Gemini 4 Hydrogen vs Gemini 4 Neon
Full profiles: Gemini 4 Hydrogen (Google) and Gemini 4 Neon (Google): every benchmark, price and rank.
Updated · Data from 8 sources
As of 19 Nov 2026, Gemini 4 Neon is ahead of Gemini 4 Hydrogen on quality (67.3 vs 63.6 on the BenchLeader Index), but Gemini 4 Hydrogen is 2.0× cheaper at $3.00 vs $6.00 per 1M tokens blended. Gemini 4 Neon leads in every category we measure both in. Gemini 4 Hydrogen streams ~1.5× faster.
Key facts (as of 19 Nov 2026)
- Gemini 4 Hydrogen scores 63.6 on the BenchLeader Index and Gemini 4 Neon scores 67.3 (BenchLeader, 19 Nov 2026).
- Gemini 4 Hydrogen costs $3.00 per 1M tokens blended (list price, 19 Nov 2026).
- Gemini 4 Neon costs $6.00 per 1M tokens blended (list price, 19 Nov 2026).
- Gemini 4 Hydrogen streams ~1.5× faster than Gemini 4 Neon (Artificial Analysis, 7-day median, 19 Nov 2026).
- Of the 12 benchmarks both models have, Gemini 4 Neon leads 10 (BenchLeader, 19 Nov 2026).
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 Neon | 73 vs 68 category score; FrontierCode 2.0 (AA) 43.3% vs 39.0% | Medium |
| Reasoning | Gemini 4 Neon | 72 vs 70 category score; HLE-Diamond (AA) 68.4% vs 58.8% | Medium |
| Knowledge | Gemini 4 Neon | 72 vs 70 category score; AA-Omniscience v1.1 53.8 vs 46.3 | Medium |
| Chat quality (human preference) | – | Only Gemini 4 Neon has an Arena rating (72 category score) | Not comparable |
| Lowest cost | Gemini 4 Hydrogen | $3.00 vs $6.00 per 1M blended; agentic coding session $0.120 vs $0.240 | – |
| Fastest first answer | Either | 47.3 s (Gemini 4 Hydrogen (xhigh)) vs 40.6 s (Gemini 4 Neon (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 Neon (high) leads on quality: 67.3 vs 63.6.
- Gemini 4 Neon (high) is stronger in coding, knowledge, reasoning.
- Gemini 4 Hydrogen (xhigh) is 2.0× cheaper ($3.00 vs $6.00 per 1M blended).
- Gemini 4 Hydrogen (xhigh) streams 1.7× faster (168 vs 101 tokens per second).
At a glance
| Spec | Gemini 4 Hydrogen | Gemini 4 Neon |
|---|---|---|
| Developer | ||
| Released | 12 Nov 2026 | 18 Nov 2026 |
| Context window (tokens) | 1,048,576 | 1,048,576 |
| Compared at | Gemini 4 Hydrogen (xhigh) | Gemini 4 Neon (high) |
| Open weights | No | No |
| Price in / out / cached input per 1M | $1.50 / $7.50 / $0.075 | $3.00 / $15.00 / $0.150 |
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 Hydrogen (xhigh) | Gemini 4 Neon (high) | Leader |
|---|---|---|---|
| Reasoning | 70.0 | 71.9 | Gemini 4 Neon |
| Coding | 67.7 | 73.4 | Gemini 4 Neon |
| Agents & tools | – | 76.2 | not comparable |
| Maths | 69.8 | – | not comparable |
| Knowledge | 70.2 | 72.3 | Gemini 4 Neon |
| Human preference | – | 71.7 | not comparable |
| Composite | 60.9 | – | 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: Agents & tools, Maths, Instruction following, Long context, Multimodal, Human preference.
