RLTasksby ulam.ai
Models / OpenAI

OpenAI / MODEL EVIDENCE

o4-mini

53 benchmarks · 79 observations · 56 sources · released 2025-04-16

Scores at a glance

53 benchmarks · large dot: o4-mini; small dots: closest models where reported

MATH Level 5 ↗97.83%
3.2998.13

o4-mini (high) · MATH level 5 · Best score (across scorers) · % ↗

CadEval ↗62%
1274

o4-mini (medium) · CadEval · Overall pass (%) · % ↗

GSO ↗3.6%
026.5

o4-mini (high) · GSO-Bench · Score OPT@1 · % ↗

VPCT ↗57.5%
3091

o4-mini (medium) · VPCT · Correct · % ↗

CritPt ↗0.6%
032.29

o4-mini (high) · CritPt · Accuracy · % ↗

GDPval ↗25.3%
9.949.7

o4-mini (high) · GDPval · Win Rate (%) · % ↗

LMCA ↗26.5%
2.7868.26

o4-mini (high) · LMCA · Score · % ↗

DTBench ↗77.6%
41.6598.93

o4-mini (high) · DTBench · Accuracy · % ↗

Fortress ↗21.49%
5.7874.39

o4-mini · Scale Labs · Risk elicitation score ↗

SimpleQA ↗20.2%
7.662.5

o4-mini · SimpleQA · Correct answers · OpenAI Simple Evals · archived July 2025 ↗

HumanEval ↗97.3%
71.599.3

o4-mini · HumanEval · Pass@1 · OpenAI Simple Evals · archived July 2025 ↗

Closest models by score

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

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 code editing benchmark ↗

    Paul Gauthier, Aider contributors

  2. Aider LLM Leaderboards — Polyglot coding benchmark ↗

    Aider

  3. ARC Prize - Leaderboard ↗

    ARC Prize Foundation

  4. AIME 2025 Benchmark | Artificial Analysis ↗

    Artificial Analysis

  5. LiveCodeBench Benchmark | Artificial Analysis ↗

    Artificial Analysis

  6. MATH-500 Benchmark | Artificial Analysis ↗

    Artificial Analysis

  7. SealQA: Raising the Bar for Reasoning in Search-Augmented Language Models — published result table ↗

    Pham, Thinh, Nguyen, Nguyen, Zunjare, Pratibha, Chen, Weiyuan, Tseng, Yu-Min, Vu, Tu · 2025

  8. TextQuests: How Good are LLMs at Text-Based Video Games? — published result table ↗

    Phan, Long, Mazeika, Mantas, Zou, Andy, Hendrycks, Dan · 2025

  9. DTBench — Conceptual Reasoning Index ↗

    Conceptual Reasoning Index

  10. LMCA — Conceptual Reasoning Index ↗

    Conceptual Reasoning Index

  11. Algotune — methodology and published results ↗

    Epoch AI · 2026

  12. ARC-AGI-2 ↗

    Epoch AI

  13. Chess Puzzles ↗

    Epoch AI

  14. CritPt v1 ↗

    Epoch AI

  15. FrontierMath Tier 4 (v1, old) ↗

    Epoch AI

  16. FrontierMath Tier 4 (v2) ↗

    Epoch AI

  17. FrontierMath Tiers 1-3 (v1, old) ↗

    Epoch AI

  18. FrontierMath Tiers 1-3 (v2) ↗

    Epoch AI

  19. GDPval ↗

    Epoch AI

  20. GPQA Diamond ↗

    Epoch AI

  21. Humanity's Last Exam ↗

    Epoch AI

  22. MATH Level 5 ↗

    Epoch AI

  23. Mystery Game Puzzles ↗

    Epoch AI

  24. OTIS Mock AIME 2024-2025 ↗

    Epoch AI

  25. SimpleQA Verified ↗

    Epoch AI

  26. SimpleBench ↗

    Epoch AI

  27. Capabilities & benchmarking — retained external evaluation records ↗

    Epoch AI · 2026

  28. AI benchmarks & capabilities ↗

    Epoch AI

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

    Fiction.live · 2025

  30. GeoBench — GeoGuessr model benchmark ↗

    GeoBench

  31. Writing benchmark — incorporating mandatory story elements ↗

    lechmazur

  32. GSO: Challenging Software Optimization Tasks for Evaluating SWE-Agents ↗

    Shetty, Manish, Jain, Naman, Liu, Jinjian, Kethanaboyina, Vijay, Sen, Koushik, Stoica, Ion · 2025

  33. WeirdML ↗

    Håvard Tveit Ihle

  34. EnigmaEval ↗

    Scale Labs / SEAL

  35. Scale Labs — evaluation methodology and results ↗

    Scale Labs / SEAL · 2026

  36. Scale Labs — evaluation methodology and results ↗

    Scale Labs / SEAL · 2026

  37. Scale Labs — evaluation methodology and results ↗

    Scale Labs / SEAL · 2026

  38. Measuring AI Ability to Complete Long Software Tasks ↗

    METR

  39. BrowseComp-ZH: Benchmarking Web Browsing Ability of Large Language Models in Chinese — published result table ↗

    Peilin Zhou, Bruce Leon, Xiang Ying, Can Zhang, Yifan Shao, Qichen Ye et al. · 2025

    All 16 authors

    Peilin Zhou, Bruce Leon, Xiang Ying, Can Zhang, Yifan Shao, Qichen Ye, Dading Chong, Zhiling Jin, Chenxuan Xie, Meng Cao, Yuxin Gu, Sixin Hong, Jing Ren, Jian Chen, Chao Liu, Yining Hua

  40. Simple Evals — model benchmark results ↗

    OpenAI · 2025

  41. CadEval Dashboard — run 20250422_095709 ↗

    willpatrick · 2025

  42. AIME — evaluation methodology and results ↗

    Vals AI · 2026

  43. CorpFin — evaluation methodology and results ↗

    Vals AI · 2026

  44. GPQA Diamond — evaluation methodology and results ↗

    Vals AI · 2026

  45. LiveCodeBench — evaluation methodology and results ↗

    Vals AI · 2026

  46. LegalBench — evaluation methodology and results ↗

    Vals AI · 2026

  47. MATH 500 — evaluation methodology and results ↗

    Vals AI · 2026

  48. MedCode — evaluation methodology and results ↗

    Vals AI · 2026

  49. MedQA — evaluation methodology and results ↗

    Vals AI · 2026

  50. MedScribe — evaluation methodology and results ↗

    Vals AI · 2026

  51. MGSM — evaluation methodology and results ↗

    Vals AI · 2026

  52. MMLU Pro — evaluation methodology and results ↗

    Vals AI · 2026

  53. MMMU Pro — evaluation methodology and results ↗

    Vals AI · 2026

  54. MortgageTax — evaluation methodology and results ↗

    Vals AI · 2026

  55. SAGE — evaluation methodology and results ↗

    Vals AI · 2026

  56. TaxEval — evaluation methodology and results ↗

    Vals AI · 2026

Names used in source tables

O4-mini · o4 Mini · o4-mini · o4-mini (High) · o4-mini (high) · o4-mini (low) · o4-mini (medium)