RLTasksby ulam.ai
Models / OpenAI

OpenAI / MODEL EVIDENCE

GPT-5.1

48 benchmarks · 85 observations · 56 sources · released 2025-11-13

Scores at a glance

48 benchmarks · large dot: GPT-5.1; small dots: closest models where reported

FrontierMath Tiers 1-3 (v1, old) ↗31.03%
31.0331.03

GPT-5.1 (high) · FrontierMath-2025-02-28-Private · Best score (across scorers) · % ↗

3 more reported results

26.9% · GPT-5.1 (medium) · FrontierMath-2025-02-28-Private · Best score (across scorers) · % · Epoch AI · FrontierMath-2025-02-28-Private ↗

17.3% · GPT-5.1 (low) · FrontierMath-2025-02-28-Private · Best score (across scorers) · % · Epoch AI · FrontierMath-2025-02-28-Private ↗

2.1% · GPT-5.1 (no thinking) · FrontierMath-2025-02-28-Private · Best score (across scorers) · % · Epoch AI · FrontierMath-2025-02-28-Private ↗

OTIS Mock AIME 2024-2025 ↗88.61%
88.6188.61

GPT-5.1 (high) · OTIS Mock AIME 2024-2025 · Best score (across scorers) · % ↗

3 more reported results

85.56% · GPT-5.1 (medium) · OTIS Mock AIME 2024-2025 · Best score (across scorers) · % · Epoch AI · OTIS Mock AIME 2024-2025 ↗

63.89% · GPT-5.1 (low) · OTIS Mock AIME 2024-2025 · Best score (across scorers) · % · Epoch AI · OTIS Mock AIME 2024-2025 ↗

37.78% · GPT-5.1 (no thinking) · OTIS Mock AIME 2024-2025 · Best score (across scorers) · % · Epoch AI · OTIS Mock AIME 2024-2025 ↗

ARC-AGI-1 ↗72.83%
72.872.83

GPT-5.1 (high) · ARC-AGI · Score · % ↗

6 more reported results

72.8% · GPT-5.1 (high) · ARC-AGI · Score · % · Epoch AI · ARC-AGI ↗

57.7% · GPT-5.1 (medium) · ARC-AGI · Score · % · Epoch AI · ARC-AGI ↗

57.67% · GPT-5.1 (medium) · ARC-AGI · Score · % · Epoch AI · ARC-AGI ↗

33.1% · GPT-5.1 (Low) · ARC-AGI · Score · % · Epoch AI · ARC-AGI ↗

33.17% · GPT-5.1 (low) · ARC-AGI · Score · % · Epoch AI · ARC-AGI ↗

5.83% · GPT-5.1 (no thinking) · ARC-AGI · Score · % · Epoch AI · ARC-AGI ↗

GSO ↗13.73%
9.888.24

GPT-5.1 (unknown thinking) · GSO-Bench · Score OPT@1 · % ↗

1 more reported result

13.7% · GPT-5.1 (high) · GSO-Bench · Score OPT@1 · % · Epoch AI · GSO-Bench ↗

VPCT ↗58.7%
58.758.7

GPT-5.1 (high) · VPCT · Correct · % ↗

1 more reported result

53.3% · GPT-5.1 (medium) · VPCT · Correct · % · Epoch AI · VPCT ↗

CritPt ↗4.86%
032.29

GPT-5.1 (unknown thinking) · CritPt · Accuracy · % ↗

LMCA ↗43.89%
2.7868.26

GPT-5.1 (high) · LMCA · Score · % ↗

DTBench ↗90.13%
41.6598.93

GPT-5.1 (high) · DTBench · Accuracy · % ↗

LiveBench ↗78.79%
22.0882.35

GPT-5.1 (high) · LiveBench · Global average · % ↗

SciCode ↗43.29%
1.2766.9

GPT-5.1 (unknown thinking) · SciCode · Score · % ↗

Closest models by score

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

GPT-5 →OpenAI
9.4 percentile-point gap

19 of 22 shared benchmark comparisons

o3 →OpenAI
17.3 percentile-point gap

15 of 22 shared benchmark comparisons

17.9 percentile-point gap

14 of 22 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. AIME 2025 Benchmark | Artificial Analysis ↗

