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

Claude Fable 5.1 vs Gemma 4 31B

Anthropic's Claude Fable 5.1 and Google's Gemma 4 31B, 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, Claude Fable 5.1
  • 0–0higher 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.

  • Claude Fable 5.1 reads more at once: a context window of 1M tokens against 256K.
  • Gemma 4 31B can be downloaded and run on your own machine; Claude Fable 5.1 can't.
  • No independent board we follow ranks both models yet.
Side by side

The specs.

Claude Fable 5.1Gemma 4 31B
Made byAnthropic · USGoogle · US
ReleasedSep 1, 2026Apr 2, 2026
Price per 1M tokens$10 in / $50 outFree to download; hosts set prices
Context window1M256K
Takes intext, imagetext, image, video
Download and run it yourselfNoYes (Apache 2.0)
SizeNot published30.7B (dense) parameters
Maker says“For demanding reasoning and long-horizon agentic work”“Today, we are introducing Gemma 4 — our most intelligent open models to date.”
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 Fable 5.1Gemma 4 31B
Epoch Capabilities IndexEpoch AI, Oct 20, 2026#4164.65Not listed
LMArena textLMArena, Oct 15, 2026#6Not listed
LMArena creative writingLMArena, Oct 15, 2026#9Not listed
LMArena coding chatsLMArena, Oct 15, 2026#14Not listed
LMArena WebDevLMArena, Oct 19, 2026#5Not listed
LMArena mathLMArena, Oct 15, 2026#2Not listed
LMArena visionLMArena, Oct 19, 2026#17Not listed
LMArena documentsLMArena, Sep 13, 2026#2Not listed
LMArena Agent ArenaLMArena, Oct 19, 2026#3Not listed
Humanity's Last ExamScale AI#4Not listed
SWE-Bench ProScale AI, Sep 22, 2026#3Not listed
Remote Labor IndexScale AI#3Not listed
Terminal-Bench 4.0Vals AI, Oct 19, 2026#4Not listed
Vibe Code BenchVals AI, Oct 18, 2026#6Not listed
ProofBenchVals AI, Oct 12, 2026#3Not listed
GPQA Diamond (run by Vals AI, archived)Vals AI, Sep 1, 2026#9Not listed
MMMU Pro (run by Vals AI, archived)Vals AI, Sep 1, 2026#1Not listed
CUA-bench (games)Vals AI, Oct 13, 2026#3Not listed