Sign in
VERIFIEDNov 222026

Is Gemini 4 Hydrogen state of the art?Yes.Yes on Factuality (best per dollar). Not the overall leader.

As of Nov 22, 2026, Gemini 4 Hydrogen is state of the art on best per dollar in Factuality (since Nov 13, 2026; sources LMArena Text factuality; methodology v1.0). Gemini 4 Hydrogen shares the Factuality best-per-dollar frontier with DeepSeek V4.1 Flash, Gemini 4 Carbon, GLM 5.3, Granite 4.2 8B, Mimo V2.6 Pro since Nov 13, 2026. Co-SOTA shares rank 1.

Computed automaticallyas of Nov 22, 2026methodology v1.0confidence: medium
View as of point-in-time crowns
At a glance

Facts and scores

Gemini 4 Hydrogen is a closed-weights text, image, audio, video and file model from Google DeepMind, listed on LMArena since Nov 11, 2026; no public parameter count, a 1,049K-token context window and $3.00 per 1M tokens blended.

How it scores

  • On GPQA Diamond it scores 96.8% (CI 94.5%–99.1%), #2 of 245 (top 1%); 0.0 pts behind GPT-6.2 Astra; level with GPT-6.2 Astra above and Gemini 4 Carbon is 0.3 pts below.
  • On Tax Agent Bench it scores 52.3 (CI 45.2–59.4), #1 of 79 (top 2%); Gemini 4 Carbon is 0.5 below.
  • On LMArena Text factuality it scores 1494 (CI 1486–1501), #6 of 215 (top 3%); 28 behind Gemini 4 Carbon; level with Muse Wonder above and Claude Opus 4.6 is 1 below.

History

First result on isitsota: Nov 12, 2026. Best overall rank so far: #2 in Science, first held Nov 22, 2026.

Why

The ruling, in plain English

Ranked #14 in General LLM.

Receipts

Evidence

Scores come from the latest ingested snapshot
SourceScoreDateTypeReceipt
LMArena Text (style-controlled, overall)
Gemini 4 Hydrogen (High)
1490 1481–14992026-11-19INDEP.snap_280a9b5ca493
LMArena Text (style-controlled, hard prompts)
Gemini 4 Hydrogen (High)
1511 1500–15222026-11-19INDEP.snap_280a9b5ca493
GPQA Diamond
gemini-4-hydrogen_xhigh · xhigh
96.8% 94.5%–99.1%2026-11-12INDEP.snap_4e4b95c17b0f
LMArena Text (style-controlled, coding)
Gemini 4 Hydrogen (High)
1514 1496–15322026-11-19INDEP.snap_280a9b5ca493
LMArena WebDev
Gemini 4 Hydrogen (High)
1701 1686–17152026-11-20INDEP.snap_2f4a3ebc7e46
LMArena Text (style-controlled, longer query)
Gemini 4 Hydrogen (High)
1510 1496–15242026-11-19INDEP.snap_280a9b5ca493
GDP.pdf
gemini-4-hydrogen_xhigh · xhigh
54.2%2026-11-12INDEP.snap_2d63325b3124
LMArena Text factuality
Gemini 4 Hydrogen (High)
1494 1486–15012026-11-19INDEP.snap_275d95909246
Legal Research Bench
google/gemini-4-hydrogen · xhigh · Source: Vals AI
53.8 47.1–60.62026-11-21INDEP.snap_vals_e4530282a8b5

Rows marked Vals AI come from Vals AI's proprietary benchmarks, republished with permission. Each receipt links to the benchmark on Vals.

Reign history

Where it sits in the succession

Full timeline →

Crown intervals for this model are still empty.

Honest about the gaps

Where it is not the crown

CategoryThis modelRankLeader
General LLM#14 in this category#14Gemini 4 Carbon
Reasoning#17 in this category#17Gemini 4 Carbon
Science#2 in this category#2GPT-6.2 Astra
CodingNot enough data—Claude Sonnet 5.5
Coding › Web dev#12 in this category#12Claude Fable 5.2
Long context#9 in this category#9Gemini 4 Argon
VisionNot enough data——
FactualityNear-SOTA#5Gemini 4 Carbon
Links

Related pages

Is Gemini 4 Hydrogen SOTA?

As of Nov 22, 2026, Gemini 4 Hydrogen is state of the art on best per dollar in Factuality (since Nov 13, 2026; sources LMArena Text factuality; methodology v1.0).

What is Gemini 4 Hydrogen best at?

As of Nov 22, 2026, Gemini 4 Hydrogen is near state of the art, rank #5 in Factuality (since Nov 22, 2026; sources LMArena Text factuality).

How does Gemini 4 Hydrogen rank in Coding?

As of Nov 22, 2026, Gemini 4 Hydrogen is short of the evidence for a rank in Coding (since Nov 22, 2026; sources LMArena Text (style-controlled, coding); methodology v1.0).

When was Gemini 4 Hydrogen last SOTA?

As of Nov 22, 2026, Gemini 4 Hydrogen last held Coding › Web dev from Nov 13, 2026 until Nov 16, 2026.