GLM-5.1 vs Kimi K2.6

Every finance benchmark where both have a score (Zhipu AI and Moonshot AI). Data refreshed 2 Nov 2026.

Shared benchmarks
3
GLM-5.1 only
0
Kimi K2.6 only
0

Shared benchmarks, side by side

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

  • GLM-5.1
  • Kimi K2.6

  • IPO Finance Agent mean rubric score %, higher is better

    GLM-5.1:79.7 (better)
    Kimi K2.6:68

  • KTD-Fin total return %, higher is better

    GLM-5.1:-3.5 (better)
    Kimi K2.6:-24.2

  • PortBench CEPS (0-1), higher is better

    GLM-5.1:0.384 (better)
    Kimi K2.6:0.274

  • PortBench mean QA score (0-1), higher is better

    GLM-5.1:0.757 (better)
    Kimi K2.6:0.511
Benchmark
GLM-5.1
Kimi K2.6

4 benchmarks, 4 scored for both. Bold marks the better score where both have one.

IPO Finance Agentmean rubric score %, higher is better
79.7
Paper Table 1 (Reported by the authors, 30 Jun 2026)
68
Paper Table 1 (Reported by the authors, 30 Jun 2026)
KTD-Fintotal return %, higher is better
-3.5
Paper Table 4 (Reported by the authors, 27 May 2026)
-24.2
Paper Table 4 (Reported by the authors, 27 May 2026)
PortBenchCEPS (0-1), higher is better
0.384
Paper Table 2 (Reported by the authors, 9 Oct 2026)
0.274
Paper Table 2 (Reported by the authors, 9 Oct 2026)
PortBenchmean QA score (0-1), higher is better
0.757
Paper Table 1 (Reported by the authors, 9 Oct 2026)
0.511
Paper Table 1 (Reported by the authors, 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.