RLTasksby ulam.ai
Models / Anthropic

Anthropic / MODEL EVIDENCE

Claude Opus 4.8

79 benchmarks · 119 observations · 84 sources · released 2026-05-28

Scores at a glance

79 benchmarks · large dot: Claude Opus 4.8; small dots: closest models where reported

ErdősBench ↗2.510 / 4
2.512.51

Claude Opus 4.8 max · ErdősBench · mean progress / 4 · Claude Code ↗

GSO ↗47.06%
9.888.24

Claude Opus 4.8 · GSO-Bench · Score OPT@1 · % ↗

GBAEval ↗70.9%
70.970.9

Claude Opus 4.8 · GBAEval · Overall score · % ↗

CritPt ↗20.86%
032.29

Claude Opus 4.8 · CritPt · Accuracy · % ↗

LMCA ↗57.51%
2.7868.26

Claude Opus 4.8 · LMCA · Score · % ↗

DTBench ↗94.93%
41.6598.93

Claude Opus 4.8 · DTBench · Accuracy · % ↗

Vals RSI Index ↗0.38 reference score
00.46

Claude Opus 4.8 (max) · Compression · reference-anchored score ↗

3 more reported results

0.41 reference score · Claude Opus 4.8 (max) · LM training · reference-anchored score · Vals RSI Index · LM training ↗

0.17 reference score · Claude Opus 4.8 (max) · Harness engineering · reference-anchored score · Vals RSI Index · Harness engineering ↗

0.00 reference score · Claude Opus 4.8 (max) · Post-training · reference-anchored score · Vals RSI Index · Post-training ↗

MedCode ↗53.22 %
19.7263.57

Claude Opus 4.8 · MedCode · Accuracy ↗

Fortress ↗18.19%
5.7874.39

Claude Opus 4.8 max · Scale Labs · Risk elicitation score ↗

Kimi Code Bench 2.0 ↗71.7%
64.276.9

Claude Opus 4.8 (max) · 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.

13.8 percentile-point gap

37 of 45 shared benchmark comparisons

15.6 percentile-point gap

31 of 45 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. EnterpriseOps-Gym-AA Benchmark | Artificial Analysis ↗