Where sources disagree
Across the 12 benchmarks both have, Gemini 4 Hydrogen leads 2, Gemini 4 Neon leads 10. Every overall index that rates both puts Gemini 4 Neon ahead.
| Overall index | Gemini 4 Hydrogen (xhigh) | Gemini 4 Neon (high) | Leader |
|---|---|---|---|
| BenchLeader Index | 63.6 | 67.3 | Gemini 4 Neon |
| AA Intelligence Index v5.0.1 | 53.9 | 59.6 | Gemini 4 Neon |
| Arena Text | 1490† | 1519 | Gemini 4 Neon |
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 Hydrogen (xhigh) | Gemini 4 Neon (high) |
|---|---|---|
| Blended price per 1M tokens | $3.00 | $6.00 |
| Input / output per 1M | $1.50 / $7.50 | $3.00 / $15.00 |
| Cached input per 1M | $0.075 | $0.150 |
| Price per task: chat reply | $0.0029 | $0.0057 |
| Price per task: summarize a 30-page report | $0.022 | $0.045 |
| Price per task: code edit | $0.020 | $0.041 |
| Price per task: agentic coding session | $0.120 | $0.240 |
| Price per task: structured extraction | $0.0045 | $0.0090 |
| Agentic coding session, input mostly cached | $0.056 | $0.112 |
| Cost per benchmark task (AA Index) | $3.16 | $3.74 |
| Output tokens per task (AA Index) | 154k | 90k |
| Of which reasoning | 97k | 46k |
| Time per task (AA Index) | 15 min | 15 min |
| Output speed | 168 tok/s | 101 tok/s |
| Time to first answer | 47.3 s | 40.6 s |
| Time to a complete answer, last measured 13 Nov 2026 | 103.9 s | – |
Per token is not per task: an average task of Artificial Analysis' Intelligence Index cost $3.16 on Gemini 4 Hydrogen (xhigh) and $3.74 on Gemini 4 Neon (high), and Gemini 4 Hydrogen (xhigh) wrote 1.7× 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 Hydrogen (xhigh) scores 63.6 and takes 47 s to its first answer token; Gemini 4 Hydrogen (high) scores 63.5 in 21 s, Gemini 4 Hydrogen scores 61.1 in 2 s. Gemini 4 Neon (high) scores 67.3 and takes 41 s to its first answer token; Gemini 4 Neon (xhigh) scores 64.3 in 57 s. 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
74 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 Hydrogen (xhigh) | Gemini 4 Neon (high) |
|---|---|---|---|
| BenchLeader Index | BenchLeader | 63.6 | 67.3 |
| Coding score | BenchLeader | 67.7 | 73.4 |
| Composite score | BenchLeader | 60.9 | – |
| Knowledge score | BenchLeader | 70.2 | 72.3 |
| Maths score | BenchLeader | 69.8 | – |
| Reasoning score | BenchLeader | 70.0 | 71.9 |
| Agents & tools score | BenchLeader | – | 76.2 |
| Human preference score | BenchLeader | – | 71.7 |
| Blended price $/M | BenchLeader | $3.00 | $6.00 |
| Output speed | BenchLeader | 168 tok/s | 101 tok/s |
| Time to first answer | BenchLeader | 47.3 s | 40.6 s |
| Context window | BenchLeader | 1,048,576 tokens | 1,048,576 tokens |
| Reasoning | |||
| GPQA Diamond | Epoch AI Benchmarking Hub | 96.8% | – |
| Arena Hard Prompts | Arena (LMArena) | 1511† | 1546 |
| LiveBench 2.0 Reasoning | LiveBench | 88.6% | 89.6%† |
| HLE-Diamond (AA) | Artificial Analysis | 58.8% | 68.4% |
| CritPt v2 hard subset (AA) | Artificial Analysis | 66.0% | 59.0% |
| Arena Expert | Arena (LMArena) | 1538† | 1541 |
| Chess Puzzles | Epoch AI Benchmarking Hub | 60.0% | – |
| Mystery Game Puzzles | Epoch AI Benchmarking Hub | 65.0% | – |
| Coding | |||
| Arena Coding | Arena (LMArena) | 1515† | 1558 |
| Arena WebDev | Arena (LMArena) | 1703† | 1764 |
| LiveBench 2.0 Coding | LiveBench | 78.5% | 89.7%† |
| Vibe Code Bench v1.1 | Vals AI | 87.8% | – |
| CursorBench | Cursor | 57.8% | – |
| ALE-Bench | Epoch AI Benchmarking Hub | 1825.7 | – |
| FrontierSWE | Epoch AI Benchmarking Hub | 53.1%† | – |
