Claude2 vs Numa 1 in finance

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

Shared benchmarks
1
Claude2 only
0
Numa 1 only
6

Shared benchmarks, side by side

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

  • Claude2
  • Numa 1
    Benchmark
    Claude2
    Numa 1

    9 benchmarks, 0 scored for both. Bold marks the better score where both have one.

    FinanceQAaccuracy (total, 0-1), higher is better
    Not scored
    0.355
    Moneda run, 2026-11-01 (Run by Moneda, 1 Nov 2026)
    FinanceBench% correct, no filing given (150-question sample), higher is better
    Not scored
    67
    Moneda run, 2026-11-02 (Run by Moneda, 2 Nov 2026)
    FinanceBench% correct, the right filing given (150-question sample), higher is better
    76
    Paper Table 2 (Reported by the authors, 20 Nov 2023)
    Not scored
    FinSearchCompGlobal subset average accuracy %, higher is better
    Not scored
    59.4
    Moneda run, 2026-11-01 (Run by Moneda, 1 Nov 2026)
    FinSearchCompGreater China subset average accuracy %, higher is better
    Not scored
    57.1
    Moneda run, 2026-11-01 (Run by Moneda, 1 Nov 2026)
    Moneda CiteBenchFactual share of linked claims %, higher is better
    Not scored
    63.3
    Moneda run, 2026-11-02 (Run by Moneda, 2 Nov 2026)
    Moneda FilingsBench% correct (private split), higher is better
    Not scored
    91.6
    Moneda run, 2026-11-02 (Run by Moneda, 2 Nov 2026)
    Moneda PortfolioBenchPortfolio tasks, % correct, higher is better
    Not scored
    96
    Moneda run, 2026-11-01 (Run by Moneda, 1 Nov 2026)
    Finance Agent BenchmarkPartial credit % on the 27 public questions (run by Moneda; not comparable, unranked), higher is better
    Not scored
    80.2
    Moneda run, 2026-10-09 (Run by Moneda, 9 Oct 2026)

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