← comparisons · head to head
Gemini 4 Hydrogen vs Gemini 3.8 Flash
Gemini 4 Hydrogen scores higher than Gemini 3.8 Flash on all 4 public leaderboards that rate both. On the ArtificialWatch Index, which takes the median of each model's percentile across the boards that score it, Gemini 4 Hydrogen is at 81.9 and Gemini 3.8 Flash at 41.3 (out of 100). On each maker's API, Gemini 4 Hydrogen costs $1.50 / $7.50 per 1M tokens (input / output) and Gemini 3.8 Flash $0.75 / $3.75.
Scores as published by each board; table composed November 13, 2026.
Get the next launch alert, free →
Leaderboard by leaderboard
| Board | Gemini 4 Hydrogen | Gemini 3.8 Flash | Higher |
|---|---|---|---|
| LMArena Elo (community votes) | 1,704.2 | 1,583.5 | Gemini 4 Hydrogen |
| LiveBench global average (0-100) | 77 | 57.3 | Gemini 4 Hydrogen |
| Vals AI Vals Index accuracy % · weighted finance + coding tasks | 68.5 | 56 | Gemini 4 Hydrogen |
| Artificial Analysis intelligence index · measured runs only | 53.9 | 30.8 | Gemini 4 Hydrogen |
Raw scores are each board's own scale, so compare within a row, not across rows. Full table: the bench index.
For coding
On the ArtificialWatch coding index, Gemini 4 Hydrogen is at 76 (#10 of 48) and Gemini 3.8 Flash at 44.4 (#22). Gemini 4 Hydrogen scores higher on all 3 coding boards that rate both.
| Coding board | Gemini 4 Hydrogen | Gemini 3.8 Flash |
|---|---|---|
| LMArena · Coding | 1,515.9 | 1,510.1 |
| LiveBench · Coding | 78.5 | 73.3 |
| Vals Vibe Code Bench | 87.8 | 78.7 |
Gemini 4 Hydrogen at a glance
- Developer
- Status
- Live since November 12, 2026
- API price
- $1.50 input / $7.50 output per 1M tokens · Google, gemini-4-hydrogen
- Context window
- 1.05M tokens
Live — Nov 12 · GA on the Gemini API as gemini-4-hydrogen (Google's release notes, Nov 12), free tier and paid tier, also in Google AI Studio and the default model for the Antigravity agent in Gemini Managed Agents · $1.50 / $7.50 per 1M, $0.075 cached (implicit caching only); Batch and Flex $0.75 / $3.75; Priority $2.70 / $13.50 · no introductory discount: the same as the SKU rows Google Cloud listed at 08:50 UTC · 1M unified context; 65,536 max output by default, up to 1M with long decode · text, image, video, audio and PDF in, text out · thinking levels low, medium, high (default) and a new xhigh · Google calls Gemini 3.8 Flash its 'previous-generation Flash model' ($0.75 / $3.75 intro through Dec 31, $1.50 / $7.50 from Jan 1) · our sweep fired at 17:46 UTC · before launch: codename reported since Oct 27, Business Insider (Nov 11) on staff testing, billing SKUs Nov 12 08:50 UTC · Nov 12 18:50 UTC: 54 on Artificial Analysis' Intelligence Index (Gemini 4 Hydrogen (Xhigh)), above Gemini 4 Argon (50) and GPT-6.1 Terra (51), one point under Claude Sonnet 5.5 (55); 54.3% on CursorBench at High, 12th of its listed settings.
Gemini 4 Hydrogen is live: Google's new everyday model costs $1.50 / $7.50 per 1M tokens, with a free tier and a 1M context
2026-11-12 · Google released Gemini 4 Hydrogen (gemini-4-hydrogen) on November 12 as generally available on the Gemini API, on the free tier and at $1.50 per 1M input tokens and $7.50 per 1M output tokens on the paid tier.
Gemini 4 Hydrogen appears in Google Cloud's price list at $1.50 input and $7.50 output per 1M tokens, before Google has announced it
2026-11-12 · Google Cloud's public SKU list now carries Gemini 4 Hydrogen under two services, the Gemini API and Vertex AI, before Google has announced the model. @Mr_Salio flagged the rows at 08:11 UTC on November 12, and ArtificialWatch read them on Google's SKU list at 08:50 UTC.
Gemini 3.8 Flash at a glance
- Developer
- Status
- Live since September 2, 2026
- API price
- $0.75 input / $3.75 output per 1M tokens · Google, gemini-3.8-flash
- Context window
- 1.05M tokens
Live — GA Sep 2 · $0.75/$3.75 per 1M introductory through Dec 31, identical to 3.7 · 1M in / 64K out · 'our most intelligent Flash model' · 20 days after 3.7.
Gemini 3.8 Flash is GA — same price as 3.7, twenty days later
2026-09-02 · Google released Gemini 3.8 Flash today. The Gemini API changelog for September 2 reads: "Gemini 3.8 Flash generally available (GA): Released gemini-3.8-flash, our most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows."
Gemini 4 Hydrogen vs Gemini 3.8 Flash: quick answers
Which is better, Gemini 4 Hydrogen or Gemini 3.8 Flash?
It depends on what you measure. Gemini 4 Hydrogen scores higher than Gemini 3.8 Flash on all 4 public leaderboards that rate both. Gemini 4 Hydrogen's widest lead is on LiveBench. On the ArtificialWatch Index, which takes the median of each model's percentile across the boards that score it, Gemini 4 Hydrogen is at 81.9 and Gemini 3.8 Flash at 41.3 (out of 100).
Which is newer, Gemini 4 Hydrogen or Gemini 3.8 Flash?
Gemini 4 Hydrogen. It went live on November 12, 2026, 71 days after Gemini 3.8 Flash (September 2, 2026).
Which is cheaper, Gemini 4 Hydrogen or Gemini 3.8 Flash?
Gemini 3.8 Flash is cheaper on both input and output. On each vendor's own API, Gemini 4 Hydrogen is $1.50 input / $7.50 output per million tokens and Gemini 3.8 Flash is $0.75 input / $3.75 output per million tokens. Prices as published in the models.dev catalog, as of 2026-11-12.
Which has the bigger context window, Gemini 4 Hydrogen or Gemini 3.8 Flash?
Neither. Both take 1.05M tokens.
How do Gemini 4 Hydrogen and Gemini 3.8 Flash compare for coding?
On the ArtificialWatch coding index, Gemini 4 Hydrogen is at 76 (#10 of 48) and Gemini 3.8 Flash at 44.4 (#22). Gemini 4 Hydrogen scores higher on all 3 coding boards that rate both.
Who makes Gemini 4 Hydrogen and Gemini 3.8 Flash?
Both are from Google.
Where do these numbers come from?
Each score is the leaderboard's own published figure, read by ArtificialWatch (table composed November 13, 2026). Boards measure different things, so raw scores are only comparable within a row.
More comparisons
Hear when the next one drops. Free.
Free: a Chrome push and an email about 15 minutes after a new model answers on a public API. Members get a text or a phone call the moment a launch is confirmed.
- Free forever
- No card
- Unsubscribe in one click
Also: the bench index · API pricing · what a workload costs on each · the wire