Gemini 4 Argon vs Gemini 4 Hydrogen
Full profiles: Gemini 4 Argon (Google) and Gemini 4 Hydrogen (Google): every benchmark, price and rank.
Updated · Data from 11 sources
As of 13 Nov 2026, Gemini 4 Argon and Gemini 4 Hydrogen are neck and neck on quality (65.3 vs 63.4 on the BenchLeader Index, inside the ±3.3 margin), and Gemini 4 Hydrogen is 1.3× cheaper at $3.00 vs $4.00 per 1M tokens blended. Choose 4 Argon for human preference (72 vs 68), knowledge (72 vs 69), and maths (70 vs 68); choose 4 Hydrogen for fast first answers (16.4 s vs 42.7 s) and agents & tools (62 vs 56) and coding (69 vs 67), where it also streams ~2× faster. Gemini 4 Argon's current price runs until 30 Nov 2026, then $8.00.
Key facts (as of 13 Nov 2026)
- Gemini 4 Argon scores 65.3 on the BenchLeader Index and Gemini 4 Hydrogen scores 63.4 (BenchLeader, 13 Nov 2026).
- Gemini 4 Argon costs $4.00 per 1M tokens blended until 30 Nov 2026, then $8.00 (https://ai.google.dev/gemini-api/docs/pricing, checked 20 Oct 2026).
- Gemini 4 Hydrogen costs $3.00 per 1M tokens blended (list price, 13 Nov 2026).
- Gemini 4 Hydrogen streams ~2× faster than Gemini 4 Argon (Artificial Analysis, 7-day median, 13 Nov 2026).
- Of the 19 benchmarks both models have, Gemini 4 Argon leads 14 (BenchLeader, 13 Nov 2026).
- On Arena WebDev, Gemini 4 Argon is rated 1681 and Gemini 4 Hydrogen 1704 (LMArena, as published by 13 Nov 2026).
Gemini 4 Argon 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 67 category score; Arena WebDev 1704 vs 1681 | Medium |
| Agents & tool use | Gemini 4 Hydrogen | 62 vs 56 category score; GDP.pdf (AA) 30.0% vs 21.8% | Medium |
| Maths | Gemini 4 Argon | 70 vs 68 category score; Arena Maths 1536 vs 1495 | Medium |
| Reasoning | Either | 70 vs 70 category score; HLE-Diamond (AA) 56.7% vs 54.9% | Either |
| Knowledge | Gemini 4 Argon | 72 vs 69 category score; AA-Omniscience v1.1 46.1 vs 43.7 | Medium |
| Chat quality (human preference) | Gemini 4 Argon | 72 vs 68 on Arena votes | Medium |
| Lowest cost | Gemini 4 Hydrogen | $3.00 vs $4.00 per 1M blended; agentic coding session $0.120 vs $0.160; from 1 Dec 2026: $3.00 vs $8.00 | – |
| Fastest first answer | Gemini 4 Hydrogen | 16.4 s (Gemini 4 Hydrogen (high)) vs 42.7 s (Gemini 4 Argon (high)) 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
- Gemini 4 Argon (high) and Gemini 4 Hydrogen (high) are neck and neck on quality (65.3 vs 63.4, within the ±3.3 margin).
- Gemini 4 Argon (high) is stronger in human preference, knowledge, maths.
- Gemini 4 Hydrogen (high) is stronger in agents & tools, coding, reasoning.
- Gemini 4 Hydrogen (high) is 1.3× cheaper ($3.00 vs $4.00 per 1M blended) until 30 Nov 2026, then $3.00 vs $8.00 from 1 Dec 2026.
- Gemini 4 Hydrogen (high) streams 2.8× faster (180 vs 64 tokens per second).
At a glance
| Spec | Gemini 4 Argon | Gemini 4 Hydrogen |
|---|---|---|
| Developer | ||
| Released | 30 Sep 2026 | 12 Nov 2026 |
| Generally available | 13 Oct 2026 | 12 Nov 2026 |
| Context window (tokens) | 1,048,576 | 1,048,576 |
| Max output (tokens) | 65,536 (up to 1,048,576 with long decode) | – |
| Input types | text, image, video, audio, PDF | – |
| Reasoning effort settings | low, medium, high | – |
| Compared at | Gemini 4 Argon (high) | Gemini 4 Hydrogen (high) |
| Open weights | No | No |
| Price in / out / cached input per 1M | $2.00 / $10.00 / $0.100 | $1.50 / $7.50 / $0.075 |
| Announced price change | $4.00 / $20.00 / $0.200 from 1 Dec 2026 | None announced |
| API model ID | gemini-4-argon | – |
| Where to use it | Gemini API (AI Studio), Gemini Enterprise Agent Platform, Gemini app | – |
Limits, availability and announced prices from the vendors' own pages: ai.google.dev, ai.google.dev pricing (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.
