Llama-3.1-8B vs Qwen3-32B in finance

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

Shared benchmarks
2
Llama-3.1-8B only
0
Qwen3-32B only
1

Shared benchmarks, side by side

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

  • Llama-3.1-8B
  • Qwen3-32B

  • FAITH overall accuracy %, higher is better

    Llama-3.1-8B:47.5
    Qwen3-32B:73.9 (better)

  • K-FinHallu binary detection F1, higher is better

    Llama-3.1-8B:0.674
    Qwen3-32B:0.732 (better)
Benchmark
Llama-3.1-8B
Qwen3-32B

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

FAITHoverall accuracy %, higher is better
47.5
Paper Table 3 (Reported by the authors, 24 Oct 2025)
73.9
Paper Table 3 (Reported by the authors, 24 Oct 2025)
K-FinHallubinary detection F1, higher is better
0.674
Paper Table 3 (Reported by the authors, 28 May 2026)
0.732
Paper Table 3 (Reported by the authors, 28 May 2026)
BizFinBenchaverage score across 9 tasks, higher is better
Not scored
68.3
Paper Table 3 (Reported by the authors, 26 May 2025)

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