| Terminal-Bench 4.0 (AA) | Artificial Analysis | 53.5% | 61.6% |
| Design Arena Website | Design Arena | 1326† | – |
| FrontierCode 2.0 (AA) | Artificial Analysis | 39.0% | 43.3% |
| Agents & tools | |||
| Terminal-Bench | Terminal-Bench | 56.4%† | – |
| APEX-Agents | Mercor | 78.0%† | – |
| Arena Agent | Arena (LMArena) | 13.5† | 18.4 |
| LiveBench Long Agentic | LiveBench | 61.8% | 82.6%† |
| LiveBench Browser | LiveBench | 77.1% | 95.6%† |
| HiL-Bench | Scale AI SEAL | 55.3%† | – |
| Finance Agent v2.1 | Vals AI | 65.1% | – |
Show all 74 benchmarks
| Metric | Publisher | Gemini 4 Hydrogen (xhigh) | Gemini 4 Neon (high) |
|---|---|---|---|
| Agents & tools | |||
| Harvey's Legal Agent Benchmark v1.1 | Vals AI | 11.3% | – |
| Legal Research Bench | Vals AI | 53.9% | – |
| Tax Agent Bench | Vals AI | 52.3% | – |
| Terminal-Bench 4.0 (Vals) | Vals AI | 54.0% | – |
| Arena Agent Task Completion | Arena (LMArena) | 15.7† | 19.2 |
| Vending-Bench 2 | Andon Labs | 14549.5† | – |
| SpireClimb | Epoch AI Benchmarking Hub | 7.7% | – |
| AutomationBench | Artificial Analysis | 76.1% | 79.2% |
| GDP.pdf (AA) | Artificial Analysis | 27.6% | 33.4% |
| AA-Briefcase v1.1 | Artificial Analysis | 1568 | 1632 |
| Design Arena Agentic | Design Arena | 1266† | – |
| Terminal-Bench-Science 0.1 (AA) | Artificial Analysis | 49.5% | 65.7% |
| MKA (AA) | Artificial Analysis | – | 54.6% |
| FACTS Search | 93.6%† | – | |
| Maths | |||
| FrontierMath Tiers 1–3 | Epoch AI Benchmarking Hub | 88.1% | – |
| FrontierMath Tier 4 | Epoch AI Benchmarking Hub | 87.8% | – |
| OTIS Mock AIME | Epoch AI Benchmarking Hub | 100.0% | – |
| Autoform-Hard | Vals AI | 64.3% | – |
| Arena Maths | Arena (LMArena) | 1504† | – |
| Knowledge | |||
| SimpleQA Verified | Epoch AI Benchmarking Hub | 70.9% | – |
| LiveBench 2.0 Data Analysis | LiveBench | 83.2% | 85.3%† |
| LiveBench Research | LiveBench | 86.8% | 94.5%† |
| AA-Omniscience v1.1 | Artificial Analysis | 46.3 | 53.8 |
| PRBench Finance | Scale AI SEAL | 52.3%† | – |
| PRBench Legal | Scale AI SEAL | 53.1%† | – |
| Excel Modeling Benchmark v1.1 | Vals AI | 75.8% | – |
| DrugDiscoveryBench | Scale AI SEAL | 69.1%† | – |
| EBR-bench | Epoch AI Benchmarking Hub | 70.5% | – |
| AA-Omniscience v1.1: accuracy | Artificial Analysis | 50.5% | 59.4% |
| AA-Omniscience v1.1: non-hallucination | Artificial Analysis | 91.5% | 86.1% |
| FACTS Parametric | 76.7%† | – | |
| Instruction following | |||
| MultiChallenge | Scale AI SEAL | 80.6%† | – |
| Arena Instruction Following | Arena (LMArena) | 1499† | 1522 |
| Human preference | |||
| Arena Text | Arena (LMArena) | 1490† | 1519 |
| Arena Creative Writing | Arena (LMArena) | 1491† | 1514 |
| Arena Multi-turn | Arena (LMArena) | 1480† | 1529 |
| Arena Longer Queries | Arena (LMArena) | 1511† | 1521 |
| Multimodal | |||
| LiveBench Design | LiveBench | 77.3% | 81.5%† |
| Humanity's Sixth Sense | Scale AI SEAL | 63.4% | 75.9%† |
| Furniture Assembly | Epoch AI Benchmarking Hub | 57.5% | – |
| FACTS Multimodal | 63.1%† | – | |
| Long context | |||
| MLCR | Artificial Analysis | 21.1% | 28.9% |
| FACTS Grounding | 78.7%† | – | |
| Composite | |||
| LiveBench 2.0 | LiveBench | 77.0% | 87.4%† |
| AA Intelligence Index v5.0.1 | Artificial Analysis | 53.9 | 59.6 |
| Vals Index | Vals AI | 68.5 | – |
| Vals Finance Index | Vals AI | 66.1% | – |
| Vals Legal Index | Vals AI | 73.6% | – |
| Safety & honesty | |||
| FORTRESS | Scale AI SEAL | 17.5%† | – |
Data as of 2026-11-19. Best configuration of each model; every score links to its source on the model pages.
