Claude Sonnet 4.5 vs Gemini 4 Hydrogen
Gemini 4 Hydrogen leads Claude Sonnet 4.5 on coding, 77.9 to 39.5 on the Vibe Coding Index, and Gemini 4 Hydrogen costs 2.0x less per output token ($7.50 vs $15.00 per million). Updated November 14, 2026; 32 benchmarks have a result for both.
Claude Sonnet 4.5 or Gemini 4 Hydrogen: which to pick
Pick Gemini 4 Hydrogen for coding: it scores 77.9 on the Vibe Coding Index against 39.5 for Claude Sonnet 4.5.
Claude Sonnet 4.5 is neither cheaper nor larger in context, and leads no benchmark both models were measured on.
- Shared results
- 32
- Claude Sonnet 4.5 only
- 68
- Gemini 4 Hydrogen only
- 18
- Like-for-like categories
- 6 of 9
Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.
Which one for your work
Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.
Coding
Vibe Coding Index, six public coding benchmarks
Gemini 4 Hydrogen
Gemini 4 Hydrogen scores 77.9 against 39.5.
3 and 4 benchmarks behind the scores
Agentic work
AA Agentic Index
No call
Only Claude Sonnet 4.5 has a AA Agentic Index result, 15.8.
Directional only
Reasoning
GPQA Diamond
No call
Only Claude Sonnet 4.5 has a GPQA Diamond result, 81.6%.
Directional only
Math
AIME
No call
Only Claude Sonnet 4.5 has a AIME result, 88.2%.
Directional only
Knowledge
MMLU Pro
No call
Only Claude Sonnet 4.5 has a MMLU Pro result, 87.4%.
Directional only
Web design
Design Arena: websites
Gemini 4 Hydrogen
Gemini 4 Hydrogen leads, 1320 against 1181.
Same board, both measured
General
Vals Index
No call
Only Gemini 4 Hydrogen has a Vals Index result, 68.5%.
Directional only
Long documents
Listed context window
Gemini 4 Hydrogen
Gemini 4 Hydrogen takes 1.05M tokens against 1M.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Gemini 4 Hydrogen
Claude Sonnet 4.5 $0.011, Gemini 4 Hydrogen $0.0053 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only Claude Sonnet 4.5 has the number, $1.16.
Directional only
At a glance
- Coding index
- Claude Sonnet 4.5 39.5 from 3 benchmarks, Gemini 4 Hydrogen 77.9 from 4 benchmarks.
- Widest category
- Coding, 31.7 points apart on average over 6 shared benchmarks.
- Widest single gap
- Vibe Code Bench (Vals AI): Claude Sonnet 4.5 22.6% against Gemini 4 Hydrogen 87.8%, 65.2 points apart on a 0 to 100 scale.
- Output price
- Claude Sonnet 4.5 $15.00 against Gemini 4 Hydrogen $7.50 per million output tokens, 2.0x apart.
- Context window
- Claude Sonnet 4.5 takes 1M tokens, Gemini 4 Hydrogen 1.05M.
Benchmark by benchmark
First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.
| Category | Claude Sonnet 4.5 | Bars | Gemini 4 Hydrogen | Ties |
|---|---|---|---|---|
| Coding | 0 | 6 | ||
| Reasoning | 0 | 3 | ||
| Math | 0 | 2 | ||
| Knowledge | 0 | 4 | ||
| Web design | 0 | 4 | ||
| General | 0 | 13 | ||
| All shared boards | 0 | 32 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index06
| Benchmark | Claude Sonnet 4.5 | Gemini 4 Hydrogen | Leader |
|---|---|---|---|
| SWE-bench Verified | 74.8% | Not measured | Only Claude Sonnet 4.5 measured |
| SWE-bench Multilingual | 67.0% | Not measured | Only Claude Sonnet 4.5 measured |
| LiveBench coding | Not measured | 78.5% | Only Gemini 4 Hydrogen measured |
| LMArena WebDev | 1393 | 1704 | Gemini 4 Hydrogen |
| AA Coding Index | 52.1 | Not measured | Only Claude Sonnet 4.5 measured |
| LiveCodeBench (Vals AI) | 73.0% | Not measured | Only Claude Sonnet 4.5 measured |
| SWE-bench Verified (Vals AI) | 70.0% | Not measured | Only Claude Sonnet 4.5 measured |
| Terminal-Bench 4 (Vals AI) | Not measured | 54.0% | Only Gemini 4 Hydrogen measured |
| Vibe Code Bench (Vals AI) | 22.6% | 87.8% | Gemini 4 Hydrogen |
| Terminal-Bench 4.0 (Artificial Analysis run) | Not measured | 54.0% | Only Gemini 4 Hydrogen measured |
| FrontierCode 2.0 | Not measured | 39.0% | Only Gemini 4 Hydrogen measured |