    Artificial Analysis

  6. SciCode Benchmark | Artificial Analysis ↗

    Artificial Analysis

  7. 𝜏²-Bench Telecom Benchmark | Artificial Analysis ↗

    Artificial Analysis

  8. Terminal-Bench 2.1 Benchmark | Artificial Analysis ↗

    Artificial Analysis

  9. Terminal-Bench Hard Benchmark | Artificial Analysis ↗

    Artificial Analysis

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

    Jaffe, Oliver, Sherburn, Dane · 2026

  11. FrontierCode Leaderboard ↗

    Cognition

  12. DTBench — Conceptual Reasoning Index ↗

    Conceptual Reasoning Index

  13. LMCA — Conceptual Reasoning Index ↗

    Conceptual Reasoning Index

  14. DeepSWE ↗

    Datacurve

  15. APEX-Agents ↗

    Epoch AI

  16. ARC-AGI-2 ↗

    Epoch AI

  17. Chess Puzzles ↗

    Epoch AI

  18. CritPt v1 ↗

    Epoch AI

  19. Earthborne Rangers (EBR-bench) ↗

    Epoch AI

  20. FrontierMath Tier 4 (v1, old) ↗

    Epoch AI

  21. FrontierMath Tier 4 (v2) ↗

    Epoch AI

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

    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. PostTrainBench v1.1 ↗

    Epoch AI

  29. Remote Labor Index ↗

    Epoch AI

  30. SimpleQA Verified ↗

    Epoch AI

  31. Vending Bench 2 — methodology and published results ↗

    Epoch AI · 2026

  32. AI benchmarks & capabilities ↗

    Epoch AI

  33. FutureSearch Evals ↗

    FutureSearch

  34. FutureSearch Evals ↗

    FutureSearch

  35. Claude Opus 4.8 — GBA Eval ↗

    GBA Eval

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

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

  37. WeirdML ↗

    Håvard Tveit Ihle

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

    Moonshot AI · 2026

  39. DistressBench — evaluation methodology and results ↗

    Scale Labs / SEAL · 2026

  40. DrugDiscoveryBench — evaluation methodology and results ↗

    Scale Labs / SEAL · 2026

  41. EnigmaEval ↗

    Scale Labs / SEAL

  42. Scale Labs — evaluation methodology and results ↗

    Scale Labs / SEAL · 2026

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

    Scale Labs / SEAL · 2026

  44. Humanity's Sixth Sense — 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. AI Model Benchmarks — LM Council ↗

    LM Council

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

    OSWorld Team

  52. GDP.pdf Benchmark | Surge AI ↗

    Surge AI

  53. ErdősBench: research mathematics, scoped progress and proof audits ↗

    Ulam AI · 2026

  54. Code Migration v1 — evaluation methodology and results ↗

    Vals AI · 2026

  55. CorpFin — evaluation methodology and results ↗

    Vals AI · 2026

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

    Vals AI · 2026

  57. Finance Agent v2 — evaluation methodology and results ↗

    Vals AI · 2026

  58. GPQA Diamond — evaluation methodology and results ↗

    Vals AI · 2026

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

    Vals AI · 2026

  60. LiveCodeBench — evaluation methodology and results ↗

    Vals AI · 2026

  61. LegalBench — evaluation methodology and results ↗

    Vals AI · 2026

  62. Legal Research Bench — evaluation methodology and results ↗

    Vals AI · 2026

  63. MedCode — evaluation methodology and results ↗

    Vals AI · 2026

  64. MedScribe — evaluation methodology and results ↗

    Vals AI · 2026

  65. MMLU Pro — evaluation methodology and results ↗

    Vals AI · 2026

  66. MMMU Pro — evaluation methodology and results ↗

    Vals AI · 2026

  67. MortgageTax — evaluation methodology and results ↗

    Vals AI · 2026

  68. ProgramBench — evaluation methodology and results ↗

    Vals AI · 2026

  69. ProofBench — evaluation methodology and results ↗

    Vals AI · 2026

  70. Public Benefits Bench — evaluation methodology and results ↗

    Vals AI · 2026

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

    Vals AI · 2026

  72. Vals RSI Index — evaluation methodology and results ↗

    Vals AI · 2026

  73. SAGE — evaluation methodology and results ↗

    Vals AI · 2026

  74. SkillsBench — evaluation methodology and results ↗

    Vals AI · 2026

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

    Vals AI · 2026

  76. Tax Agent Bench — evaluation methodology and results ↗

    Vals AI · 2026

  77. TaxEval — evaluation methodology and results ↗

    Vals AI · 2026

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

    Vals AI · 2026

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

    Vals AI · 2026

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

    Vals AI · 2026

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

    Vals AI · 2026

  82. Vals Multimodal Index — evaluation methodology and results ↗

    Vals AI · 2026

  83. Vibe Code Bench — evaluation methodology and results ↗

    Vals AI · 2026

  84. Surface Evolver Bench ↗

    yhenon

Names used in source tables

Claude Opus 4.8 · Claude Opus 4.8 (Claude Code) · Claude Opus 4.8 (Claude Code) max · Claude Opus 4.8 (Max) · Claude Opus 4.8 (Mini-SWE-agent) · Claude Opus 4.8 (OpenHands) · Claude Opus 4.8 (high) · Claude Opus 4.8 (high, agent SDK) · Claude Opus 4.8 (max) · Claude Opus 4.8 (mini-SWE-agent) max · Claude Opus 4.8 (xhigh) · Claude Opus 4.8 - High · Claude Opus 4.8 - Max · Claude Opus 4.8 max · Claude-Opus-4.8 (max) · Opus 4.8 · Opus 4.8 (Claude Code) · Opus 4.8 (Claude Code) xhigh · Opus 4.8 (max) · claude-opus-4-8 (max) · claude-opus-4.8