The honest view from inside technical leadership
LLM Leaderboard · Head to head

GPT-6.1 Terra vs Claude Fable 5.2

Claude Fable 5.2 scores higher on the CTO Index (95.5 vs 73.3). Across the 3 benchmarks both have results, GPT-6.1 Terra wins 0 and Claude Fable 5.2 wins 3 (Terminal-Bench, WebDev, Text Arena). GPT-6.1 Terra costs 88% less per blended token.

← All models

GPT-6.1 TerraClaude Fable 5.2
CTO Index73.3 (#16)95.5 (#1)
ProviderOpenAIAnthropic
WeightsClosedClosed
Price $/M in / out$1 / $5$8 / $40
Context window1.1M1M
LicenseProprietaryProprietary
Terminal-Bench 4.153.3%65.8%
WebDev Arena16851824
ARC-AGI-2—93.8%
Text Arena14741503
ARC-AGI-3—81.2%

Snapshot 22 November 2026 · Scores copied from each benchmark's own leaderboard · How the CTO Index works

Frequently asked questions

Is GPT-6.1 Terra better than Claude Fable 5.2?

Claude Fable 5.2 scores higher on the CTO Index (95.5 vs 73.3). Across the 3 benchmarks both have results, GPT-6.1 Terra wins 0 and Claude Fable 5.2 wins 3 (Terminal-Bench, WebDev, Text Arena). GPT-6.1 Terra costs 88% less per blended token.

Which is better for coding agents, GPT-6.1 Terra or Claude Fable 5.2?

On Terminal-Bench 4.1, Claude Fable 5.2 scores 65.8% against GPT-6.1 Terra's 53.3%. Differences under about three points are within the error bars.

How do GPT-6.1 Terra and Claude Fable 5.2 compare on price?

GPT-6.1 Terra lists at $1 / $5 and Claude Fable 5.2 at $8 / $40 per million input / output tokens.