RLTasksby ulam.ai
Models / OpenAI

OpenAI / MODEL EVIDENCE

GPT-5.4 mini

45 benchmarks · 60 observations · 47 sources · released 2026-03-17

Scores at a glance

45 benchmarks · large dot: GPT-5.4 mini; small dots: closest models where reported

ITBench-AA ↗35.22%
35.2256.21

GPT-5.4 mini (Xhigh) · ITBench-AA · root-cause score ↗

CritPt ↗10%
032.29

GPT-5.4 mini (xhigh) · CritPt · Accuracy · % ↗

LMCA ↗40.79%
2.7868.26

GPT-5.4 mini (xhigh) · LMCA · Score · % ↗

DTBench ↗80%
41.6598.93

GPT-5.4 mini (xhigh) · DTBench · Accuracy · % ↗

SciCode ↗52.08%
1.2766.9

GPT-5.4 mini (xhigh) · SciCode · Score · % ↗

Closest models by score

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

17.1 percentile-point gap

18 of 29 shared benchmark comparisons

20.5 percentile-point gap

20 of 29 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. ARC Prize - Leaderboard ↗

    ARC Prize Foundation

  2. Arena leaderboard — WebDev evaluation ↗

    Arena

  3. APEX-Agents-AA Benchmark | Artificial Analysis ↗

    Artificial Analysis

  4. Global-MMLU-Lite Benchmark | Artificial Analysis ↗

    Artificial Analysis

  5. ITBench-AA Benchmark | Artificial Analysis ↗

    Artificial Analysis

  6. SciCode Benchmark | Artificial Analysis ↗

    Artificial Analysis

  7. Terminal-Bench Hard Benchmark | Artificial Analysis ↗

    Artificial Analysis

  8. FrontierCode Leaderboard ↗

    Cognition

  9. DTBench — Conceptual Reasoning Index ↗

    Conceptual Reasoning Index

  10. LMCA — Conceptual Reasoning Index ↗

    Conceptual Reasoning Index

  11. ARC-AGI-2 ↗

    Epoch AI

  12. Chess Puzzles ↗

    Epoch AI

  13. CritPt v1 ↗

    Epoch AI

  14. FrontierMath Tier 4 (v1, old) ↗

    Epoch AI

  15. FrontierMath Tier 4 (v2) ↗

    Epoch AI

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

    Epoch AI

  17. FrontierMath Tiers 1-3 (v2) ↗

    Epoch AI

  18. GPQA Diamond ↗

    Epoch AI

  19. Mystery Game Puzzles ↗

    Epoch AI

  20. OTIS Mock AIME 2024-2025 ↗

    Epoch AI

  21. SimpleQA Verified ↗

    Epoch AI

  22. AI benchmarks & capabilities ↗

    Epoch AI

  23. FutureSearch Evals ↗

    FutureSearch

  24. WeirdML ↗

    Håvard Tveit Ihle

  25. Scale Labs — evaluation methodology and results ↗

    Scale Labs / SEAL · 2026

  26. AIME — evaluation methodology and results ↗

    Vals AI · 2026

  27. CaseLaw — evaluation methodology and results ↗

    Vals AI · 2026

  28. Code Migration v1 — evaluation methodology and results ↗

    Vals AI · 2026

  29. CorpFin — evaluation methodology and results ↗

    Vals AI · 2026

  30. Excel Modeling Benchmark v1 — evaluation methodology and results ↗

    Vals AI · 2026

  31. Finance Agent v2 — evaluation methodology and results ↗

    Vals AI · 2026

  32. GPQA Diamond — evaluation methodology and results ↗

    Vals AI · 2026

  33. Harvey's Legal Agent Benchmark v1 — evaluation methodology and results ↗

    Vals AI · 2026

  34. LiveCodeBench — evaluation methodology and results ↗

    Vals AI · 2026

  35. Legal Research Bench — evaluation methodology and results ↗

    Vals AI · 2026

  36. MMLU Pro — evaluation methodology and results ↗

    Vals AI · 2026

  37. MMMU Pro — evaluation methodology and results ↗

    Vals AI · 2026

  38. MortgageTax — evaluation methodology and results ↗

    Vals AI · 2026

  39. ProgramBench — evaluation methodology and results ↗

    Vals AI · 2026

  40. ProofBench — evaluation methodology and results ↗

    Vals AI · 2026

  41. SAGE — evaluation methodology and results ↗

    Vals AI · 2026

  42. SWE-bench Verified — evaluation methodology and results ↗

    Vals AI · 2026

  43. Tax Agent Bench — evaluation methodology and results ↗

    Vals AI · 2026

  44. TaxEval — evaluation methodology and results ↗

    Vals AI · 2026

  45. Terminal-Bench 4.0 — evaluation methodology and results ↗

    Vals AI · 2026

  46. Vals Multimodal Index — evaluation methodology and results ↗

    Vals AI · 2026

  47. Vibe Code Bench — evaluation methodology and results ↗

    Vals AI · 2026

Names used in source tables

GPT 5.4 Mini · GPT 5.4 Mini (Mini-SWE-agent) · GPT 5.4 Mini (OpenHands) · GPT-5.4 Mini · GPT-5.4 mini (Xhigh) · GPT-5.4 mini (high) · GPT-5.4 mini (low) · GPT-5.4 mini (medium) · GPT-5.4 mini (unknown thinking) · GPT-5.4 mini (xhigh) · gpt-5.4-mini (xhigh)