RLTasksby ulam.ai
Models / OpenAI

OpenAI / MODEL EVIDENCE

GPT-5.5

83 benchmarks · 141 observations · 90 sources · released 2026-04-23

Scores at a glance

83 benchmarks · large dot: GPT-5.5; small dots: closest models where reported

GPQA Diamond ↗93.18 %
27.0295.45

GPT 5.5 · GPQA Diamond · Accuracy ↗

4 more reported results

93.54% · GPT-5.5 (Xhigh) · GPQA Diamond · AA implementation · Artificial Analysis ↗

94% · GPT-5.5 (xhigh) · GPQA diamond · Best score (across scorers) · % · Epoch AI · GPQA diamond ↗

90.66% · GPT-5.5 (low) · GPQA diamond · Best score (across scorers) · % · Epoch AI · GPQA diamond ↗

77.27% · GPT-5.5 (no thinking) · GPQA diamond · Best score (across scorers) · % · Epoch AI · GPQA diamond ↗

IFBench ↗75.85%
75.5883.33

GPT-5.5 (Xhigh) · IFBench · AA implementation ↗

SimoBench ↗5.968 / 7
3.175.97

GPT-5.5 xhigh · SimoBench · mean progress / 7 · As published ↗

Mystery Game Puzzles ↗56%
5656

GPT-5.5 (xhigh) · Mystery Game Puzzles · Best score (across scorers) · % ↗

3 more reported results

52% · GPT-5.5 (high) · Mystery Game Puzzles · Best score (across scorers) · % · Epoch AI · Mystery Game Puzzles ↗

28% · GPT-5.5 (low) · Mystery Game Puzzles · Best score (across scorers) · % · Epoch AI · Mystery Game Puzzles ↗

18% · GPT-5.5 (no thinking) · Mystery Game Puzzles · Best score (across scorers) · % · Epoch AI · Mystery Game Puzzles ↗

MirrorCode ↗10%
8.8977.4

GPT-5.5 (high) · MirrorCode · Best score (across scorers) · % ↗

GSO ↗40.2%
9.888.24

GPT-5.5 (xhigh) · GSO-Bench · Score OPT@1 · % ↗

SimpleBench ↗69%
45.880.6

GPT-5.5 (unknown thinking) · SimpleBench · Score (AVG@5) · % ↗

Terminal-Bench 2.0 ↗84.72%
3.0784.72

GPT-5.5 (unknown thinking) · Terminal Bench · Accuracy mean · % ↗

4 more reported results

83.15% · GPT-5.5 (unknown thinking) · Terminal Bench · Accuracy mean · % · Epoch AI · Terminal Bench ↗

82.25% · GPT-5.5 (unknown thinking) · Terminal Bench · Accuracy mean · % · Epoch AI · Terminal Bench ↗

82% · GPT-5.5 (unknown thinking) · Terminal Bench · Accuracy mean · % · Epoch AI · Terminal Bench ↗

66.07% · GPT-5.5 (unknown thinking) · Terminal Bench · Accuracy mean · % · Epoch AI · Terminal Bench ↗

GBAEval ↗53.22%
53.2253.22

GPT-5.5 (unknown thinking) · GBAEval · Overall score · % ↗

LMCA ↗54.27%
2.7868.26

GPT-5.5 (xhigh) · LMCA · Score · % ↗

DTBench ↗96%
41.6598.93

GPT-5.5 (xhigh) · DTBench · Accuracy · % ↗

Vals RSI Index ↗0.29 reference score
00.46

GPT 5.5 (xhigh) · Compression · reference-anchored score ↗

3 more reported results

0.31 reference score · GPT 5.5 (xhigh) · LM training · reference-anchored score · Vals RSI Index · LM training ↗

0.06 reference score · GPT 5.5 (xhigh) · Harness engineering · reference-anchored score · Vals RSI Index · Harness engineering ↗

0.00 reference score · GPT 5.5 (xhigh) · Post-training · reference-anchored score · Vals RSI Index · Post-training ↗

