RLTasksby ulam.ai
Models / OpenAI

OpenAI / MODEL EVIDENCE

GPT-5.4 nano

40 benchmarks · 63 observations · 42 sources · released 2026-03-17

Scores at a glance

40 benchmarks · large dot: GPT-5.4 nano; small dots: closest models where reported

IFBench ↗75.92%
75.5883.33

GPT-5.4 nano (Xhigh) · IFBench · AA implementation ↗

Mystery Game Puzzles ↗9%
99

GPT-5.4 nano (no thinking) · Mystery Game Puzzles · Best score (across scorers) · % ↗

3 more reported results

6% · GPT-5.4 nano (medium) · Mystery Game Puzzles · Best score (across scorers) · % · Epoch AI · Mystery Game Puzzles ↗

5% · GPT-5.4 nano (high) · Mystery Game Puzzles · Best score (across scorers) · % · Epoch AI · Mystery Game Puzzles ↗

3% · GPT-5.4 nano (low) · Mystery Game Puzzles · Best score (across scorers) · % · Epoch AI · Mystery Game Puzzles ↗

CritPt ↗9.25%
032.29

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

LMCA ↗36.86%
2.7868.26

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

DTBench ↗80.27%
41.6598.93

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

SciCode ↗47.22%
1.2766.9

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

Closest models by score

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

11.8 percentile-point gap

17 of 27 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. APEX-Agents-AA Benchmark | Artificial Analysis ↗

    Artificial Analysis

  3. IFBench Benchmark | Artificial Analysis ↗

    Artificial Analysis

  4. SciCode Benchmark | Artificial Analysis ↗

    Artificial Analysis

  5. DTBench — Conceptual Reasoning Index ↗

    Conceptual Reasoning Index

  6. LMCA — Conceptual Reasoning Index ↗

    Conceptual Reasoning Index

  7. ARC-AGI-2 ↗

    Epoch AI

  8. Chess Puzzles ↗

    Epoch AI

  9. CritPt v1 ↗

    Epoch AI

  10. FrontierMath Tier 4 (v1, old) ↗

    Epoch AI

  11. FrontierMath Tier 4 (v2) ↗

    Epoch AI

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

    Epoch AI

  13. FrontierMath Tiers 1-3 (v2) ↗

    Epoch AI

  14. GPQA Diamond ↗

    Epoch AI

  15. Mystery Game Puzzles ↗

    Epoch AI

  16. OTIS Mock AIME 2024-2025 ↗

    Epoch AI

  17. SimpleQA Verified ↗

    Epoch AI

  18. AI benchmarks & capabilities ↗

    Epoch AI

  19. WeirdML ↗

    Håvard Tveit Ihle

  20. AIME — evaluation methodology and results ↗

    Vals AI · 2026

  21. CaseLaw — evaluation methodology and results ↗

    Vals AI · 2026

  22. Code Migration v1 — evaluation methodology and results ↗

    Vals AI · 2026

  23. CorpFin — evaluation methodology and results ↗

    Vals AI · 2026

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

    Vals AI · 2026

  25. Finance Agent v2 — evaluation methodology and results ↗

    Vals AI · 2026

  26. GPQA Diamond — evaluation methodology and results ↗

    Vals AI · 2026

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

    Vals AI · 2026

  28. LiveCodeBench — evaluation methodology and results ↗

    Vals AI · 2026

  29. LegalBench — evaluation methodology and results ↗

    Vals AI · 2026

  30. Legal Research Bench — evaluation methodology and results ↗

    Vals AI · 2026

  31. MedCode — evaluation methodology and results ↗

    Vals AI · 2026

  32. MedScribe — evaluation methodology and results ↗

    Vals AI · 2026

  33. MMLU Pro — evaluation methodology and results ↗

    Vals AI · 2026

  34. MMMU Pro — evaluation methodology and results ↗

    Vals AI · 2026

  35. MortgageTax — evaluation methodology and results ↗

    Vals AI · 2026

  36. ProofBench — evaluation methodology and results ↗

    Vals AI · 2026

  37. SAGE — evaluation methodology and results ↗

    Vals AI · 2026

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

    Vals AI · 2026

  39. Tax Agent Bench — evaluation methodology and results ↗

    Vals AI · 2026

  40. TaxEval — evaluation methodology and results ↗

    Vals AI · 2026

  41. Vals Multimodal Index — evaluation methodology and results ↗

    Vals AI · 2026

  42. Vibe Code Bench — evaluation methodology and results ↗

    Vals AI · 2026

Names used in source tables

GPT 5.4 Nano · GPT 5.4 Nano (Mini-SWE-agent) · GPT 5.4 Nano (OpenHands) · GPT-5.4 Nano · GPT-5.4 nano (Xhigh) · GPT-5.4 nano (high) · GPT-5.4 nano (low) · GPT-5.4 nano (medium) · GPT-5.4 nano (no thinking) · GPT-5.4 nano (xhigh)