 tok/s |
| Time to first answer | 53.0 s | 16.4 s |
| Time to a complete answer | 191.6 s | 63.3 s |
Per token is not per task: an average task of Artificial Analysis' Intelligence Index cost $11.82 on Claude Opus 5 (max) and $1.87 on Gemini 4 Hydrogen (high), and Claude Opus 5 (max) wrote 1.4× 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 (max) scores 64.9 and takes 53 s to its first answer token; Claude Opus 5 scores 64.7 in 2 s, Claude Opus 5 (high) scores 64.2 in 18 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
142 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.
| Metric | Publisher | Claude Opus 5 (max) | Gemini 4 Hydrogen (high) |
|---|---|---|---|
| BenchLeader Index | BenchLeader | 64.9 | 63.4 |
| Agents & tools score | BenchLeader | 64.0 | 61.9 |
| Coding score | BenchLeader | 67.5 | 68.8 |
| Human preference score | BenchLeader | 68.1 | 68.2 |
| Knowledge score | BenchLeader | 64.7 | 68.5 |
| Long context score | BenchLeader | 64.3 | – |
| Maths score | BenchLeader | 69.8 | 67.8 |
| Multimodal score | BenchLeader | 67.2 | – |
| Reasoning score | BenchLeader | 66.1 | 69.6 |
| Blended price $/M | BenchLeader | $10.00 | $3.00 |
| Output speed | BenchLeader | 82 tok/s | 180 tok/s |
| Time to first answer | BenchLeader | 53.0 s | 16.4 s |
| Context window | BenchLeader | 1,000,000 tokens | 1,048,576 tokens |
| Reasoning | |||
| GPQA Diamond | Epoch AI Benchmarking Hub | 93.9% | – |
| SimpleBench | SimpleBench | 80.6%† | – |
| Arena Hard Prompts | Arena (LMArena) | 1513 | 1514 |
| LiveBench 2.0 Reasoning | LiveBench | – | 88.6%† |
| LiveBench 1.0 Reasoning | LiveBench | 91.2% | – |
| GPQA Diamond (AA) | Artificial Analysis | 93.2% | – |
| Humanity's Last Exam (AA) | Artificial Analysis | 54.9% | – |
| HLE-Diamond (AA) | Artificial Analysis | 44.8% | 54.9% |
| GPQA Diamond (Vals) | Vals AI | 93.4%† | – |
| ARC-AGI-1 | ARC Prize | 97.5% | – |
| ARC-AGI-2 | ARC Prize | 90.4% | – |
| ARC-AGI-3 | ARC Prize | 30.2%† | – |
| CritPt | Artificial Analysis | 29.1% | – |
| CritPt v2 hard subset (AA) | Artificial Analysis | 50.0% | 61.5% |
| MysteryMechanism | Vals AI | 37.4%† | – |
| Chess Puzzles | Epoch AI Benchmarking Hub | 43.0% | – |
| Mystery Game Puzzles | Epoch AI Benchmarking Hub | 59.0% | – |
| LMCA | Epoch AI Benchmarking Hub | 63.3% | – |
| DTBench | Epoch AI Benchmarking Hub | 97.6% | – |
| ForecastBench | ForecastBench | 66.6% | – |
| BTF-3 | Epoch AI Benchmarking Hub | 12.0%† | – |
| Coding | |||
| SciCode | SciCode | 56.4% | – |
| WeirdML | WeirdML | 91.8% | – |
| FrontierCode | Cognition | 53.4% | – |
| Arena Coding | Arena (LMArena) | 1528 | 1518 |
Show all 142 benchmarks
| Metric | Publisher | Claude Opus 5 (max) | Gemini 4 Hydrogen (high) |
|---|---|---|---|
| Coding | |||
| Arena WebDev | Arena (LMArena) | 1691 | 1704 |
| LiveBench 2.0 Coding | LiveBench | – | 78.5%† |
| LiveBench 1.0 Coding | LiveBench | 81.5% | – |
| LiveCodeBench | Vals AI | 89.0%† | – |
| IOI | Vals AI | 84.3%† | – |
