Monday, October 26, 2026 · Edition updated 6:00 AM ETMON, OCT 26 editionNext edition in Next in --:--:--
Intelligence Verdict
Compare AI models

Claude Sonnet 5.5 vs Gemini 4 Argon

Anthropic's Claude Sonnet 5.5 and Google's Gemini 4 Argon, side by side: what each costs, how much it can read at once, whether you can run it yourself, and where independent tests place it.

  • —no price to compare
  • 1Mcontext window, Gemini 4 Argon
  • 6–4higher placings on boards ranking both
In short

How they differ.

Worked out from the figures below. Prices and specs are the makers' own, read Oct 20, 2026.

  • Gemini 4 Argon reads more at once: a context window of 1M tokens against 1M.
  • On the 10 independent boards that rank both, Claude Sonnet 5.5 places higher on 6 and Gemini 4 Argon on 4.
Side by side

The specs.

Claude Sonnet 5.5Gemini 4 Argon
Made byAnthropic · USGoogle · US
ReleasedSep 28, 2026Sep 30, 2026
Price per 1M tokens$2 in / $10 out$2 in / $10 out (introductory price)
Context window1M1M
Takes intext, imagetext, image, video, audio, pdf
Download and run it yourselfNoNo
SizeNot publishedNot published
Maker says“High-performance model for coding and agents”“Our flagship reasoning model with a unified 1M context window and long decodes up to 1M tokens.”
SourcesPrices, Oct 20, 2026 · DescriptionPrices, Oct 20, 2026 · Description
Independent tests

Where they place.

Position on each board we follow (1 is best). Epoch AI's and Vectara's scores are shown; the other boards are linked for their own figures.

BoardClaude Sonnet 5.5Gemini 4 Argon
Epoch Capabilities IndexEpoch AI, Oct 20, 2026#6164.45#5164.56
LMArena textLMArena, Oct 15, 2026Not listed#1
LMArena creative writingLMArena, Oct 15, 2026Not listed#2
LMArena coding chatsLMArena, Oct 15, 2026Not listed#1
LMArena WebDevLMArena, Oct 19, 2026#3#10
LMArena mathLMArena, Oct 15, 2026#15#1
LMArena Agent ArenaLMArena, Oct 19, 2026#5#6
Humanity's Last ExamScale AI#6#3
SWE-Bench ProScale AI, Sep 22, 2026#8#2
Vals IndexVals AI, Oct 19, 2026#1#3
Terminal-Bench 4.0Vals AI, Oct 19, 2026#2#6
Vibe Code BenchVals AI, Oct 18, 2026#1#2
ProofBenchVals AI, Oct 12, 2026#1#7
CUA-bench (games)Vals AI, Oct 13, 2026Not listed#8
Vectara hallucination testVectara, Oct 16, 2026Not listed#8312.1%