RLTasksby ulam.ai
Models / OpenAI

OpenAI / MODEL EVIDENCE

GPT-4.5 Preview

3 benchmarks · 6 observations · 3 sources

Scores at a glance

3 benchmarks · large dot: GPT-4.5 Preview; small dots: closest models where reported

PolyMath ↗14.7%
5.740.3

GPT-4.5-preview† · PolyMath · PolyMath-Top · Mean accuracy across the published languages ↗

3 more reported results

27.4% · GPT-4.5-preview† · PolyMath · PolyMath-High · Mean accuracy across the published languages · PolyMath: Evaluating Mathematical Reasoning in Multilingual Contexts ↗

42.9% · GPT-4.5-preview† · PolyMath · PolyMath-Medium · Mean accuracy across the published languages · PolyMath: Evaluating Mathematical Reasoning in Multilingual Contexts ↗

91.5% · GPT-4.5-preview† · PolyMath · PolyMath-Low · Mean accuracy across the published languages · PolyMath: Evaluating Mathematical Reasoning in Multilingual Contexts ↗

Closest models by score

Similar positions on shared benchmark leaderboards. Smaller gaps are closer.

There are not enough shared scored settings to identify close comparisons reliably.

Filter comparisons to this model →

Sources

Every plotted observation links to its evaluation. Reported configurations, benchmark versions and task subsets can differ; similarity describes shared scores, not training lift.

  1. Aider code editing benchmark ↗

    Paul Gauthier, Aider contributors

  2. PolyMath: Evaluating Mathematical Reasoning in Multilingual Contexts — published result table ↗

    Yiming Wang, Pei Zhang, Jialong Tang, Haoran Wei, Baosong Yang, Rui Wang et al. · 2025

    All 16 authors

    Yiming Wang, Pei Zhang, Jialong Tang, Haoran Wei, Baosong Yang, Rui Wang, Chenshu Sun, Feitong Sun, Jiran Zhang, Junxuan Wu, Qiqian Cang, Yichang Zhang, Fei Huang, Junyang Lin, Fei Huang, Jingren Zhou

  3. Scale Labs — evaluation methodology and results ↗

    Scale Labs / SEAL · 2026

Names used in source tables

GPT 4.5 Preview · GPT-4.5-preview† · gpt-4.5-preview