| SWE-bench (Vals) | Vals AI | 97.0%† | – |
| Code Migration | Vals AI | 57.5%† | – |
| ProgramBench | Vals AI | 3.0%† | – |
| Vibe Code Bench 1-100 | Vals AI | 28.5%† | – |
| Vibe Code Bench v1.1 | Vals AI | 88.4%† | 87.8%† |
| SWE Atlas: Codebase QnA | Scale AI SEAL | 63.2%† | – |
| SWE Atlas: Test Writing | Scale AI SEAL | 62.2%† | – |
| MirrorCode | Epoch AI Benchmarking Hub | 87.8% | – |
| DeepSWE v1.1 | Epoch AI Benchmarking Hub | 73.7% | – |
| CursorBench | Cursor | 46.6% | – |
| ALE-Bench | Epoch AI Benchmarking Hub | 2164.6† | – |
| FrontierSWE | Epoch AI Benchmarking Hub | 52.0% | – |
| Terminal-Bench 4.0 (AA) | Artificial Analysis | 49.0% | 54.0% |
| Terminal-Bench 2.1 (AA) | Artificial Analysis | 89.1% | – |
| Startrise Frontend | Startrise | 82.3%† | – |
| GameBench 2 Overall | DuelLab GameBench 2 | 76.6† | – |
| GameBench 2 by reasoning setting | DuelLab GameBench 2 | 84.8† | – |
| Design Arena Website | Design Arena | 1304† | 1316† |
| FrontierCode 2.0 (AA) | Artificial Analysis | 31.1% | 36.3% |
| Agents & tools | |||
| Terminal-Bench | Terminal-Bench | 52.1% | 56.4% |
| OSWorld-Verified 2.0 | OSWorld | 31.4% | – |
| APEX-Agents | Mercor | 65.8% | – |
| Arena Agent | Arena (LMArena) | 7.2 | – |
| LiveBench Long Agentic | LiveBench | – | 61.8%† |
| LiveBench Browser | LiveBench | – | 77.1%† |
| LiveBench Agentic Coding | LiveBench | 65.2% | – |
| Terminal-Bench 2.1 (Vals) | Vals AI | 84.6%† | – |
| MCP Atlas | Scale AI SEAL | 85.8%† | – |
| HiL-Bench | Scale AI SEAL | 57.0%† | – |
| τ³-bench Banking | τ²-bench | 48.7% | – |
| τ³-Banking (AA) | Artificial Analysis | 42.1% | – |
| Analyst Agent (AA) | Artificial Analysis | 53.8% | – |
| CUA-bench | Vals AI | 9.0% | – |
| CyberBench | Vals AI | 65.4%† | – |
| Finance Agent v2 | Vals AI | 58.6%† | – |
| Finance Agent v2.1 | Vals AI | – | 65.1%† |
| Harvey's Legal Agent Benchmark v1.1 | Vals AI | – | 11.3%† |
| Harvey's Legal Agent Benchmark v1 | Vals AI | 6.7%† | – |
| Legal Research Bench | Vals AI | 55.3%† | 53.9%† |
| SkillsBench | Vals AI | 60.4%† | – |
| SREBench | Vals AI | 12.2%† | – |
| Tax Agent Bench | Vals AI | 47.1%† | 52.3%† |
| Terminal-Bench 4.0 (Vals) | Vals AI | 53.5%† | 54.0%† |
| Terminal-Bench Science | Vals AI | 27.1%† | – |
| Time Horizon Index: KSP | Vals AI | 18.8%† | – |
| Arena Search | Arena (LMArena) | 1213† | – |
| BALROG | BALROG | 63.4% | – |
| PostTrainBench | Epoch AI Benchmarking Hub | 35.7%† | – |
| GBAEval | Epoch AI Benchmarking Hub | 79.6%† | – |
| Vending-Bench 2 | Andon Labs | 11181.9† | – |
| AutomationBench | Artificial Analysis | 56.6% | 74.4% |
| GDP.pdf (AA) | Artificial Analysis | 21.6% | 30.0% |
| EnterpriseOps-Gym | Artificial Analysis | 47.5% | – |
| AA-Briefcase v1.1 | Artificial Analysis | 1655 | 1497 |
| Design Arena Agentic | Design Arena | 1264† | – |
| Terminal-Bench-Science 0.1 (AA) | Artificial Analysis | 28.6% | 41.4% |
| DeepSec-Bench (AA) | Artificial Analysis | 25.9% | – |
| Maths | |||
| FrontierMath Tiers 1–3 | Epoch AI Benchmarking Hub | 85.6% | – |
