RLTasksby ulam.ai
Models / OpenAI

OpenAI / MODEL EVIDENCE

GPT-5.4

82 benchmarks · 130 observations · 73 sources · released 2026-03-05

Scores at a glance

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

GPQA Diamond ↗93.3%
93.393.3

GPT-5.4 (xhigh) · GPQA diamond · Best score (across scorers) · % ↗

5 more reported results

89.9% · GPT-5.4 (high) · GPQA diamond · Best score (across scorers) · % · Epoch AI · GPQA diamond ↗

88.89% · GPT-5.4 (medium) · GPQA diamond · Best score (across scorers) · % · Epoch AI · GPQA diamond ↗

84.85% · GPT-5.4 (low) · GPQA diamond · Best score (across scorers) · % · Epoch AI · GPQA diamond ↗

91.67 % · GPT 5.4 (xhigh) · GPQA Diamond · Accuracy · Vals AI · GPQA Diamond ↗

92.8 · GPT-5.4 (xhigh) · GPQA-Diamond · Kimi K2.6 technical model card ↗

V* ↗98.4*
86.498.4

GPT-5.4 (xhigh) · V* (w/ python) ↗

OTIS Mock AIME 2024-2025 ↗97.78%
97.7897.78

GPT-5.4 (high) · OTIS Mock AIME 2024-2025 · Best score (across scorers) · % ↗

3 more reported results

95.56% · GPT-5.4 (medium) · OTIS Mock AIME 2024-2025 · Best score (across scorers) · % · Epoch AI · OTIS Mock AIME 2024-2025 ↗

95.3% · GPT-5.4 (xhigh) · OTIS Mock AIME 2024-2025 · Best score (across scorers) · % · Epoch AI · OTIS Mock AIME 2024-2025 ↗

84.44% · GPT-5.4 (low) · OTIS Mock AIME 2024-2025 · Best score (across scorers) · % · Epoch AI · OTIS Mock AIME 2024-2025 ↗

MirrorCode ↗15.56%
8.8977.4

GPT-5.4 (high) · MirrorCode · Best score (across scorers) · % ↗

GSO ↗31.37%
31.3731.37

GPT-5.4 (xhigh) · GSO-Bench · Score OPT@1 · % ↗

1 more reported result

25.49% · GPT-5.4 (high) · GSO-Bench · Score OPT@1 · % · Epoch AI · GSO-Bench ↗

GBAEval ↗45.15%
45.1545.15

GPT-5.4 (unknown thinking) · GBAEval · Overall score · % ↗

CritPt ↗23.43%
032.29

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

LMCA ↗51.97%
2.7868.26

GPT-5.4 (xhigh) · LMCA · Score · % ↗

DTBench ↗94.4%
41.6598.93

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

Vals RSI Index ↗0.25 reference score
00.46

GPT 5.4 (xhigh) · Compression · reference-anchored score ↗

3 more reported results

0.28 reference score · GPT 5.4 (xhigh) · LM training · reference-anchored score · Vals RSI Index · LM training ↗

0.09 reference score · GPT 5.4 (xhigh) · Harness engineering · reference-anchored score · Vals RSI Index · Harness engineering ↗

0.00 reference score · GPT 5.4 (xhigh) · Post-training · reference-anchored score · Vals RSI Index · Post-training ↗

MedCode ↗41.29 %
19.7263.57

GPT 5.4 (xhigh) · MedCode · Accuracy ↗

Closest models by score

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

16.7 percentile-point gap

23 of 35 shared benchmark comparisons

16.7 percentile-point gap

31 of 35 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 →

Reports featuring this model

Kimi K2.6 · earlier-2026 baseline · Kimi →

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. Blueprint-Bench 2 | Andon Labs ↗

    Andon Labs

  2. ARC Prize - Leaderboard ↗

    ARC Prize Foundation

  3. Arena leaderboard — WebDev evaluation ↗

    Arena

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

    Artificial Analysis

  5. SciCode Benchmark | Artificial Analysis ↗

    Artificial Analysis

  6. 𝜏³-Banking Benchmark | Artificial Analysis ↗

    Artificial Analysis

  7. Terminal-Bench Hard Benchmark | Artificial Analysis ↗

    Artificial Analysis

  8. OfficeQA Pro: An Enterprise Benchmark for End-to-End Grounded Reasoning — published result table ↗

    Opsahl-Ong, Krista, Singhvi, Arnav, Collins, Jasmine, Zhou, Ivan, Wang, Cindy, Baheti, Ashutosh et al. · 2026

    All 13 authors

    Opsahl-Ong, Krista, Singhvi, Arnav, Collins, Jasmine, Zhou, Ivan, Wang, Cindy, Baheti, Ashutosh, Oertell, Owen, Portes, Jacob, Havens, Sam, Elsen, Erich, Bendersky, Michael, Zaharia, Matei, Chen, Xing

