Claude Fable 5.1 vs GPT-6 Astra in finance

Every finance benchmark where both have a score (Anthropic and OpenAI). Data refreshed 2 Nov 2026.

Shared benchmarks
2
Claude Fable 5.1 only
2
GPT-6 Astra only
1

Shared benchmarks, side by side

Each benchmark is drawn on its own scale. Bars are not comparable across rows.

  • Claude Fable 5.1
  • GPT-6 Astra

  • Ramp Accounting Bench mean reward % (criteria, mean of 3 attempts), higher is better

    Claude Fable 5.1:49.7 (better)
    GPT-6 Astra:48.7

  • Excel Modeling Benchmark (EMB) accuracy % (v1.1), higher is better

    Claude Fable 5.1:76.7 (better)
    GPT-6 Astra:72.7
Benchmark
Claude Fable 5.1
GPT-6 Astra

5 benchmarks, 2 scored for both. Bold marks the better score where both have one.

Ramp Accounting Benchmean reward % (criteria, mean of 3 attempts), higher is better
49.7
Ramp Labs Accounting Bench (Official board, 2 Sept 2026)
48.7
Ramp Labs Accounting Bench (Official board, 5 Sept 2026)
Excel Modeling Benchmark (EMB)accuracy % (v1.1), higher is better
76.7
Vals.ai leaderboard (Official board, 29 Oct 2026)
72.7
Vals.ai leaderboard (Official board, 29 Oct 2026)
APEX-AccountingMean Score (% criteria passed), higher is better
Not scored
64.7
Mercor APEX-Accounting leaderboard (Official board, 1 Nov 2026)
MortgageTaxaccuracy %, higher is better
70.8
Vals.ai MortgageTax leaderboard (Official board, 1 Sept 2026)
Not scored
Tax Agent Benchaccuracy % (all-pass x citation factor), higher is better
49.2
Vals.ai leaderboard (Official board, 29 Oct 2026)
Not scored

Scores from different benchmarks use different scales and are not added up. Settings can differ between sources; see each leaderboard for details.