| Terminal-Bench | 46.5% | Not measured | Only Claude Sonnet 4.5 measured |
| GSO-Bench | 14.7% | Not measured | Only Claude Sonnet 4.5 measured |
| WeirdML | 47.7% | Not measured | Only Claude Sonnet 4.5 measured |
| Cybench | 60.0% | Not measured | Only Claude Sonnet 4.5 measured |
| LMArena Text: coding | 1488 | 1516 | Gemini 4 Hydrogen |
| LMArena Text: software and IT | 1473 | 1513 | Gemini 4 Hydrogen |
| LMArena WebDev: React | 1386 | 1724 | Gemini 4 Hydrogen |
| LMArena WebDev: HTML | 1398 | 1743 | Gemini 4 Hydrogen |
| Terminal-Bench 2.0 | 46.5% | Not measured | Only Claude Sonnet 4.5 measured |
| CursorBench 4.0 | Not measured | 57.8% | Only Gemini 4 Hydrogen measured |
| Neither model has a result on the other 31 boards here | |||
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
| Benchmark | Claude Sonnet 4.5 | Gemini 4 Hydrogen | Leader |
|---|---|---|---|
| Epoch Capabilities Index | 147.6 | Not measured | Only Claude Sonnet 4.5 measured |
| Neither model has a result on the other 1 board here | |||
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index19 boards, none shared
| Benchmark | Claude Sonnet 4.5 | Gemini 4 Hydrogen | Leader |
|---|---|---|---|
| AA Agentic Index | 15.8 | Not measured | Only Claude Sonnet 4.5 measured |
| Design Arena: agents building web apps | 1036 | Not measured | Only Claude Sonnet 4.5 measured |
| Design Arena: agents building full-stack apps | 1024 | Not measured | Only Claude Sonnet 4.5 measured |
| Design Arena: agents building mobile apps | 1130 | Not measured | Only Claude Sonnet 4.5 measured |
| LiveBench research | Not measured | 86.8% | Only Gemini 4 Hydrogen measured |
| LiveBench browser | Not measured | 77.1% | Only Gemini 4 Hydrogen measured |
| LiveBench long agentic | Not measured | 61.8% | Only Gemini 4 Hydrogen measured |
| Tax Agent Bench (Vals AI) | Not measured | 52.3% | Only Gemini 4 Hydrogen measured |
| Legal Research Bench (Vals AI) | Not measured | 53.8% | Only Gemini 4 Hydrogen measured |
| Harvey's Legal Agent Benchmark (Vals AI) | Not measured | 11.3% | Only Gemini 4 Hydrogen measured |
| METR time horizons | 67.4% | Not measured | Only Claude Sonnet 4.5 measured |
| Remote Labor Index | 2.1% | Not measured | Only Claude Sonnet 4.5 measured |
| GDPval | 42.5% | Not measured | Only Claude Sonnet 4.5 measured |
| DeepResearch Bench | 52.6% | Not measured | Only Claude Sonnet 4.5 measured |
| OSWorld | 62.9% | Not measured | Only Claude Sonnet 4.5 measured |
| Vending-Bench 2 | $3,839 | Not measured | Only Claude Sonnet 4.5 measured |
| LMArena Search | 1159 | Not measured | Only Claude Sonnet 4.5 measured |
| Berkeley Function Calling Leaderboard (BFCL) | 73.2% | Not measured | Only Claude Sonnet 4.5 measured |
| MCP Atlas | 59.5% | Not measured | Only Claude Sonnet 4.5 measured |
| Neither model has a result on the other 25 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index03
| Benchmark | Claude Sonnet 4.5 | Gemini 4 Hydrogen | Leader |
|---|---|---|---|
| GPQA Diamond | 81.6% | Not measured | Only Claude Sonnet 4.5 measured |
| LiveBench reasoning | Not measured | 88.6% | Only Gemini 4 Hydrogen measured |
| MMMU Pro (Vals AI) | 79.3% | Not measured | Only Claude Sonnet 4.5 measured |
| HLE-Diamond (Artificial Analysis run) | Not measured | 58.8% | Only Gemini 4 Hydrogen measured |
| CritPt v2, hard subset (Artificial Analysis run) | Not measured | 66.0% | Only Gemini 4 Hydrogen measured |
| GPQA Diamond (Epoch AI run) | 82.3% | Not measured | Only Claude Sonnet 4.5 measured |
| ARC-AGI | 63.7% | Not measured | Only Claude Sonnet 4.5 measured |
| ARC-AGI-2 | 13.6% | Not measured | Only Claude Sonnet 4.5 measured |
| SimpleBench | 54.3% | Not measured | Only Claude Sonnet 4.5 measured |
| Chess puzzles | 10.0% | Not measured | Only Claude Sonnet 4.5 measured |
| Mystery game puzzles | 17.0% | Not measured | Only Claude Sonnet 4.5 measured |