    Artificial Analysis

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

    Artificial Analysis

  5. LiveCodeBench Benchmark | Artificial Analysis ↗

    Artificial Analysis

  6. MMLU-Pro Benchmark | Artificial Analysis ↗

    Artificial Analysis

  7. SciCode Benchmark | Artificial Analysis ↗

    Artificial Analysis

  8. Terminal-Bench Hard Benchmark | Artificial Analysis ↗

    Artificial Analysis

  9. 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

  10. DTBench — Conceptual Reasoning Index ↗

    Conceptual Reasoning Index

  11. LMCA — Conceptual Reasoning Index ↗

    Conceptual Reasoning Index

  12. ARC-AGI-1 ↗

    Epoch AI

  13. ARC-AGI-2 ↗

    Epoch AI

  14. Chess Puzzles ↗

    Epoch AI

  15. CL-bench ↗

    Epoch AI

  16. CL-bench Life ↗

    Epoch AI

  17. CritPt v1 ↗

    Epoch AI

  18. FrontierMath Tier 4 (v1, old) ↗

    Epoch AI

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

    Epoch AI

  20. GPQA Diamond ↗

    Epoch AI

  21. Humanity's Last Exam ↗

    Epoch AI

  22. Mystery Game Puzzles ↗

    Epoch AI

  23. OTIS Mock AIME 2024-2025 ↗

    Epoch AI

  24. SimpleQA Verified ↗

    Epoch AI

  25. SWE-bench Verified ↗

    Epoch AI

  26. Terminal-Bench 2.0 ↗

    Epoch AI

  27. Capabilities & benchmarking — retained external evaluation records ↗

    Epoch AI · 2026

  28. Vending Bench 2 — methodology and published results ↗

    Epoch AI · 2026

  29. Text Arena (Coding) ↗

    Epoch AI

  30. AI benchmarks & capabilities ↗

    Epoch AI

  31. FutureSearch Evals ↗

    FutureSearch

  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. LiveBench — model evaluation leaderboard ↗

    LiveBench Team

  37. AI Model Benchmarks — LM Council ↗

    LM Council

  38. Terminal-Bench 2.0 leaderboard ↗

    Terminal-Bench Team

  39. AIME — evaluation methodology and results ↗

    Vals AI · 2026

  40. CaseLaw — evaluation methodology and results ↗

    Vals AI · 2026

  41. CorpFin — evaluation methodology and results ↗

    Vals AI · 2026

  42. GPQA Diamond — evaluation methodology and results ↗

    Vals AI · 2026

  43. LiveCodeBench — evaluation methodology and results ↗

    Vals AI · 2026

  44. LegalBench — evaluation methodology and results ↗

    Vals AI · 2026

  45. MedCode — evaluation methodology and results ↗

    Vals AI · 2026

  46. MedQA — evaluation methodology and results ↗

    Vals AI · 2026

  47. MedScribe — evaluation methodology and results ↗

    Vals AI · 2026

  48. MGSM — evaluation methodology and results ↗

    Vals AI · 2026

  49. MMLU Pro — evaluation methodology and results ↗

    Vals AI · 2026

  50. MMMU Pro — evaluation methodology and results ↗

    Vals AI · 2026

  51. MortgageTax — evaluation methodology and results ↗

    Vals AI · 2026

  52. Poker Agent — evaluation methodology and results ↗

    Vals AI · 2026

  53. SAGE — evaluation methodology and results ↗

    Vals AI · 2026

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

    Vals AI · 2026

  55. TaxEval — evaluation methodology and results ↗

    Vals AI · 2026

  56. Vibe Code Bench — evaluation methodology and results ↗

    Vals AI · 2026

Names used in source tables

GPT 5.1 · GPT 5.1 (Mini-SWE-agent) · GPT 5.1 (OpenHands) · GPT-5.1 · GPT-5.1 (High) · GPT-5.1 (Low) · GPT-5.1 (high) · GPT-5.1 (low) · GPT-5.1 (medium) · GPT-5.1 (no thinking) · GPT-5.1 (unknown thinking) · gpt-5.1 (high)