Gemini 4 Hydrogen vs GPT-6.1 Sol

Google against OpenAI. 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).
  • GPT-6.1 Sol scores higher on the Artificial Analysis Intelligence Index: 54.6 against 53.9.
  • On the 24 benchmarks both have scores on, Gemini 4 Hydrogen leads on 13 and GPT-6.1 Sol on 10, with 1 tied.
  • GPT-6.1 Sol reads more context: 1.1M tokens against 1M.
  • Gemini 4 Hydrogen is newer: listed Nov 12, 2026, against Sep 29, 2026.

Side by side

Gemini 4 HydrogenGPT-6.1 Sol
LabGoogleOpenAI
ListedNov 12, 2026Sep 29, 2026
Input per 1M tokens$2.25$3.00
Output per 1M tokens$11.25$15.00
Cached input per 1M$0.11$0.15
Blended (3:1) per 1M$4.50$6.00
Context window1M1.1M
Max output944K128K
Knowledge cutoff--
Intelligence index53.954.6
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.

BenchmarkGemini 4 HydrogenGPT-6.1 Sol
AIME100%Epoch AI100%Epoch AI
APEX-Agents78%Epoch AI60%Epoch AI
Artificial Analysis Intelligence Index53.9Artificial Analysis and OpenRouter54.6Artificial Analysis and OpenRouter
Chess Puzzles60%Epoch AI68%Epoch AI
Design Arena: 3D1397 EloDesign Arena1414 EloDesign Arena
Design Arena: Code1334 EloDesign Arena1355 EloDesign Arena
Design Arena: Data Viz1287 EloDesign Arena1281 EloDesign Arena
Design Arena: Game Dev1339 EloDesign Arena1395 EloDesign Arena
Design Arena: UI Component1340 EloDesign Arena1355 EloDesign Arena
Design Arena: Website1330 EloDesign Arena1312 EloDesign Arena
Earthborne Rangers (EBR-bench)70.5Epoch AI54.3Epoch AI
FrontierMath Tier 4 (v2)87.8%Epoch AI100%Epoch AI
FrontierMath Tiers 1-3 (v2)88.1%Epoch AI93.7%Epoch AI
GPQA Diamond96.8%Epoch AI94.4%Artificial Analysis and OpenRouter
LMArena (Coding)1512 EloLMArena1490 EloLMArena
LMArena (Overall)1502 EloLMArena1446 EloLMArena
LMArena: Creative Writing1508 EloLMArena1421 EloLMArena
LMArena: Hard Prompts1517 EloLMArena1468 EloLMArena
LMArena: Longer Query1521 EloLMArena1460 EloLMArena
LMArena: Math1537 EloLMArena1495 EloLMArena
LMArena: Multi-Turn1489 EloLMArena1450 EloLMArena
Mystery Game Puzzles65%Epoch AI80%Epoch AI
SimpleBench91.7%Epoch AI82.9%Epoch AI
SimpleQA Verified70.9%Epoch AI73.9%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 Google models, OpenAI models, every LLM's price and our sources.