| EBR-bench | 2.4% | Not measured | Only Claude Sonnet 4.5 measured |
| VPCT | 39.8% | Not measured | Only Claude Sonnet 4.5 measured |
| LMArena Text: hard prompts | 1462 | 1520 | Gemini 4 Hydrogen |
| LMArena Text: expert | 1483 | 1558 | Gemini 4 Hydrogen |
| LMArena Text: hard prompts in English | 1471 | 1514 | Gemini 4 Hydrogen |
| Kagi LLM Benchmark | 57.9% | Not measured | Only Claude Sonnet 4.5 measured |
| Neither model has a result on the other 9 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | Claude Sonnet 4.5 | Gemini 4 Hydrogen | Leader |
|---|---|---|---|
| AIME | 88.2% | Not measured | Only Claude Sonnet 4.5 measured |
| MGSM (Vals AI) | 94.3% | Not measured | Only Claude Sonnet 4.5 measured |
| OTIS Mock AIME | 77.8% | Not measured | Only Claude Sonnet 4.5 measured |
| FrontierMath, tiers 1 to 3 | 23.9% | Not measured | Only Claude Sonnet 4.5 measured |
| FrontierMath, tier 4 | 2.4% | Not measured | Only Claude Sonnet 4.5 measured |
| ProofBench | 19.0% | Not measured | Only Claude Sonnet 4.5 measured |
| MATH level 5 | 97.7% | Not measured | Only Claude Sonnet 4.5 measured |
| LMArena Text: math | 1449 | 1507 | Gemini 4 Hydrogen |
| LMArena Text: mathematical work | 1463 | 1534 | Gemini 4 Hydrogen |
| MathArena | 13.2% | Not measured | Only Claude Sonnet 4.5 measured |
| Neither model has a result on the other 4 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index04
| Benchmark | Claude Sonnet 4.5 | Gemini 4 Hydrogen | Leader |
|---|---|---|---|
| MMLU Pro | 87.4% | Not measured | Only Claude Sonnet 4.5 measured |
| LegalBench (Vals AI) | 84.1% | Not measured | Only Claude Sonnet 4.5 measured |
| CaseLaw (Vals AI) | 62.2% | Not measured | Only Claude Sonnet 4.5 measured |
| CorpFin (Vals AI) | 62.0% | Not measured | Only Claude Sonnet 4.5 measured |
| TaxEval (Vals AI) | 73.3% | Not measured | Only Claude Sonnet 4.5 measured |
| MortgageTax (Vals AI) | 64.0% | Not measured | Only Claude Sonnet 4.5 measured |
| MedQA (Vals AI) | 94.7% | Not measured | Only Claude Sonnet 4.5 measured |
| MedCode (Vals AI) | 44.1% | Not measured | Only Claude Sonnet 4.5 measured |
| AA-Omniscience | Not measured | 46.3 | Only Gemini 4 Hydrogen measured |
| SimpleQA Verified | 30.7% | Not measured | Only Claude Sonnet 4.5 measured |
| GeoBench | 60.0% | Not measured | Only Claude Sonnet 4.5 measured |
| LMArena Text: science | 1447 | 1519 | Gemini 4 Hydrogen |
| LMArena Text: medicine and healthcare | 1443 | 1488 | Gemini 4 Hydrogen |
| LMArena Text: legal and government | 1450 | 1532 | Gemini 4 Hydrogen |
| LMArena Text: business and finance | 1440 | 1486 | Gemini 4 Hydrogen |
| PRBench Finance | 43.8% | Not measured | Only Claude Sonnet 4.5 measured |
| PRBench Legal | 40.8% | Not measured | Only Claude Sonnet 4.5 measured |
| Neither model has a result on the other 4 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index04
| Benchmark | Claude Sonnet 4.5 | Gemini 4 Hydrogen | Leader |
|---|---|---|---|
| Design Arena: websites | 1181 | 1320 | Gemini 4 Hydrogen |
| Design Arena: UI components | 1162 | Not measured | Only Claude Sonnet 4.5 measured |
| Design Arena: game dev | 1155 | 1369 | Gemini 4 Hydrogen |
| Design Arena: data viz | 1164 | Not measured | Only Claude Sonnet 4.5 measured |
| Design Arena: 3D | 1137 | 1415 | Gemini 4 Hydrogen |
| Design Arena: all code categories | 1172 | 1333 | Gemini 4 Hydrogen |
| Design Arena: SVG | 1104 | Not measured | Only Claude Sonnet 4.5 measured |
| Design Arena: ASCII art | 1200 | Not measured | Only Claude Sonnet 4.5 measured |
| LiveBench design | Not measured | 77.3% | Only Gemini 4 Hydrogen measured |
GeneralLike-for-likePublic boards, shown as published, kept out of the index013
| Benchmark | Claude Sonnet 4.5 | Gemini 4 Hydrogen | Leader |
|---|---|---|---|
