Gemini 2.5 Pro vs Gemini 4 Hydrogen
Gemini 4 Hydrogen leads Gemini 2.5 Pro on coding, 77.9 to 19.2 on the Vibe Coding Index, and Gemini 4 Hydrogen costs 1.3x less per output token ($7.50 vs $10.00 per million). Updated November 14, 2026; 32 benchmarks have a result for both.
vs boards won of 32 shared
Gemini 2.5 Pro or Gemini 4 Hydrogen: which to pick
Pick Gemini 4 Hydrogen for coding: it scores 77.9 on the Vibe Coding Index against 19.2 for Gemini 2.5 Pro.
Gemini 2.5 Pro is neither cheaper nor larger in context, and leads no benchmark both models were measured on.
Model AGemini 2.5 ProGoogle19.2/1003 independent benchmarks$0.64 per solved taskModel BGemini 4 HydrogenGoogle77.9/1004 independent benchmarksNo cost per solved task
- Shared results
- 32
- Gemini 2.5 Pro only
- 62
- 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 19.2.
3 and 4 benchmarks behind the scores
Agentic work
AA Agentic Index
No call
Only Gemini 2.5 Pro has a AA Agentic Index result, 1.6.
Directional only
Web design
Design Arena: websites
Gemini 4 Hydrogen
Gemini 4 Hydrogen leads, 1320 against 1159.
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
No call
Both take 1.05M tokens.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Gemini 4 Hydrogen
Gemini 2.5 Pro $0.0063, Gemini 4 Hydrogen $0.0053 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only Gemini 2.5 Pro has the number, $0.64.
Directional only
At a glance
- Coding index
- Gemini 2.5 Pro 19.2 from 3 benchmarks, Gemini 4 Hydrogen 77.9 from 4 benchmarks.
- Widest category
- Coding, 48.3 points apart on average over 6 shared benchmarks.
- Widest single gap
- Vibe Code Bench (Vals AI): Gemini 2.5 Pro 0.4% against Gemini 4 Hydrogen 87.8%, 87.4 points apart on a 0 to 100 scale.
- Output price
- Gemini 2.5 Pro $10.00 against Gemini 4 Hydrogen $7.50 per million output tokens, 1.3x apart.
- Context window
- Both take 1.05M tokens.
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 | Gemini 2.5 Pro | 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 | Gemini 2.5 Pro | Gemini 4 Hydrogen | Leader |
|---|---|---|---|
| SWE-bench Verified | 53.6% | Not measured | Only Gemini 2.5 Pro measured |
| LiveBench coding | Not measured | 78.5% | Only Gemini 4 Hydrogen measured |
| LMArena WebDev | 1228 | 1704 | Gemini 4 Hydrogen |
| AA Coding Index | 33.3 | Not measured | Only Gemini 2.5 Pro measured |
| SWE-bench Verified (Vals AI) | 54.4% | Not measured | Only Gemini 2.5 Pro measured |
| Terminal-Bench 4 (Vals AI) | Not measured | 54.0% | Only Gemini 4 Hydrogen measured |
| Vibe Code Bench (Vals AI) | 0.4% | 87.8% | Gemini 4 Hydrogen |
| LiveCodeBench (Artificial Analysis run) | 80.1% | Not measured | Only Gemini 2.5 Pro measured |
| SciCode | 46.3% | Not measured | Only Gemini 2.5 Pro measured |
| Terminal-Bench Hard (Artificial Analysis run) | 26.5% | Not measured | Only Gemini 2.5 Pro measured |
| Terminal-Bench 4.0 (Artificial Analysis run) | 0.0% | 54.0% | Gemini 4 Hydrogen |
| FrontierCode 2.0 | Not measured | 39.0% | Only Gemini 4 Hydrogen measured |
| Terminal-Bench | 32.6% | Not measured | Only Gemini 2.5 Pro measured |
| GSO-Bench | 3.9% | Not measured | Only Gemini 2.5 Pro measured |
| WeirdML | 54.0% | Not measured | Only Gemini 2.5 Pro measured |