| FrontierMath Tier 4 | Epoch AI Benchmarking Hub | 73.2% | – |
| OTIS Mock AIME | Epoch AI Benchmarking Hub | 98.9% | – |
| ProofBench | Vals AI | 99.0% | – |
| LiveBench Mathematics | LiveBench | 95.7% | – |
| Arena Maths | Arena (LMArena) | 1515 | 1495 |
| Knowledge | |||
| SimpleQA Verified | Epoch AI Benchmarking Hub | 59.9% | – |
| LiveBench 2.0 Data Analysis | LiveBench | – | 83.2%† |
| LiveBench Research | LiveBench | – | 86.8%† |
| LiveBench 1.0 Data Analysis | LiveBench | 74.5% | – |
| AA-Omniscience v1.1 | Artificial Analysis | 37.6 | 43.7 |
| MMLU-Pro | Vals AI | 91.6%† | – |
| LegalBench | Vals AI | 87.0%† | – |
| CorpFin | Vals AI | 73.2%† | – |
| TaxEval | Vals AI | 75.1%† | – |
| BioMysteryBench | Vals AI | 79.3%† | – |
| Excel Modeling Benchmark | Vals AI | 73.6%† | – |
| Excel Modeling Benchmark v1.1 | Vals AI | – | 75.8%† |
| MedCode | Vals AI | 63.6%† | – |
| MedScribe | Vals AI | 91.0%† | – |
| Public Benefits Bench v1.1 | Vals AI | 76.9%† | – |
| DrugDiscoveryBench | Scale AI SEAL | 53.7% | – |
| EBR-bench | Epoch AI Benchmarking Hub | 45.7% | – |
| GDP.pdf | Epoch AI Benchmarking Hub | 24.0% | – |
| AA-Omniscience v1.1: accuracy | Artificial Analysis | 60.9% | 48.2% |
| AA-Omniscience v1.1: non-hallucination | Artificial Analysis | 40.6% | 91.3% |
| Instruction following | |||
| LiveBench Language | LiveBench | 88.7% | – |
| LiveBench Instruction Following | LiveBench | 63.8% | – |
| Arena Instruction Following | Arena (LMArena) | 1494 | 1503 |
| Human preference | |||
| Arena Text | Arena (LMArena) | 1489 | 1490 |
| EQ-Bench 4 | EQ-Bench | 1365† | – |
| Arena Creative Writing | Arena (LMArena) | 1473 | 1492 |
| Arena Multi-turn | Arena (LMArena) | 1486 | 1476 |
| Arena Longer Queries | Arena (LMArena) | 1502 | 1514 |
| Multimodal | |||
| Arena Vision | Arena (LMArena) | 1318† | – |
| LiveBench Design | LiveBench | – | 77.3%† |
| MMMU-Pro | Artificial Analysis | 84.7% | – |
| MMMU-Pro (Vals) | Vals AI | 89.9%† | – |
| MortgageTax | Vals AI | 72.1%† | – |
| Blueprint-Bench 2 | Epoch AI Benchmarking Hub | 30.4%† | – |
| Long context | |||
| AA-LCR v1.1 | Artificial Analysis | 79.3% | – |
| Arena Document | Arena (LMArena) | 1486† | – |
| MLCR | Artificial Analysis | 11.1% | 21.1%† |
| Composite | |||
| Epoch Capabilities Index | Epoch AI Benchmarking Hub | 164.7† | – |
| LiveBench 2.0 | LiveBench | – | 77.0%† |
| LiveBench 1.0 | LiveBench | 80.1% | – |
| AA Intelligence Index v5.0 | Artificial Analysis | 44.2 | 50.8 |
| AA Intelligence Index v4.3.2 | Artificial Analysis | 50.8 | – |
| AA Progress Index v1 | Artificial Analysis | 333.7 | – |
| Vals Index | Vals AI | – | 68.5† |
| Vals Finance Index | Vals AI | – | 66.1%† |
| Vals RSI Index | Vals AI | 33.0% | – |
| Vals Science Index | Vals AI | 47.9%† | – |
| Vals Multimodal Index | Vals AI | 73.9%† | – |
| Safety & honesty | |||
| FORTRESS | Scale AI SEAL | 16.8%† | – |
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 (max): 1 new result (MirrorCode).