Kimi Code Bench 2.0 ↗69%
64.276.9

GPT-5.5 (xhigh) · Kimi Code Bench 2.0 · score · Kimi K3 · official model-card comparison ↗

Closest models by score

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

14.2 percentile-point gap

29 of 47 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. Blueprint-Bench 2 | Andon Labs ↗

    Andon Labs

  2. ARC Prize - Leaderboard ↗

    ARC Prize Foundation

  3. Arena leaderboard — WebDev evaluation ↗

    Arena

  4. AA-AnalystAgent Benchmark | Artificial Analysis ↗

    Artificial Analysis

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

    Artificial Analysis

  6. EnterpriseOps-Gym-AA Benchmark | Artificial Analysis ↗

    Artificial Analysis

  7. GPQA Diamond Benchmark | Artificial Analysis ↗

    Artificial Analysis

  8. IFBench Benchmark | Artificial Analysis ↗

    Artificial Analysis

  9. ITBench-AA Benchmark | Artificial Analysis ↗

    Artificial Analysis

  10. MMMU-Pro Benchmark | Artificial Analysis ↗

    Artificial Analysis

  11. SciCode Benchmark | Artificial Analysis ↗

    Artificial Analysis

  12. 𝜏³-Banking Benchmark | Artificial Analysis ↗

    Artificial Analysis

  13. Terminal-Bench 2.1 Benchmark | Artificial Analysis ↗

    Artificial Analysis

  14. Terminal-Bench Hard Benchmark | Artificial Analysis ↗

    Artificial Analysis

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

    Jaffe, Oliver, Sherburn, Dane · 2026

  16. FrontierCode Leaderboard ↗

    Cognition

  17. DTBench — Conceptual Reasoning Index ↗

    Conceptual Reasoning Index

  18. LMCA — Conceptual Reasoning Index ↗

    Conceptual Reasoning Index

  19. DeepSWE ↗

    Datacurve

  20. APEX-Agents ↗

    Epoch AI

  21. ARC-AGI-2 ↗

    Epoch AI

  22. Chess Puzzles ↗

    Epoch AI

  23. CL-bench Life ↗

    Epoch AI

  24. CritPt v1 ↗

    Epoch AI

  25. Earthborne Rangers (EBR-bench) ↗

    Epoch AI

  26. ExploitBench v0.1 ↗

    Epoch AI

  27. FrontierMath Erdős ↗

    Epoch AI

  28. FrontierMath Tier 4 (v1, old) ↗

    Epoch AI

  29. FrontierMath Tier 4 (v2) ↗

    Epoch AI

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

    Epoch AI

  31. FrontierMath Tiers 1-3 (v2) ↗

    Epoch AI

  32. Furniture Assembly Benchmark ↗

    Epoch AI

  33. GPQA Diamond ↗

    Epoch AI

  34. MirrorCode ↗

    Epoch AI

  35. Mystery Game Puzzles ↗

    Epoch AI

  36. OTIS Mock AIME 2024-2025 ↗

    Epoch AI

  37. PostTrainBench v1.1 ↗

    Epoch AI

  38. Remote Labor Index ↗

    Epoch AI

  39. SimpleQA Verified ↗

    Epoch AI

  40. SWE-bench Verified ↗

    Epoch AI

  41. Vending Bench 2 — methodology and published results ↗

    Epoch AI · 2026

  42. AI benchmarks & capabilities ↗

    Epoch AI

  43. FutureSearch Evals ↗

    FutureSearch

  44. FutureSearch Evals ↗

    FutureSearch

  45. GPT-5.5 (unknown thinking) — GBA Eval ↗

    GBA Eval

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

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

  47. WeirdML ↗

    Håvard Tveit Ihle

  48. Kimi K3: Open Frontier Intelligence — official model card ↗

    Moonshot AI · 2026

  49. DrugDiscoveryBench — evaluation methodology and results ↗

    Scale Labs / SEAL · 2026

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

    Scale Labs / SEAL · 2026

  51. Scale Labs — evaluation methodology and results ↗

    Scale Labs / SEAL · 2026

  52. Scale Labs — evaluation methodology and results ↗

