Claude Sonnet 5.5 vs Gemini 4 Hydrogen

Anthropic against Google. Prices, scores and speed below are live.

  • Gemini 4 Hydrogen costs 25% less on blended price ($4.50 against $6.00 per 1M tokens, 3 input to 1 output).
  • Claude Sonnet 5.5 scores higher on the Artificial Analysis Intelligence Index: 54.5 against 53.9.
  • On the 24 benchmarks both have scores on, Claude Sonnet 5.5 leads on 6 and Gemini 4 Hydrogen on 16, with 2 tied.
  • Gemini 4 Hydrogen reads more context: 1M tokens against 1M.
  • Gemini 4 Hydrogen is newer: listed Nov 12, 2026, against Sep 28, 2026.

Side by side

Claude Sonnet 5.5Gemini 4 Hydrogen
LabAnthropicGoogle
ListedSep 28, 2026Nov 12, 2026
Input per 1M tokens$3.00$2.25
Output per 1M tokens$15.00$11.25
Cached input per 1M$0.15$0.11
Blended (3:1) per 1M$6.00$4.50
Context window1M1M
Max output128K944K
Knowledge cutoff--
Intelligence index54.553.9
Coding index--
ReasoningYesYes
Reads imagesYesYes
Tool useYesYes
Structured outputYesYes

Every benchmark both are scored on

Each model's best score per benchmark, with its source. Scores from different sources or settings are not always comparable; each links to where it was published.

BenchmarkClaude Sonnet 5.5Gemini 4 Hydrogen
AIME100%Epoch AI100%Epoch AI
APEX-Agents75.5%Epoch AI78%Epoch AI
Artificial Analysis Intelligence Index54.5Artificial Analysis and OpenRouter53.9Artificial Analysis and OpenRouter
Chess Puzzles59%Epoch AI60%Epoch AI
Design Arena: 3D1393 EloDesign Arena1397 EloDesign Arena
Design Arena: ASCII Art1399 EloDesign Arena1450 EloDesign Arena
Design Arena: Code1340 EloDesign Arena1334 EloDesign Arena
Design Arena: Data Viz1358 EloDesign Arena1287 EloDesign Arena
Design Arena: Game Dev1375 EloDesign Arena1339 EloDesign Arena
Design Arena: UI Component1379 EloDesign Arena1340 EloDesign Arena
Design Arena: Website1303 EloDesign Arena1330 EloDesign Arena
FrontierMath Tier 4 (v2)80.5%Epoch AI87.8%Epoch AI
FrontierMath Tiers 1-3 (v2)88.8%Epoch AI88.1%Epoch AI
GPQA Diamond92.8%Artificial Analysis and OpenRouter96.8%Epoch AI
LMArena (Coding)1500 EloLMArena1512 EloLMArena
LMArena (Overall)1470 EloLMArena1502 EloLMArena
LMArena: Creative Writing1463 EloLMArena1508 EloLMArena
LMArena: Hard Prompts1487 EloLMArena1517 EloLMArena
LMArena: Longer Query1484 EloLMArena1521 EloLMArena
LMArena: Math1509 EloLMArena1537 EloLMArena
LMArena: Multi-Turn1462 EloLMArena1489 EloLMArena
Mystery Game Puzzles65%Epoch AI65%Epoch AI
SimpleBench75.9%Epoch AI91.7%Epoch AI
SimpleQA Verified46.5%Epoch AI70.9%Epoch AI

More comparisons

Where these figures come from

Prices are GenMagic's own, what the studio and the API charge, recomputed from each provider's price list every few minutes. The indices are the Artificial Analysis indices, and every benchmark score links to its source, re-read daily. Measured speed is GenMagic's own generation records, in aggregate. See Anthropic models, Google models, every LLM's price and our sources.