RLTasksby ulam.ai
Models / OpenAI

OpenAI / MODEL EVIDENCE

GPT-4.5 Preview (Feb 2025)

15 benchmarks · 15 observations · 15 sources · released 2025-02-27

Scores at a glance

15 benchmarks · large dot: GPT-4.5 Preview (Feb 2025); small dots: closest models where reported

GPQA Diamond ↗68.69%
9.2896.4

GPT-4.5 Preview (Feb 2025) · GPQA diamond · Best score (across scorers) · % ↗

MATH Level 5 ↗78.63%
3.2998.13

GPT-4.5 Preview (Feb 2025) · MATH level 5 · Best score (across scorers) · % ↗

Cybench ↗17.5%
555

GPT-4.5 Preview (Feb 2025) · Cybench · Unguided % Solved · % ↗

SimpleBench ↗34.5%
10.781.9

GPT-4.5 Preview (Feb 2025) · SimpleBench · Score (AVG@5) · % ↗

VPCT ↗45%
3091

GPT-4.5 Preview (Feb 2025) · VPCT · Correct · % ↗

LiveBench ↗68.95%
22.0882.35

GPT-4.5 Preview (Feb 2025) · LiveBench · Global average · % ↗

EnigmaEval ↗3.18%
0.3839.28

GPT-4.5 Preview (Feb 2025) · EnigmaEval · Accuracy · % ↗

Closest models by score

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

2.1 percentile-point gap

3 of 3 shared benchmark comparisons

How similarity is measured

Mean absolute gap in percentile positions on shared benchmark settings; lower is closer. At least 60% overlap is required, with a minimum of three when available. Independent evaluations are used when there are at least three; otherwise published report comparisons are used. Repeated model observations within one setting are averaged before ranking. Writing-style traits and composite indices are excluded. This describes similarity, not an overall quality ranking.

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 LLM Leaderboards — Polyglot coding benchmark ↗

    Aider

  2. ARC Prize - Leaderboard ↗

    ARC Prize Foundation

  3. Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models ↗

    Zhang, Andy K., Perry, Neil, Dulepet, Riya, Ji, Joey, Menders, Celeste, Lin, Justin W. et al. · 2024

    All 27 authors

    Zhang, Andy K., Perry, Neil, Dulepet, Riya, Ji, Joey, Menders, Celeste, Lin, Justin W., Jones, Eliot, Hussein, Gashon, Liu, Samantha, Jasper, Donovan, Peetathawatchai, Pura, Glenn, Ari, Sivashankar, Vikram, Zamoshchin, Daniel, Glikbarg, Leo, Askaryar, Derek, Yang, Mike, Zhang, Teddy, Alluri, Rishi, Tran, Nathan, Sangpisit, Rinnara, Yiorkadjis, Polycarpos, Osele, Kenny, Raghupathi, Gautham, Boneh, Dan, Ho, Daniel E., Liang, Percy

  4. ARC-AGI-2 ↗

    Epoch AI

  5. GPQA Diamond ↗

    Epoch AI

  6. Humanity's Last Exam ↗

    Epoch AI

  7. MATH Level 5 ↗

    Epoch AI

  8. OTIS Mock AIME 2024-2025 ↗

    Epoch AI

  9. SimpleBench ↗

    Epoch AI

  10. Capabilities & benchmarking — retained external evaluation records ↗

    Epoch AI · 2026

  11. Fiction.liveBench — March 14, 2025 benchmark release ↗

    Fiction.live · 2025

  12. Writing benchmark — incorporating mandatory story elements ↗

    lechmazur

  13. WeirdML ↗

    Håvard Tveit Ihle

  14. EnigmaEval ↗

    Scale Labs / SEAL

  15. LiveBench — model evaluation leaderboard ↗

    LiveBench Team

Names used in source tables

GPT-4.5 Preview (Feb 2025)