| LMArena Text: coding | 1451 | 1516 | Gemini 4 Hydrogen |
| LMArena Text: software and IT | 1459 | 1513 | Gemini 4 Hydrogen |
| LMArena WebDev: React | Not measured | 1724 | Only Gemini 4 Hydrogen measured |
| LMArena WebDev: HTML | 1236 | 1743 | Gemini 4 Hydrogen |
| LMArena WebDev: from an image | 1285 | Not measured | Only Gemini 2.5 Pro measured |
| Terminal-Bench 2.0 | 32.6% | Not measured | Only Gemini 2.5 Pro measured |
| CursorBench 4.0 | Not measured | 57.8% | Only Gemini 4 Hydrogen measured |
| Neither model has a result on the other 30 boards here | |||
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
| Benchmark | Gemini 2.5 Pro | Gemini 4 Hydrogen | Leader |
|---|---|---|---|
| Epoch Capabilities Index | 144.9 | Not measured | Only Gemini 2.5 Pro measured |
| Neither model has a result on the other 1 board here | |||
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index14 boards, none shared
| Benchmark | Gemini 2.5 Pro | Gemini 4 Hydrogen | Leader |
|---|---|---|---|
| AA Agentic Index | 1.6 | Not measured | Only Gemini 2.5 Pro 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 |
| τ²-Bench Telecom | 54.1% | Not measured | Only Gemini 2.5 Pro measured |
| GDPval | 23.3% | Not measured | Only Gemini 2.5 Pro measured |
| DeepResearch Bench | 41.5% | Not measured | Only Gemini 2.5 Pro measured |
| Vending-Bench 2 | $574 | Not measured | Only Gemini 2.5 Pro measured |
| LMArena Search | 1143 | Not measured | Only Gemini 2.5 Pro measured |
| BrowseComp-Plus | 29.5% | Not measured | Only Gemini 2.5 Pro measured |
| τ³-Banking | 13.7% | Not measured | Only Gemini 2.5 Pro measured |
| Neither model has a result on the other 30 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index03
| Benchmark | Gemini 2.5 Pro | Gemini 4 Hydrogen | Leader |
|---|---|---|---|
| LiveBench reasoning | Not measured | 88.6% | Only Gemini 4 Hydrogen measured |
| GPQA Diamond (Artificial Analysis run) | 84.4% | Not measured | Only Gemini 2.5 Pro measured |
| Humanity's Last Exam (Artificial Analysis run) | 22.5% | Not measured | Only Gemini 2.5 Pro 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) | 85.3% | Not measured | Only Gemini 2.5 Pro measured |
| ARC-AGI | 41.0% | Not measured | Only Gemini 2.5 Pro measured |
| ARC-AGI-2 | 4.9% | Not measured | Only Gemini 2.5 Pro measured |
| LMArena Text: hard prompts | 1455 | 1520 | Gemini 4 Hydrogen |
| LMArena Text: expert | 1452 | 1558 | Gemini 4 Hydrogen |
| LMArena Text: hard prompts in English | 1452 | 1514 | Gemini 4 Hydrogen |
| LMArena Vision: diagrams | 1273 | Not measured | Only Gemini 2.5 Pro measured |
| LMArena Vision: homework | 1282 | Not measured | Only Gemini 2.5 Pro measured |
| Kagi LLM Benchmark | 70.3% | Not measured | Only Gemini 2.5 Pro measured |
| Neither model has a result on the other 12 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | Gemini 2.5 Pro | Gemini 4 Hydrogen | Leader |
|---|---|---|---|
| AIME 2025 (Artificial Analysis run) | 87.7% | Not measured | Only Gemini 2.5 Pro measured |
| OTIS Mock AIME | 84.7% | Not measured | Only Gemini 2.5 Pro measured |
| FrontierMath, tiers 1 to 3 | 24.6% | Not measured | Only Gemini 2.5 Pro measured |
| FrontierMath, tier 4 | 0.0% | Not measured | Only Gemini 2.5 Pro measured |