- Claude Opus 5 (max): BenchLeader Index 65.5 → 65.0.
- Claude Opus 5 (max): 7 new results (AA Intelligence Index v5.0, HLE-Diamond (AA), AA-Omniscience v1.1…).
- Claude Opus 5 (max): 1 new result (MirrorCode).
- Claude Opus 5 (max): 1 score revision.
- Claude Opus 5 (max): BenchLeader Index 66.3 → 65.5.
- Claude Opus 5 (max): 1 new result (AA Progress Index v1).
- Claude Opus 5 (max): BenchLeader Index 66.8 → 66.3.
- Claude Opus 5 (max): 1 new result (Vals RSI Index).
Related comparisons
- Claude Opus 5 vs Claude Fable 5.2
- Claude Opus 5 vs Gemini 4 Carbon
- Claude Opus 5 vs Claude Opus 5.5
- Gemini 4 Hydrogen vs Claude Fable 5.2
- Gemini 4 Hydrogen vs Gemini 4 Carbon
- Gemini 4 Hydrogen vs Claude Opus 5.5
- Gemini 4 Hydrogen vs GPT-6 Astra
- Claude Fable 5 vs Gemini 4 Hydrogen
Rankings: Best LLM overall · Best LLM for agents · Best cheap LLMs
Claude Opus 5 vs Gemini 4 Hydrogen: questions
- Is Claude Opus 5 better than Gemini 4 Hydrogen?
- Claude Opus 5 (max) and Gemini 4 Hydrogen (high) are neck and neck on quality (64.9 vs 63.4, within the ±2.7 margin). The BenchLeader Index combines every independent quality benchmark; the two are within the margin of error as of 13 Nov 2026, so check the category scores for your use.
- Claude Opus 5 vs Gemini 4 Hydrogen: which is cheaper, and will that change?
- Gemini 4 Hydrogen is cheaper today: $3.00 against $10.00 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
- Is Claude Opus 5 or Gemini 4 Hydrogen better for coding?
- Gemini 4 Hydrogen scores higher in coding (69 vs 68 on the category index, where 50 is average). On Arena WebDev, the top shared coding benchmark, it is 1691 for Claude Opus 5 against 1704 for Gemini 4 Hydrogen.
- Which is faster, Claude Opus 5 or Gemini 4 Hydrogen?
- Gemini 4 Hydrogen streams ~2× faster (180 vs 82 output tokens per second, Artificial Analysis 7-day median).
- Is Claude Opus 5 or Gemini 4 Hydrogen better for agents and tool use?
- Claude Opus 5 scores higher in agentic tasks (64 vs 62 on the category index, where 50 is average). On Terminal-Bench, the top shared agents & tools benchmark, it is 52.1% for Claude Opus 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 1,000,000, Gemini 4 Hydrogen 1,048,576.
- Which has lower latency?
- Gemini 4 Hydrogen answers first: 16.4 s against 53.0 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 vs Gemini 4 Hydrogen?
- Across the 20 benchmarks both have, Claude Opus 5 leads 5, Gemini 4 Hydrogen leads 15. Every overall index that rates both puts Gemini 4 Hydrogen ahead.
- When was Gemini 4 Hydrogen released?
- Gemini 4 Hydrogen was released on 12 Nov 2026.