Gemini 4 Argon vs GPT-6.1 Sol

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

  • They cost the same: $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 50.4.
  • On the 33 benchmarks both have scores on, Gemini 4 Argon leads on 17 and GPT-6.1 Sol on 13, with 3 tied.
  • GPT-6.1 Sol reads more context: 1.1M tokens against 1M.
  • Gemini 4 Argon is newer: listed Oct 13, 2026, against Sep 29, 2026.

Side by side

Gemini 4 ArgonGPT-6.1 Sol
LabGoogleOpenAI
ListedOct 13, 2026Sep 29, 2026
Input per 1M tokens$3.00$3.00
Output per 1M tokens$15.00$15.00
Cached input per 1M$0.15$0.15
Blended (3:1) per 1M$6.00$6.00
Context window1M1.1M
Max output944K128K
Knowledge cutoff--
Intelligence index50.454.6
Coding index--
ReasoningYesYes
Reads imagesYesYes
Tool useYesYes
Structured outputYesYes
Measured output speed25 tokens/s-

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 ArgonGPT-6.1 Sol
AIME100%Epoch AI100%Epoch AI
APEX-Agents82.4%Epoch AI60%Epoch AI
ARC-AGI-198.5%Epoch AI98.5%Epoch AI
ARC-AGI-291.3%Epoch AI94.2%Epoch AI
Artificial Analysis Intelligence Index50.4Artificial Analysis and OpenRouter54.6Artificial Analysis and OpenRouter
Chess Puzzles59%Epoch AI68%Epoch AI
Design Arena: 3D1363 EloDesign Arena1433 EloDesign Arena
Design Arena: Code1325 EloDesign Arena1355 EloDesign Arena
Design Arena: Data Viz1335 EloDesign Arena1281 EloDesign Arena
Design Arena: Game Dev1363 EloDesign Arena1410 EloDesign Arena
Design Arena: UI Component1330 EloDesign Arena1345 EloDesign Arena
Design Arena: Website1315 EloDesign Arena1310 EloDesign Arena
DTBench97.6%Epoch AI96.5%Epoch AI
Earthborne Rangers (EBR-bench)64.8Epoch AI54.3Epoch AI
FrontierCode47.6Epoch AI50.2Epoch AI
FrontierMath Tier 4 (v2)78%Epoch AI100%Epoch AI
FrontierMath Tiers 1-3 (v2)86%Epoch AI93.7%Epoch AI
GPQA Diamond96.5%Artificial Analysis and OpenRouter94.4%Artificial Analysis and OpenRouter
LMArena (Coding)1540 EloLMArena1486 EloLMArena
LMArena (Overall)1530 EloLMArena1446 EloLMArena
LMArena: Creative Writing1535 EloLMArena1420 EloLMArena
LMArena: Hard Prompts1543 EloLMArena1467 EloLMArena
LMArena: Longer Query1547 EloLMArena1460 EloLMArena
LMArena: Math1551 EloLMArena1495 EloLMArena
LMArena: Multi-Turn1549 EloLMArena1452 EloLMArena
LMCA63.7Epoch AI62.8Epoch AI
MirrorCode (ML, +Private, 2L)58.9Epoch AI61.1Epoch AI
Mystery Game Puzzles64%Epoch AI80%Epoch AI
ProofBench99%Epoch AI99%Epoch AI
SciCode61.8%Epoch AI55.8%Epoch AI
SimpleQA Verified76%Epoch AI73.9%Epoch AI
tau-bench (Airline)78.7%Artificial Analysis and OpenRouter70%Artificial Analysis and OpenRouter
WebDev Arena1680 EloEpoch AI1759 EloEpoch AI

In our tests and guides

Where Gemini 4 Argon or GPT-6.1 Sol ran on a real brief, or shows in a live table.

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.