| LMArena Text: math | 1450 | 1507 | Gemini 4 Hydrogen |
| LMArena Text: mathematical work | 1455 | 1534 | Gemini 4 Hydrogen |
| MathArena | 13.3% | Not measured | Only Gemini 2.5 Pro measured |
| Neither model has a result on the other 7 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index04
| Benchmark | Gemini 2.5 Pro | Gemini 4 Hydrogen | Leader |
|---|---|---|---|
| CaseLaw (Vals AI) | 63.9% | Not measured | Only Gemini 2.5 Pro measured |
| CorpFin (Vals AI) | 60.8% | Not measured | Only Gemini 2.5 Pro measured |
| MortgageTax (Vals AI) | 68.9% | Not measured | Only Gemini 2.5 Pro measured |
| MedCode (Vals AI) | 50.6% | Not measured | Only Gemini 2.5 Pro measured |
| MMLU Pro (Artificial Analysis run) | 86.2% | Not measured | Only Gemini 2.5 Pro measured |
| AA-Omniscience | Not measured | 46.3 | Only Gemini 4 Hydrogen measured |
| LMArena Text: science | 1481 | 1519 | Gemini 4 Hydrogen |
| LMArena Text: medicine and healthcare | 1476 | 1488 | Gemini 4 Hydrogen |
| LMArena Text: legal and government | 1480 | 1532 | Gemini 4 Hydrogen |
| LMArena Text: business and finance | 1440 | 1486 | Gemini 4 Hydrogen |
| PRBench Finance | 38.9% | Not measured | Only Gemini 2.5 Pro measured |
| PRBench Legal | 41.4% | Not measured | Only Gemini 2.5 Pro measured |
| Neither model has a result on the other 9 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index04
| Benchmark | Gemini 2.5 Pro | Gemini 4 Hydrogen | Leader |
|---|---|---|---|
| Design Arena: websites | 1159 | 1320 | Gemini 4 Hydrogen |
| Design Arena: UI components | 1130 | Not measured | Only Gemini 2.5 Pro measured |
| Design Arena: game dev | 1101 | 1369 | Gemini 4 Hydrogen |
| Design Arena: data viz | 1219 | Not measured | Only Gemini 2.5 Pro measured |
| Design Arena: 3D | 1060 | 1415 | Gemini 4 Hydrogen |
| Design Arena: all code categories | 1142 | 1333 | Gemini 4 Hydrogen |
| LiveBench design | Not measured | 77.3% | Only Gemini 4 Hydrogen measured |
| Neither model has a result on the other 2 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index013
| Benchmark | Gemini 2.5 Pro | 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) | 73.5% | Not measured | Only Gemini 2.5 Pro measured |
| IFBench | 48.7% | Not measured | Only Gemini 2.5 Pro measured |
| Long context reasoning (AA-LCR) | 69.0% | Not measured | Only Gemini 2.5 Pro measured |
| GDPval-AA | 463 | Not measured | Only Gemini 2.5 Pro measured |
| DTBench | 82.4% | Not measured | Only Gemini 2.5 Pro measured |
| LMCA | 34.8% | Not measured | Only Gemini 2.5 Pro measured |
| LMArena Text | 1458 | 1502 | Gemini 4 Hydrogen |
| LMArena Text: instruction following | 1437 | 1519 | Gemini 4 Hydrogen |
| LMArena Text: creative writing | 1454 | 1509 | Gemini 4 Hydrogen |
| LMArena Vision | 1263 | Not measured | Only Gemini 2.5 Pro measured |
| LMArena Text: English | 1458 | 1499 | Gemini 4 Hydrogen |
| LMArena Text: non-English | 1452 | 1495 | Gemini 4 Hydrogen |
| LMArena Text: Chinese | 1507 | 1631 | Gemini 4 Hydrogen |
| LMArena Text: German | 1487 | Not measured | Only Gemini 2.5 Pro measured |
| LMArena Text: Japanese | 1461 | Not measured | Only Gemini 2.5 Pro measured |
| LMArena Text: Korean | 1434 | Not measured | Only Gemini 2.5 Pro measured |