| Category | Gemini 4 Argon (high) | Gemini 4 Hydrogen (high) | Leader |
|---|---|---|---|
| Reasoning | 69.5 | 69.6 | level |
| Coding | 66.7 | 68.8 | Gemini 4 Hydrogen |
| Agents & tools | 56.3 | 61.9 | Gemini 4 Hydrogen |
| Maths | 69.9 | 67.8 | Gemini 4 Argon |
| Knowledge | 71.9 | 68.5 | Gemini 4 Argon |
| Human preference | 72.1 | 68.2 | Gemini 4 Argon |
| Long context | 64.5 | – | 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 19 benchmarks both have, Gemini 4 Argon leads 14, Gemini 4 Hydrogen leads 5. Independent sources split: Gemini 4 Argon leads on Vals Index and Arena Text; Gemini 4 Hydrogen leads on AA Intelligence Index v5.0.
| Overall index | Gemini 4 Argon (high) | Gemini 4 Hydrogen (high) | Leader |
|---|---|---|---|
| BenchLeader Index | 65.3 | 63.4 | neck and neck |
| AA Intelligence Index v5.0 | 50.4 | 50.8 | Gemini 4 Hydrogen |
| Vals Index | 69.4 | 68.5† | Gemini 4 Argon |
| Arena Text | 1522 | 1490 | Gemini 4 Argon |
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 | Gemini 4 Argon (high) | Gemini 4 Hydrogen (high) |
|---|---|---|
| Blended price per 1M tokens, until 30 Nov 2026 | $4.00 | $3.00 |
| Input / output per 1M | $2.00 / $10.00 | $1.50 / $7.50 |
| Blended price per 1M from 1 Dec 2026 | $8.00 | $3.00 |
| Input / output per 1M from 1 Dec 2026 | $4.00 / $20.00 | $1.50 / $7.50 |
| Cached input per 1M | $0.100 | $0.075 |
| Price per task: chat reply | $0.0038 | $0.0029 |
| Price per task: summarize a 30-page report | $0.030 | $0.022 |
| Price per task: code edit | $0.027 | $0.020 |
| Price per task: agentic coding session | $0.160 | $0.120 |
| Price per task: structured extraction | $0.0060 | $0.0045 |
| Agentic coding session, input mostly cached | $0.074 | $0.056 |
| Cost per benchmark task (AA Index) | $4.97 | $1.87 |
| Output tokens per task (AA Index) | 116k | 85k |
| Of which reasoning | 68k | 48k |
| Time per task (AA Index) | 30 min | 8 min |
| Output speed | 64 tok/s | 180 tok/s |
| Time to first answer | 42.7 s | 16.4 s |
| Time to a complete answer | 122.1 s | 63.3 s |
Per token is not per task: an average task of Artificial Analysis' Intelligence Index cost $4.97 on Gemini 4 Argon (high) and $1.87 on Gemini 4 Hydrogen (high), and Gemini 4 Argon (high) 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. Gemini 4 Argon (high) scores 65.3 and takes 43 s to its first answer token; Gemini 4 Argon scores 64.3 in 5 s, Gemini 4 Argon (medium) scores 61.6 in 5 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
125 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 | Gemini 4 Argon (high) | Gemini 4 Hydrogen (high) |
|---|---|---|---|
| BenchLeader Index | BenchLeader | 65.3 | 63.4 |
| Agents & tools score | BenchLeader | 56.3 | 61.9 |
| Coding score | BenchLeader | 66.7 | 68.8 |
| Human preference score | BenchLeader | 72.1 | 68.2 |
| Knowledge score | BenchLeader | 71.9 | 68.5 |
| Long context score | BenchLeader | 64.5 | – |
| Maths score | BenchLeader | 69.9 | 67.8 |
| Reasoning score | BenchLeader | 69.5 | 69.6 |
| Blended price $/M | BenchLeader | $4.00 | $3.00 |
| Output speed | BenchLeader | 64 tok/s | 180 tok/s |
| Time to first answer | BenchLeader | 42.7 s | 16.4 s |
| Context window | BenchLeader | 1,048,576 tokens | 1,048,576 tokens |
| Reasoning | |||
| GPQA Diamond | Epoch AI Benchmarking Hub | 96.4% | – |
| SimpleBench | SimpleBench | 91.7%† | – |