| Vals Index | Not measured | 68.5% | Only Gemini 4 Hydrogen measured |
| LiveBench data analysis | Not measured | 83.2% | Only Gemini 4 Hydrogen measured |
| MedScribe (Vals AI) | 84.5% | Not measured | Only Claude Sonnet 4.5 measured |
| DTBench | 83.2% | Not measured | Only Claude Sonnet 4.5 measured |
| LMCA | 38.8% | Not measured | Only Claude Sonnet 4.5 measured |
| LMArena Text | 1439 | 1502 | Gemini 4 Hydrogen |
| LMArena Text: instruction following | 1459 | 1519 | Gemini 4 Hydrogen |
| LMArena Text: creative writing | 1442 | 1509 | Gemini 4 Hydrogen |
| LMArena Text: English | 1450 | 1499 | Gemini 4 Hydrogen |
| LMArena Text: non-English | 1425 | 1495 | Gemini 4 Hydrogen |
| LMArena Text: Chinese | 1461 | 1631 | Gemini 4 Hydrogen |
| LMArena Text: German | 1427 | Not measured | Only Claude Sonnet 4.5 measured |
| LMArena Text: Japanese | 1389 | Not measured | Only Claude Sonnet 4.5 measured |
| LMArena Text: Korean | 1400 | Not measured | Only Claude Sonnet 4.5 measured |
| LMArena Text: French | 1459 | 1512 | Gemini 4 Hydrogen |
| LMArena Text: Spanish | 1457 | 1494 | Gemini 4 Hydrogen |
| LMArena Text: Russian | 1437 | 1492 | Gemini 4 Hydrogen |
| LMArena Text: Polish | 1423 | Not measured | Only Claude Sonnet 4.5 measured |
| LMArena Text: multi-turn | 1465 | 1485 | Gemini 4 Hydrogen |
| LMArena Text: longer queries | 1476 | 1524 | Gemini 4 Hydrogen |
| LMArena Text: writing and language | 1442 | 1500 | Gemini 4 Hydrogen |
| LMArena Text: entertainment and media | 1429 | 1503 | Gemini 4 Hydrogen |
| LMArena Document | 1449 | Not measured | Only Claude Sonnet 4.5 measured |
| MultiChallenge | 55.3% | Not measured | Only Claude Sonnet 4.5 measured |
| Neither model has a result on the other 25 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Claude Sonnet 4.5 | Gemini 4 Hydrogen | Leader |
|---|---|---|---|
| Neither model has a result on 5 boards here | |||
What each workload costs
Three fixed token mixes at each model's listed price, so per-token rates become a bill.
Chat turn
1K input + 500 output tokens
Gemini 4 Hydrogen costs less
Repository review
50K input + 3K output tokens
Gemini 4 Hydrogen costs less
Agent loop
200K input + 10K output tokens
Gemini 4 Hydrogen costs less
Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.
Specification differences
The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.
| Specification | Anthropic Claude Sonnet 4.5 | Google Gemini 4 Hydrogen |
|---|---|---|
| Maker | Anthropic | |
| Weights | No public weights listed | No public weights listed |
| Released | September 29, 2025 | November 12, 2026 |
| Context window | 1M | 1.05M |
| Input $/Mtok | $3.00 | $1.50 |
| Output $/Mtok | $15.00 | $7.50 |
| Coding index | 39.5 | 77.9 |
| Independent measurements behind it | 3 | 4 |
| Cost per solved task | $1.16 | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Claude Sonnet 4.5 better than Gemini 4 Hydrogen for coding?
Pick Gemini 4 Hydrogen for coding: it scores 77.9 on the Vibe Coding Index against 39.5 for Claude Sonnet 4.5. Claude Sonnet 4.5 is neither cheaper nor larger in context, and leads no benchmark both models were measured on.
Which is cheaper, Claude Sonnet 4.5 or Gemini 4 Hydrogen?
Claude Sonnet 4.5 costs $3.00 per million input tokens and $15.00 per million output tokens; Gemini 4 Hydrogen costs $1.50 and $7.50. Cost per solved task is known for Claude Sonnet 4.5 only.
Which has the bigger context window, Claude Sonnet 4.5 or Gemini 4 Hydrogen?
Gemini 4 Hydrogen, with 1.05M tokens against 1M.
How many benchmarks is the Claude Sonnet 4.5 vs Gemini 4 Hydrogen comparison based on?
32 benchmarks have a result for both models as of November 14, 2026. Claude Sonnet 4.5's coding index rests on 3 independent benchmarks and Gemini 4 Hydrogen's on 4. Where only one model has a result, the page says so instead of naming a winner.