What changed
- Gemini 4 Hydrogen (xhigh): 1 new result (Humanity's Sixth Sense).
- Gemini 4 Neon (high): 13 new results (MLCR, MKA (AA), Arena Text…).
- Gemini 4 Hydrogen (xhigh): BenchLeader Index 60.8 → 63.7.
- Gemini 4 Hydrogen (xhigh): 10 new results (GPQA Diamond, FrontierMath Tiers 1–3, FrontierMath Tier 4…).
- Gemini 4 Neon (high): first results.
- Gemini 4 Hydrogen (xhigh): BenchLeader Index 61.8 → 60.8.
- Gemini 4 Hydrogen (xhigh): 2 new results (CursorBench, ALE-Bench).
- Gemini 4 Hydrogen (xhigh): 8 new results (LiveBench 2.0, LiveBench Long Agentic, LiveBench 2.0 Reasoning…).
- Gemini 4 Hydrogen (xhigh): 1 new result (MLCR).
Related comparisons
- Gemini 4 Hydrogen vs Claude Fable 5.2
- Gemini 4 Hydrogen vs GPT-6.2 Astra
- Gemini 4 Hydrogen vs Gemini 4 Carbon
- Gemini 4 Neon vs Claude Fable 5.2
- Gemini 4 Neon vs GPT-6.2 Astra
- Gemini 4 Neon vs Gemini 4 Carbon
- Gemini 4 Neon vs Claude Opus 5.5
- Gemini 4 Hydrogen vs GPT-6 Astra
Rankings: Best LLM overall · Best LLM for coding · Best LLM for agents · Best cheap LLMs
Gemini 4 Hydrogen vs Gemini 4 Neon: questions
- Is Gemini 4 Neon better than Gemini 4 Hydrogen?
- Gemini 4 Neon (high) leads on quality: 67.3 vs 63.6. The BenchLeader Index combines every independent quality benchmark; Gemini 4 Neon (high) is ahead overall as of 19 Nov 2026, but check the category scores for your use.
- Gemini 4 Hydrogen vs Gemini 4 Neon: which is cheaper, and will that change?
- Gemini 4 Hydrogen is cheaper today: $3.00 against $6.00 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
- Is Gemini 4 Hydrogen or Gemini 4 Neon better for coding?
- Gemini 4 Neon scores higher in coding (73 vs 68 on the category index, where 50 is average). On FrontierCode 2.0 (AA), the top shared coding benchmark, it is 39.0% for Gemini 4 Hydrogen against 43.3% for Gemini 4 Neon.
- Which is faster, Gemini 4 Hydrogen or Gemini 4 Neon?
- Gemini 4 Hydrogen streams ~1.5× faster (168 vs 101 output tokens per second, Artificial Analysis 7-day median).
- Which is better for long documents?
- Both accept 1,048,576 tokens of context.
More questions (3)
- Which has lower latency?
- Gemini 4 Neon answers first: 40.6 s against 47.3 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 Hydrogen vs Gemini 4 Neon?
- Across the 12 benchmarks both have, Gemini 4 Hydrogen leads 2, Gemini 4 Neon leads 10. Every overall index that rates both puts Gemini 4 Neon ahead.
- When was Gemini 4 Neon released?
- Gemini 4 Neon was released on 18 Nov 2026.