Claude Fable 5.1 vs Gemini 4 Argon

$2.98 / task
Wins 6 of 19 benchmarks
$1.99 / task
Wins 7 of 19 benchmarks
Fable 5.154.7
Gemini 4 Argon77.5
Fable 5.152.3
Gemini 4 Argon56.2
Fable 5.1at max57.5
Gemini 4 Argon48.8
Fable 5.144.9
Gemini 4 Argon57.1
Fable 5.1at max43.3
Gemini 4 Argon52.9
Fable 5.11,527.7
Gemini 4 Argon1,485.8
Fable 5.184.7
Gemini 4 Argon79.7
Fable 5.1at max49
Gemini 4 Argon43.5
Harvey LAB-AA 1.1?
Fable 5.1at max6.4
Gemini 4 Argon3.9
Fable 5.1at high99.1
Gemini 4 Argon99.2
Fable 5.1at high92.2
Gemini 4 Argon92.2
EBR Bench?
Fable 5.1at max57.1
Gemini 4 Argon64.8
Fable 5.1at max70
Gemini 4 Argon72.5
Fable 5.1—
Gemini 4 Argon51.3
Fable 5.141
Gemini 4 Argon—
Fable 5.1at max49.5
Gemini 4 Argon—
SpireClimb?
Fable 5.1at max2
Gemini 4 Argon—
SpireClimb StS1 A20 Heart?
Fable 5.1at max0
Gemini 4 Argon—
SpireClimb StS2 A10?
Fable 5.1at max4
Gemini 4 Argon—

Specs

SpecFable 5.1Gemini 4 Argon
Input, per 1M$10!$2
Output, per 1M$50!$10
Cost per task?$2.98$1.99
Speed, tok/s5684
Context1M1M
WeightsClosedClosed
ReleasedSep 2026Oct 2026
See images✓✓
Read PDFsPartial✓
Hear audio—✓
Watch video—✓
Call tools✓✓
Force a tool callPartialPartial
Return strict JSON✓✓
Search the web?✓
Run code?✓
Use a computer??

What breaks when you switch

Fable 5.1 → Gemini 4 Argon
Synchronous output stops at 65,536›

With background false, output limits above 65,536 tokens return HTTP 400; stay at or below that limit.

Sampling parameters are ignored›

temperature, top_p and top_k are ignored; remove them from requests.

No explicit caching›

Explicit caching is unavailable; omit explicit cache requests.

Gemini 4 Argon → Fable 5.1
Replace forced tool_choice›

Forced tool_choice returns HTTP 400; use auto with an explicit instruction and strict tools, or JSON outputs.

Adaptive thinking is always on›

Disabled thinking or manual budget_tokens returns HTTP 400; omit thinking or use adaptive thinking.

No non-default sampling values›

Non-default temperature, top_p or top_k returns HTTP 400; omit non-default sampling values.

Requires 30-day data retention · Claude API›

A Claude API organization or workspace without 30-day retention receives HTTP 400; configure workspace retention or contact the Anthropic account team.

Thinking blocks bind to conversations›

Where conversation binding is enforced, replaying an invalidated block returns HTTP 400; use the documented drop_block control to continue without it.

No assistant prefill›

Assistant prefill returns HTTP 400; use system prompt instructions instead.