Skip to main content

Claude Fable 5.2 vs Gemini 4 Carbon

SpecClaude Fable 5.2Gemini 4 Carbon
Respan Index80.8 (#1)76.1 (#3)
Blended price per 1M$16$4
Context window-1M
Input / output per 1M$8 / $40$2 / $10
Max output--
Inputtexttext, image, audio, video
Released2026-11-092026-11-10

Respan Index by category

Each category is scored 0 to 100, and how far ahead the winner is. Leads under a point are close to even.

CategoryClaude Fable 5.2Gemini 4 Carbon
Coding73.0 Claude Fable 5.269.3 Gemini 4 Carbon
Agents85.3 Claude Fable 5.283.5 Gemini 4 Carbon
Reasoning90.2 Claude Fable 5.284.1 Gemini 4 Carbon
Knowledge & language94.0 Claude Fable 5.277.8 Gemini 4 Carbon
Human preference61.7 Claude Fable 5.260.6 Gemini 4 Carbon

How the Respan Index works

Benchmarks both report

Claude Fable 5.2 leads on 12 of the 17 benchmarks both report. Higher is better. Each score links to where it was published.

BenchmarkClaude Fable 5.2Gemini 4 Carbon
LMArena Elo15031527
LMArena WebDev (LMArena)18231769
LMArena Agent (LMArena)0.27420.161
Vending-Bench 2 (Andon Labs)9628.4816484.21
APEX-Agents (Mercor)80.1%84.2%
Chess Puzzles (Epoch AI)79%78%
EBR-bench (Epoch AI)90.5%87.6%
FrontierMath Tier 4 v2 (Epoch AI)100%95.1%
FrontierMath Tiers 1-3 v2 (Epoch AI)95.1%90.5%
FrontierSWE V2 (Proximal Labs)69.9%61.2%
Furniture Assembly (Epoch AI)90%77.5%
GPQA Diamond93.9%96.5%
Mystery Game Puzzles (Epoch AI)90%73%
OTIS Mock AIME 2024-2025 (Epoch AI)99.7%100%
SimpleBench (SimpleBench)94.9%92.6%
SimpleQA Verified94%77.7%
Terminal-Bench 4.0 (Vals AI)65.2%63.1%

FAQ

Is Claude Fable 5.2 better than Gemini 4 Carbon?

Claude Fable 5.2 scores 80.8 on the Respan Index (#1), ahead of Gemini 4 Carbon at 76.1 (#3). Claude Fable 5.2 leads on 12 of the 17 benchmarks both report.

Which is cheaper, Claude Fable 5.2 or Gemini 4 Carbon?

Claude Fable 5.2 lists at $8 input and $40 output per 1M tokens; Gemini 4 Carbon at $2 and $10. Gemini 4 Carbon is 4.0x cheaper per token at list price.

Compare other models

vs

Built for AI agents.
Break less.
Ship more.