RLTasksby ulam.ai
Models / OpenAI

OpenAI / MODEL EVIDENCE

GPT-5.6 Terra

62 benchmarks · 110 observations · 69 sources · released 2026-07-09

Scores at a glance

62 benchmarks · large dot: GPT-5.6 Terra; small dots: closest models where reported

ITBench-AA ↗51.04%
35.2256.21

GPT-5.6 Terra (Max) · ITBench-AA · root-cause score ↗

BALROG ↗53.2%
3.768.3

GPT-5.6 Terra (max) · Balrog · Average progress · % ↗

GDP.pdf ↗24.7%
24.724.7

GPT-5.6 Terra (unknown thinking) · GDP.pdf · GDP.pdf score · % ↗

1 more reported result

24.7% · GPT-5.6 Terra (medium) · GDP.pdf · GDP.pdf score · % · Epoch AI · GDP.pdf ↗

Closest models by score

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

14.3 percentile-point gap

30 of 40 shared benchmark comparisons

15.1 percentile-point gap

32 of 40 shared benchmark comparisons

16.4 percentile-point gap

30 of 40 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. APEX-Agents-AA Benchmark | Artificial Analysis ↗

    Artificial Analysis

  5. GPQA Diamond Benchmark | Artificial Analysis ↗

    Artificial Analysis

  6. ITBench-AA Benchmark | Artificial Analysis ↗

    Artificial Analysis

  7. MMMU-Pro Benchmark | Artificial Analysis ↗

    Artificial Analysis

  8. SciCode Benchmark | Artificial Analysis ↗

    Artificial Analysis

  9. 𝜏³-Banking Benchmark | Artificial Analysis ↗

    Artificial Analysis

  10. Terminal-Bench 2.1 Benchmark | Artificial Analysis ↗

    Artificial Analysis

  11. Terminal-Bench Hard Benchmark | Artificial Analysis ↗

    Artificial Analysis

  12. BALROG: Benchmarking Agentic LLM and VLM Reasoning On Games ↗

    Paglieri, Davide, Cupiał, Bartłomiej, Coward, Samuel, Piterbarg, Ulyana, Wolczyk, Maciej, Khan, Akbir et al. · 2024

    All 13 authors

    Paglieri, Davide, Cupiał, Bartłomiej, Coward, Samuel, Piterbarg, Ulyana, Wolczyk, Maciej, Khan, Akbir, Pignatelli, Eduardo, Kuciński, Łukasz, Pinto, Lerrel, Fergus, Rob, Foerster, Jakob Nicolaus, Parker-Holder, Jack, Rocktäschel, Tim

  13. FrontierCode Leaderboard ↗

    Cognition

  14. DTBench — Conceptual Reasoning Index ↗

    Conceptual Reasoning Index

  15. LMCA — Conceptual Reasoning Index ↗

    Conceptual Reasoning Index

  16. Cursor · CursorBench ↗

    Cursor

  17. DeepSWE ↗

    Datacurve

  18. APEX-Agents ↗

    Epoch AI

  19. ARC-AGI-2 ↗

    Epoch AI

  20. Chess Puzzles ↗

    Epoch AI

  21. CritPt v1 ↗

    Epoch AI

  22. FrontierMath Tier 4 (v2) ↗

    Epoch AI

  23. FrontierMath Tiers 1-3 (v2) ↗

    Epoch AI

  24. Furniture Assembly Benchmark ↗

    Epoch AI

  25. GPQA Diamond ↗

    Epoch AI

  26. Mystery Game Puzzles ↗

    Epoch AI

  27. OTIS Mock AIME 2024-2025 ↗

    Epoch AI

  28. SimpleQA Verified ↗

    Epoch AI

  29. SimpleBench ↗

    Epoch AI

  30. Vending Bench 2 — methodology and published results ↗

    Epoch AI · 2026

  31. AI benchmarks & capabilities ↗

    Epoch AI

  32. WeirdML ↗

    Håvard Tveit Ihle

  33. DistressBench — evaluation methodology and results ↗

    Scale Labs / SEAL · 2026

  34. Humanity's Sixth Sense — evaluation methodology and results ↗

    Scale Labs / SEAL · 2026

  35. SWE-Bench Pro V2 — evaluation methodology and results ↗

    Scale Labs / SEAL · 2026

  36. SWE-Bench Pro V2 — evaluation methodology and results ↗

    Scale Labs / SEAL · 2026

  37. AI Model Benchmarks — LM Council ↗

    LM Council

  38. GDP.pdf Benchmark | Surge AI ↗

    Surge AI

  39. Code Migration v1 — evaluation methodology and results ↗

    Vals AI · 2026

  40. CorpFin — evaluation methodology and results ↗

    Vals AI · 2026

  41. CyberBench — evaluation methodology and results ↗

    Vals AI · 2026

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

    Vals AI · 2026

  43. Finance Agent v2 — evaluation methodology and results ↗

    Vals AI · 2026

  44. GPQA Diamond — evaluation methodology and results ↗

    Vals AI · 2026

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

    Vals AI · 2026

  46. IOI — evaluation methodology and results ↗

    Vals AI · 2026

  47. LiveCodeBench — evaluation methodology and results ↗

    Vals AI · 2026

  48. LegalBench — evaluation methodology and results ↗

    Vals AI · 2026

  49. Legal Research Bench — evaluation methodology and results ↗

    Vals AI · 2026

  50. MedCode — evaluation methodology and results ↗

    Vals AI · 2026

  51. MedScribe — evaluation methodology and results ↗

    Vals AI · 2026

  52. MMLU Pro — evaluation methodology and results ↗

    Vals AI · 2026

  53. MMMU Pro — evaluation methodology and results ↗

    Vals AI · 2026

  54. MortgageTax — evaluation methodology and results ↗

    Vals AI · 2026

  55. ProgramBench — evaluation methodology and results ↗

    Vals AI · 2026

  56. ProofBench — evaluation methodology and results ↗

    Vals AI · 2026

  57. Public Benefits Bench — evaluation methodology and results ↗

    Vals AI · 2026

  58. SAGE — evaluation methodology and results ↗

    Vals AI · 2026

  59. SkillsBench — evaluation methodology and results ↗

    Vals AI · 2026

  60. SRE Bench — evaluation methodology and results ↗

    Vals AI · 2026

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

    Vals AI · 2026

  62. Tax Agent Bench — evaluation methodology and results ↗

    Vals AI · 2026

  63. TaxEval — evaluation methodology and results ↗

    Vals AI · 2026

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

    Vals AI · 2026

  65. Terminal-Bench-Science — evaluation methodology and results ↗

    Vals AI · 2026

  66. Vals Multimodal Index — evaluation methodology and results ↗

    Vals AI · 2026

  67. Vibe Code Bench 1-100 — evaluation methodology and results ↗

    Vals AI · 2026

  68. Vibe Code Bench — evaluation methodology and results ↗

    Vals AI · 2026

  69. Surface Evolver Bench ↗

    yhenon

Names used in source tables

GPT-5.6 Terra · GPT-5.6 Terra (Codex) xhigh · GPT-5.6 Terra (Max) · GPT-5.6 Terra (Mini-SWE-agent) · GPT-5.6 Terra (OpenHands) · GPT-5.6 Terra (Xhigh) · GPT-5.6 Terra (high) · GPT-5.6 Terra (low) · GPT-5.6 Terra (max) · GPT-5.6 Terra (medium) · GPT-5.6 Terra (unknown thinking) · GPT-5.6 Terra (xhigh) · GPT-5.6-Terra (Codex) xhigh · GPT-5.6-Terra (max) · gpt-5.6-terra