| LMArena Text: French | 1474 | 1512 | Gemini 4 Hydrogen |
| LMArena Text: Spanish | 1474 | 1494 | Gemini 4 Hydrogen |
| LMArena Text: Russian | 1461 | 1492 | Gemini 4 Hydrogen |
| LMArena Text: Polish | 1479 | Not measured | Only Gemini 2.5 Pro measured |
| LMArena Text: multi-turn | 1452 | 1485 | Gemini 4 Hydrogen |
| LMArena Text: longer queries | 1449 | 1524 | Gemini 4 Hydrogen |
| LMArena Text: writing and language | 1454 | 1500 | Gemini 4 Hydrogen |
| LMArena Text: entertainment and media | 1441 | 1503 | Gemini 4 Hydrogen |
| LMArena Vision: English | 1261 | Not measured | Only Gemini 2.5 Pro measured |
| LMArena Vision: Chinese | 1300 | Not measured | Only Gemini 2.5 Pro measured |
| LMArena Vision: reading text | 1270 | Not measured | Only Gemini 2.5 Pro measured |
| LMArena Vision: humor | 1262 | Not measured | Only Gemini 2.5 Pro measured |
| LMArena Vision: captioning | 1304 | Not measured | Only Gemini 2.5 Pro measured |
| LMArena Vision: recognizing things | 1284 | Not measured | Only Gemini 2.5 Pro measured |
| LMArena Vision: creative writing | 1265 | Not measured | Only Gemini 2.5 Pro measured |
| LMArena Document | 1423 | Not measured | Only Gemini 2.5 Pro measured |
| MultiChallenge | 53.6% | Not measured | Only Gemini 2.5 Pro measured |
| Neither model has a result on the other 14 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Gemini 2.5 Pro | 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 2.5 Pro$0.0063Fits in one request
Gemini 4 Hydrogen$0.0053Fits in one request
Gemini 4 Hydrogen costs less
Repository review
50K input + 3K output tokens
Gemini 2.5 Pro$0.092Fits in one request
Gemini 4 Hydrogen$0.098Fits in one request
Gemini 2.5 Pro costs less
Agent loop
200K input + 10K output tokens
Gemini 2.5 Pro$0.350Fits in one request
Gemini 4 Hydrogen$0.375Fits in one request
Gemini 2.5 Pro 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 | Google Gemini 2.5 Pro | Google Gemini 4 Hydrogen |
|---|---|---|
| Maker | ||
| Weights | No public weights listed | No public weights listed |
| Released | June 17, 2025 | November 12, 2026 |
| Context window | 1.05M | 1.05M |
| Input $/Mtok | $1.25 | $1.50 |
| Output $/Mtok | $10.00 | $7.50 |
| Coding index | 19.2 | 77.9 |
| Independent measurements behind it | 3 | 4 |
| Cost per solved task | $0.64 | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Gemini 2.5 Pro better than Gemini 4 Hydrogen for coding?
Pick Gemini 4 Hydrogen for coding: it scores 77.9 on the Vibe Coding Index against 19.2 for Gemini 2.5 Pro. Gemini 2.5 Pro is neither cheaper nor larger in context, and leads no benchmark both models were measured on.
Which is cheaper, Gemini 2.5 Pro or Gemini 4 Hydrogen?
Gemini 2.5 Pro costs $1.25 per million input tokens and $10.00 per million output tokens; Gemini 4 Hydrogen costs $1.50 and $7.50. Cost per solved task is known for Gemini 2.5 Pro only.
Which has the bigger context window, Gemini 2.5 Pro or Gemini 4 Hydrogen?
Neither: both take 1.05M tokens.
How many benchmarks is the Gemini 2.5 Pro vs Gemini 4 Hydrogen comparison based on?
32 benchmarks have a result for both models as of November 14, 2026. Gemini 2.5 Pro'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.