| Arena Hard Prompts | Arena (LMArena) | 1545 | 1514 |
| LiveBench 2.0 Reasoning | LiveBench | 95.1%† | 88.6%† |
| Humanity's Last Exam (AA) | Artificial Analysis | 57.1% | – |
| HLE-Diamond (AA) | Artificial Analysis | 56.7% | 54.9% |
| ARC-AGI-1 | ARC Prize | 98.5% | – |
| ARC-AGI-2 | ARC Prize | 91.3% | – |
| ARC-AGI-3 | ARC Prize | 97.3% | – |
| CritPt | Artificial Analysis | 27.1% | – |
| CritPt v2 hard subset (AA) | Artificial Analysis | 52.5% | 61.5% |
| MysteryMechanism | Vals AI | 45.5% | – |
| Chess Puzzles | Epoch AI Benchmarking Hub | 59.0% | – |
| Mystery Game Puzzles | Epoch AI Benchmarking Hub | 64.0% | – |
| LMCA | Epoch AI Benchmarking Hub | 63.7% | – |
| DTBench | Epoch AI Benchmarking Hub | 97.3% | – |
| Coding | |||
| SciCode | SciCode | 61.8% | – |
| FrontierCode | Cognition | 47.5%† | – |
| Arena Coding | Arena (LMArena) | 1553 | 1518 |
| Arena WebDev | Arena (LMArena) | 1681 | 1704 |
| LiveBench 2.0 Coding | LiveBench | 85.7%† | 78.5%† |
| IOI | Vals AI | 100.0% | – |
| Code Migration | Vals AI | 68.2% | – |
| Code Migration v1.1 | Vals AI | 70.8% | – |
| ProgramBench | Vals AI | 2.5% | – |
Show all 125 benchmarks
| Metric | Publisher | Gemini 4 Argon (high) | Gemini 4 Hydrogen (high) |
|---|---|---|---|
| Coding | |||
| SWE-bench Multimodal | Vals AI | 56.0% | – |
| Vibe Code Bench 1-100 | Vals AI | 21.2% | – |
| Vibe Code Bench v1.1 | Vals AI | 91.9% | 87.8%† |
| MirrorCode | Epoch AI Benchmarking Hub | 58.9% | – |
| CursorBench | Cursor | 52.9% | – |
| ALE-Bench | Epoch AI Benchmarking Hub | 2100.1 | – |
| FrontierSWE | Epoch AI Benchmarking Hub | 55.0% | – |
| Terminal-Bench 4.0 (AA) | Artificial Analysis | 57.1% | 54.0% |
| Startrise Frontend | Startrise | 71.0%† | – |
| GameBench 2 Overall | DuelLab GameBench 2 | 81.7† | – |
| GameBench 2 by reasoning setting | DuelLab GameBench 2 | 89.2 | – |
| Design Arena Website | Design Arena | 1316† | 1316† |
| FrontierCode 1.1 (AA) | Artificial Analysis | 43.5% | – |
| FrontierCode 2.0 (AA) | Artificial Analysis | 25.7% | 36.3% |
| Agents & tools | |||
| Terminal-Bench | Terminal-Bench | – | 56.4% |
| Remote Labor Index | Scale AI / CAIS | 17.1%† | – |
| APEX-Agents | Mercor | 82.4%† | – |
| Arena Agent | Arena (LMArena) | 10.7 | – |
| LiveBench Long Agentic | LiveBench | 58.5%† | 61.8%† |
| LiveBench Browser | LiveBench | 82.8%† | 77.1%† |
| Terminal-Bench 2.1 (Vals) | Vals AI | 57.7% | – |
| MCP Atlas | Scale AI SEAL | 90.7%† | – |
| HiL-Bench | Scale AI SEAL | 62.0%† | – |
| GDPval-AA v2.1, normalised score | Artificial Analysis | 56.2% | – |
| GDPval-AA v2.1 | Artificial Analysis | 1633 | – |
| Analyst Agent (AA) | Artificial Analysis | 48.8% | – |
| CUA-bench | Vals AI | 4.8% | – |
| CyberBench | Vals AI | 77.9% | – |
| Finance Agent v2 | Vals AI | 65.4% | – |
| Finance Agent v2.1 | Vals AI | 67.7% | 65.1%† |
| Harvey's Legal Agent Benchmark v1.1 | Vals AI | 27.1% | 11.3%† |
| Harvey's Legal Agent Benchmark v1 | Vals AI | 19.6% | – |
| Legal Research Bench | Vals AI | 54.8% | 53.9%† |
| Robo-bench | Vals AI | 0.8% | – |
| SREBench | Vals AI | 44.3% | – |
| Tax Agent Bench | Vals AI | 49.2% | 52.3%† |
| Terminal-Bench 4.0 (Vals) | Vals AI | 57.6% | 54.0%† |
| Terminal-Bench Science | Vals AI | 44.3% | – |
| Time Horizon Index: KSP | Vals AI | 52.5% | – |
| PostTrainBench | Epoch AI Benchmarking Hub | 40.4% | – |
| Vending-Bench 2 | Andon Labs | 13718.2† | – |