  9. TasteVal: Measuring the Experimental Research Taste of AI Systems Against Human Experts — published result table ↗

    Jaffe, Oliver, Sherburn, Dane · 2026

  10. DTBench — Conceptual Reasoning Index ↗

    Conceptual Reasoning Index

  11. LMCA — Conceptual Reasoning Index ↗

    Conceptual Reasoning Index

  12. DeepSWE ↗

    Datacurve

  13. Algotune — methodology and published results ↗

    Epoch AI · 2026

  14. APEX-Agents ↗

    Epoch AI

  15. ARC-AGI-1 ↗

    Epoch AI

  16. ARC-AGI-2 ↗

    Epoch AI

  17. Chess Puzzles ↗

    Epoch AI

  18. CL-bench ↗

    Epoch AI

  19. CL-bench Life ↗

    Epoch AI

  20. CritPt v1 ↗

    Epoch AI

  21. Earthborne Rangers (EBR-bench) ↗

    Epoch AI

  22. FrontierMath Tier 4 (v1, old) ↗

    Epoch AI

  23. FrontierMath Tier 4 (v2) ↗

    Epoch AI

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

    Epoch AI

  25. FrontierMath Tiers 1-3 (v2) ↗

    Epoch AI

  26. Furniture Assembly Benchmark ↗

    Epoch AI

  27. GPQA Diamond ↗

    Epoch AI

  28. Humanity's Last Exam ↗

    Epoch AI

  29. MirrorCode ↗

    Epoch AI

  30. Mystery Game Puzzles ↗

    Epoch AI

  31. OTIS Mock AIME 2024-2025 ↗

    Epoch AI

  32. PostTrainBench v1.1 ↗

    Epoch AI

  33. SimpleQA Verified ↗

    Epoch AI

  34. SWE-bench Verified ↗

    Epoch AI

  35. Vending Bench 2 — methodology and published results ↗

    Epoch AI · 2026

  36. AI benchmarks & capabilities ↗

    Epoch AI

  37. FutureSearch Evals ↗

    FutureSearch

  38. GPT-5.4 (unknown thinking) — GBA Eval ↗

    GBA Eval

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

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

  40. WeirdML ↗

    Håvard Tveit Ihle

  41. moonshotai/Kimi-K2.6 · Hugging Face ↗

    Moonshot AI

  42. EnigmaEval ↗

    Scale Labs / SEAL

  43. HiL-Bench (Human-in-Loop Benchmark) — evaluation methodology and results ↗

    Scale Labs / SEAL · 2026

  44. Scale Labs — evaluation methodology and results ↗

    Scale Labs / SEAL · 2026

  45. Scale Labs — evaluation methodology and results ↗

    Scale Labs / SEAL · 2026

  46. Scale Labs — evaluation methodology and results ↗

    Scale Labs / SEAL · 2026

  47. Scale Labs — evaluation methodology and results ↗

    Scale Labs / SEAL · 2026

  48. SWE Atlas - Refactoring — evaluation methodology and results ↗

    Scale Labs / SEAL · 2026

  49. SWE Atlas - Test Writing — evaluation methodology and results ↗

    Scale Labs / SEAL · 2026

  50. Measuring AI Ability to Complete Long Software Tasks ↗

    METR

  51. Terminal-Bench 2.0 leaderboard ↗

    Terminal-Bench Team

  52. AIME — evaluation methodology and results ↗

    Vals AI · 2026

  53. CaseLaw — evaluation methodology and results ↗

    Vals AI · 2026

  54. Code Migration v1 — evaluation methodology and results ↗

    Vals AI · 2026

  55. CorpFin — evaluation methodology and results ↗

    Vals AI · 2026

  56. GPQA Diamond — evaluation methodology and results ↗

    Vals AI · 2026

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

    Vals AI · 2026

  58. LiveCodeBench — evaluation methodology and results ↗

    Vals AI · 2026

  59. LegalBench — evaluation methodology and results ↗

    Vals AI · 2026

  60. MedCode — evaluation methodology and results ↗

    Vals AI · 2026

  61. MedQA — evaluation methodology and results ↗

    Vals AI · 2026

  62. MedScribe — evaluation methodology and results ↗

    Vals AI · 2026

  63. MMLU Pro — evaluation methodology and results ↗

    Vals AI · 2026

  64. MMMU Pro — evaluation methodology and results ↗

    Vals AI · 2026

  65. MortgageTax — evaluation methodology and results ↗

    Vals AI · 2026

  66. ProgramBench — evaluation methodology and results ↗

    Vals AI · 2026

  67. ProofBench — evaluation methodology and results ↗

    Vals AI · 2026

  68. Vals RSI Index — evaluation methodology and results ↗

    Vals AI · 2026

  69. SAGE — evaluation methodology and results ↗

    Vals AI · 2026

  70. SkillsBench — evaluation methodology and results ↗

    Vals AI · 2026

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

    Vals AI · 2026

  72. TaxEval — evaluation methodology and results ↗

    Vals AI · 2026

  73. Vibe Code Bench — evaluation methodology and results ↗

    Vals AI · 2026

Names used in source tables

GPT 5.4 · GPT 5.4 (Codex) · GPT 5.4 (Codex) xHigh · GPT 5.4 (high) · GPT 5.4 (xhigh) · GPT 5.4 (xhigh) (Mini-SWE-agent) · GPT 5.4 (xhigh) (OpenHands) · GPT-5.4 · GPT-5.4 (Codex) xHigh · GPT-5.4 (Xhigh) · GPT-5.4 (high) · GPT-5.4 (low) · GPT-5.4 (medium) · GPT-5.4 (unknown thinking) · GPT-5.4 (xhigh) · Gpt 5.4 xHigh (Mini-SWE-Agent) · gpt-5.4 (High) · gpt-5.4 (xhigh)