    Scale Labs / SEAL · 2026

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

    Scale Labs / SEAL · 2026

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

    Scale Labs / SEAL · 2026

  55. AI Model Benchmarks — LM Council ↗

    LM Council

  56. OSWorld 2.0: Benchmarking computer-use agents on long-horizon real-world tasks ↗

    OSWorld Team

  57. GDP.pdf Benchmark | Surge AI ↗

    Surge AI

  58. Terminal-Bench 2.0 leaderboard ↗

    Terminal-Bench Team

  59. SimoBench | Ulam ↗

    Ulam

  60. CaseLaw — evaluation methodology and results ↗

    Vals AI · 2026

  61. Code Migration v1 — evaluation methodology and results ↗

    Vals AI · 2026

  62. CorpFin — evaluation methodology and results ↗

    Vals AI · 2026

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

    Vals AI · 2026

  64. Finance Agent v2 — evaluation methodology and results ↗

    Vals AI · 2026

  65. GPQA Diamond — evaluation methodology and results ↗

    Vals AI · 2026

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

    Vals AI · 2026

  67. LiveCodeBench — evaluation methodology and results ↗

    Vals AI · 2026

  68. LegalBench — evaluation methodology and results ↗

    Vals AI · 2026

  69. Legal Research Bench — evaluation methodology and results ↗

    Vals AI · 2026

  70. MedCode — evaluation methodology and results ↗

    Vals AI · 2026

  71. MedScribe — evaluation methodology and results ↗

    Vals AI · 2026

  72. MMLU Pro — evaluation methodology and results ↗

    Vals AI · 2026

  73. MMMU Pro — evaluation methodology and results ↗

    Vals AI · 2026

  74. MortgageTax — evaluation methodology and results ↗

    Vals AI · 2026

  75. ProgramBench — evaluation methodology and results ↗

    Vals AI · 2026

  76. ProofBench — evaluation methodology and results ↗

    Vals AI · 2026

  77. Public Benefits Bench — evaluation methodology and results ↗

    Vals AI · 2026

  78. Public Benefits Bench v1 — evaluation methodology and results ↗

    Vals AI · 2026

  79. Vals RSI Index — evaluation methodology and results ↗

    Vals AI · 2026

  80. SAGE — evaluation methodology and results ↗

    Vals AI · 2026

  81. SkillsBench — evaluation methodology and results ↗

    Vals AI · 2026

  82. SRE Bench — evaluation methodology and results ↗

    Vals AI · 2026

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

    Vals AI · 2026

  84. Tax Agent Bench — evaluation methodology and results ↗

    Vals AI · 2026

  85. TaxEval — evaluation methodology and results ↗

    Vals AI · 2026

  86. Terminal-Bench 2.1 — evaluation methodology and results ↗

    Vals AI · 2026

  87. Time Horizon Index: KSP — evaluation methodology and results ↗

    Vals AI · 2026

  88. Vals Multimodal Index — evaluation methodology and results ↗

    Vals AI · 2026

  89. Vibe Code Bench — evaluation methodology and results ↗

    Vals AI · 2026

  90. Surface Evolver Bench ↗

    yhenon

Names used in source tables

GPT 5.5 · GPT 5.5 (Codex) · GPT 5.5 (Codex) xHigh · GPT 5.5 (Mini-SWE-agent) · GPT 5.5 (OpenHands) · GPT 5.5 (xhigh) · GPT-5.5 · GPT-5.5 (Codex) xHigh · GPT-5.5 (Codex) xhigh · GPT-5.5 (Medium) · GPT-5.5 (Xhigh) · GPT-5.5 (high) · GPT-5.5 (high, agent SDK) · GPT-5.5 (low) · GPT-5.5 (medium) · GPT-5.5 (mini-SWE-agent) xhigh · GPT-5.5 (no thinking) · GPT-5.5 (unknown thinking) · GPT-5.5 (xhigh) · GPT-5.5 xhigh · gpt-5.5 (xhigh)