| AutomationBench | Artificial Analysis | 77.5% | 74.4% |
| GDP.pdf (AA) | Artificial Analysis | 21.8% | 30.0% |
| Harvey LAB-AA v1.1 | Harvey | 3.9% | – |
| AA-Briefcase v1.1 | Artificial Analysis | 1484 | 1497 |
| GDPx | GDPx by SemiAnalysis | 7.3% | – |
| Design Arena Agentic | Design Arena | 1262† | – |
| Terminal-Bench-Science 0.1 (AA) | Artificial Analysis | 52.9% | 41.4% |
| FACTS Search | 89.9%† | – | |
| Maths | |||
| FrontierMath Tiers 1–3 | Epoch AI Benchmarking Hub | 86.0% | – |
| FrontierMath Tier 4 | Epoch AI Benchmarking Hub | 78.0% | – |
| OTIS Mock AIME | Epoch AI Benchmarking Hub | 100.0% | – |
| ProofBench | Vals AI | 99.0%† | – |
| Arena Maths | Arena (LMArena) | 1536 | 1495 |
| Knowledge | |||
| SimpleQA Verified | Epoch AI Benchmarking Hub | 76.0% | – |
| LiveBench 2.0 Data Analysis | LiveBench | 85.2%† | 83.2%† |
| LiveBench Research | LiveBench | 86.8%† | 86.8%† |
| AA-Omniscience v1.1 | Artificial Analysis | 46.1 | 43.7 |
| LegalBench | Vals AI | 88.3% | – |
| PRBench Finance | Scale AI SEAL | 49.9%† | – |
| PRBench Legal | Scale AI SEAL | 49.4%† | – |
| BioMysteryBench | Vals AI | 76.3% | – |
| Excel Modeling Benchmark | Vals AI | 75.2% | – |
| Excel Modeling Benchmark v1.1 | Vals AI | 74.8% | 75.8%† |
| MedCode | Vals AI | 58.8% | – |
| MedScribe | Vals AI | 87.4% | – |
| Public Benefits Bench v1.1 | Vals AI | 69.8% | – |
| DrugDiscoveryBench | Scale AI SEAL | 65.4% | – |
| EBR-bench | Epoch AI Benchmarking Hub | 64.8% | – |
| GDP.pdf | Epoch AI Benchmarking Hub | 28.4% | – |
| AA-Omniscience v1.1: accuracy | Artificial Analysis | 48.3% | 48.2% |
| AA-Omniscience v1.1: non-hallucination | Artificial Analysis | 95.7% | 91.3% |
| HealthBench Professional (AA) | OpenAI | 55.0% | – |
| Instruction following | |||
| MultiChallenge | Scale AI SEAL | 78.7%† | – |
| Arena Instruction Following | Arena (LMArena) | 1528 | 1503 |
| Human preference | |||
| Arena Text | Arena (LMArena) | 1522 | 1490 |
| EQ-Bench 4 | EQ-Bench | 1236† | – |
| Arena Creative Writing | Arena (LMArena) | 1523 | 1492 |
| Arena Multi-turn | Arena (LMArena) | 1545 | 1476 |
| Arena Longer Queries | Arena (LMArena) | 1544 | 1514 |
| Multimodal | |||
| LiveBench Design | LiveBench | 69.2%† | 77.3%† |
| MMMU-Pro | Artificial Analysis | 88.3%† | – |
| SAGE | Vals AI | 89.5% | – |
| AudioMC | Scale AI SEAL | 58.4% | – |
| AudioMC (text output) | Scale AI SEAL | 58.4% | – |
| Blueprint-Bench 2 | Epoch AI Benchmarking Hub | 54.5%† | – |
| Code2Video-AA | Artificial Analysis | 1259 | – |
| AA-3D | Artificial Analysis | 1147 | – |
| Long context | |||
| AA-LCR v1.1 | Artificial Analysis | 79.7% | – |
| MLCR | Artificial Analysis | 13.9% | 21.1%† |
| Composite | |||
| Epoch Capabilities Index | Epoch AI Benchmarking Hub | 166.5† | – |
| LiveBench 2.0 | LiveBench | 77.7%† | 77.0%† |
| AA Intelligence Index v5.0 | Artificial Analysis | 50.4 | 50.8 |
| AA Intelligence Index v4.3.2 | Artificial Analysis | 52.6 | – |
| AA Progress Index v1 | Artificial Analysis | 341.8 | – |
| Vals Index | Vals AI | 69.4 | 68.5† |
| Vals Finance Index | Vals AI | 66.0% | 66.1%† |
| Vals RSI Index | Vals AI | 30.6% | – |
| Vals Science Index | Vals AI | 55.4% | – |
| Vals Router Index | Vals AI | 69.2%† | – |
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 Argon: list price moves to $4.00 / $20.00 per 1M input / output tokens (announced).
