Skip to main content

Claude Fable 5.1 vs Gemini 4 Carbon

SpecClaude Fable 5.1Gemini 4 Carbon
Respan Index72.3 (#7)76.1 (#3)
Blended price per 1M$20$4
Context window1M1M
Input / output per 1M$10 / $50$2 / $10
Max output128K-
Inputtext, visiontext, image, audio, video
Released2026-09-012026-11-10

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 5.1Gemini 4 Carbon
Coding71.4 Claude Fable 5.169.3 Gemini 4 Carbon
Agents74.1 Claude Fable 5.183.5 Gemini 4 Carbon
Reasoning79.2 Claude Fable 5.184.1 Gemini 4 Carbon
Knowledge & language71.5 Claude Fable 5.177.8 Gemini 4 Carbon
Human preference59.8 Claude Fable 5.160.6 Gemini 4 Carbon

How the Respan Index works

Benchmarks both report

Gemini 4 Carbon leads on 15 of the 16 benchmarks both report. Higher is better. Each score links to where it was published.

BenchmarkClaude Fable 5.1Gemini 4 Carbon
LMArena Elo15031527
LMArena WebDev (LMArena)17411769
LMArena Agent (LMArena)0.13660.161
Chess Puzzles (Epoch AI)48%78%
APEX-Agents (Mercor)68.6%84.2%
EBR-bench (Epoch AI)57.1%87.6%
FrontierMath Tier 4 v2 (Epoch AI)87.8%95.1%
FrontierMath Tiers 1-3 v2 (Epoch AI)90.2%90.5%
FrontierSWE V2 (Proximal Labs)56.3%61.2%
Furniture Assembly (Epoch AI)70%77.5%
Mystery Game Puzzles (Epoch AI)58%73%
OTIS Mock AIME 2024-2025 (Epoch AI)100%100%
SimpleQA Verified70.8%77.7%
Terminal-Bench 4.0 (Vals AI)58.1%63.1%
Vending-Bench 2 (Andon Labs)5421.5616484.21
SimpleBench (SimpleBench)86.6%92.6%

FAQ

Is Claude Fable 5.1 better than Gemini 4 Carbon?

Gemini 4 Carbon scores 76.1 on the Respan Index (#3), ahead of Claude Fable 5.1 at 72.3 (#7). Gemini 4 Carbon leads on 15 of the 16 benchmarks both report.

Which is cheaper, Claude Fable 5.1 or Gemini 4 Carbon?

Claude Fable 5.1 lists at $10 input and $50 output per 1M tokens; Gemini 4 Carbon at $2 and $10. Gemini 4 Carbon is 5.0x cheaper per token at list price.

Which has the larger context window?

Both accept 1M tokens of context.

Compare other models

vs

Built for AI agents.
Break less.
Ship more.