Comparing 2 models

Claude Fable 5.2 vs Gemini 3.1 Pro Preview

Benchmarks through

Verdict

Claude Fable 5.2 and Gemini 3.1 Pro Preview are not yet ranked on the same task, so compare the specifications below. Gemini 3.1 Pro Preview costs 4.0x less per input token. Gemini 3.1 Pro Preview accepts 1.0x more context.

Built from the published task rankings below; ranks come from each task's own weighted benchmarks, so a win on one task says nothing about another.

metric
Model 1Claude Fable 5.2
Model 2Gemini 3.1 Pro Preview
Best for
Agentic Coding (#1)
Business Writing (#3)
Provider
anthropic
google
Context
1M
1.0MBest
Input / 1M
$8
$2Best
Output / 1M
$40
$12Best
Tool use
yesBest
yesBest
Vision
yesBest
yesBest
Reasoning
yesBest
yesBest
Open-weight
—
—
Released
Nov 9, 2026
Feb 19, 2026

Measured head to head

Benchmarks both models were run on

EvaluationClaude Fable 5.2Gemini 3.1 Pro PreviewSource
Design Arena Coding1375 Elo1220 Elosource · 2026-11-15
Design Arena Full-stack Agent1400 Elo1041 Elosource · 2026-11-15
Design Arena UI1382 Elo1215 Elosource · 2026-11-15
Design Arena Website1352 Elo1225 Elosource · 2026-11-15
FrontierMath Tiers 1-3 (Epoch AI)95.1% ± 1.359.6% ± 2.9source · 2026-11-06
GPQA Diamond (Epoch AI)93.9% ± 1.694.1% ± 1.7source · 2026-11-06
LMArena Agent30.4-4.5source · 2026-11-11
LMArena Agent Steerability33-8.2source · 2026-11-11
LMArena Agent Task Outcome22-11.3source · 2026-11-11
LMArena Agent Tool Hallucination1-0.4source · 2026-11-11
LMArena WebDev1838 Elo1446 Elosource · 2026-11-11
OTIS Mock AIME (Epoch AI)99.7% ± 0.395.6% ± 3.1source · 2026-11-06
SimpleQA Verified (Epoch AI)94% ± 0.873.5% ± 1.4source · 2026-11-06

Values are as published by each evaluator, in its own units; rows from different evaluators are not on a common scale.