- Gemini 4 Argon (high): 1 score revision.
- Gemini 4 Hydrogen (high): 10 new results (Arena Text, Arena Hard Prompts, Arena Coding…).
- Gemini 4 Argon (high): BenchLeader Index 65.9 → 65.3.
- Gemini 4 Argon (high): 1 new result (PostTrainBench); input price moved from $4.00/M to $2.00/M (50% down); output price moved from $20.00/M to $10.00/M (50% down); cost per task moved from $9.95/M to $4.97/M (50% down).
- Gemini 4 Argon (high): 4 score revisions.
- Gemini 4 Argon (high): 1 score revision.
- Gemini 4 Argon (high): cost per task moved from $7.68/M to $9.95/M (29% up).
- Gemini 4 Argon (high): 1 score revision.
- Gemini 4 Argon (high): 2 score revisions; input price moved from $2.00/M to $4.00/M (100% up); output price moved from $10.00/M to $20.00/M (100% up); cost per task moved from $3.84/M to $7.68/M (100% up).
Related comparisons
- Gemini 4 Argon vs Claude Fable 5.2
- Gemini 4 Argon vs Gemini 4 Carbon
- Gemini 4 Argon 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
- Gemini 3.8 Flash vs Gemini 4 Hydrogen
Rankings: Best LLM overall · Best LLM for agents · Best cheap LLMs
Gemini 4 Argon vs Gemini 4 Hydrogen: questions
- Is Gemini 4 Argon better than Gemini 4 Hydrogen?
- Gemini 4 Argon (high) and Gemini 4 Hydrogen (high) are neck and neck on quality (65.3 vs 63.4, within the ±3.3 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.
- Gemini 4 Argon vs Gemini 4 Hydrogen: which is cheaper, and will that change?
- Gemini 4 Hydrogen is cheaper today: $3.00 against $4.00 per million tokens, blended at three input tokens per output token. Gemini 4 Argon's current price runs until 30 Nov 2026, then $8.00.
- Is Gemini 4 Argon or Gemini 4 Hydrogen better for coding?
- Gemini 4 Hydrogen scores higher in coding (69 vs 67 on the category index, where 50 is average). On Arena WebDev, the top shared coding benchmark, it is 1681 for Gemini 4 Argon against 1704 for Gemini 4 Hydrogen.
- Which is faster, Gemini 4 Argon or Gemini 4 Hydrogen?
- Gemini 4 Hydrogen streams ~2× faster (180 vs 64 output tokens per second, Artificial Analysis 7-day median).
- Is Gemini 4 Argon or Gemini 4 Hydrogen better for agents and tool use?
- Gemini 4 Hydrogen scores higher in agentic tasks (62 vs 56 on the category index, where 50 is average).
More questions (4)
- Which is better for long documents?
- Both accept 1,048,576 tokens of context.
- Which has lower latency?
- Gemini 4 Hydrogen answers first: 16.4 s against 42.7 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 Gemini 4 Argon vs Gemini 4 Hydrogen?
- Across the 19 benchmarks both have, Gemini 4 Argon leads 14, Gemini 4 Hydrogen leads 5. Independent sources split: Gemini 4 Argon leads on Vals Index and Arena Text; Gemini 4 Hydrogen leads on AA Intelligence Index v5.0.
- When was Gemini 4 Hydrogen released?
- Gemini 4 Hydrogen was released on 12 Nov 2026.