RLTasksby ulam.ai
Models / Anthropic

Anthropic / MODEL EVIDENCE

Claude Opus 4.7

61 benchmarks · 89 observations · 66 sources · released 2026-04-16

Scores at a glance

61 benchmarks · large dot: Claude Opus 4.7; small dots: closest models where reported

ITBench-AA ↗46.66%
35.2256.21

Claude Opus 4.7 (Max) · ITBench-AA · root-cause score ↗

MirrorCode ↗31.11%
8.8977.4

Claude Opus 4.7 (high) · MirrorCode · Best score (across scorers) · % ↗

ARC-AGI-1 ↗93.5%
93.593.5

Claude Opus 4.7 (high) · ARC-AGI · Score · % ↗

5 more reported results

92% · Claude Opus 4.7 (max) · ARC-AGI · Score · % · Epoch AI · ARC-AGI ↗

91% · Claude Opus 4.7 (low) · ARC-AGI · Score · % · Epoch AI · ARC-AGI ↗

91% · Claude Opus 4.7 (medium) · ARC-AGI · Score · % · Epoch AI · ARC-AGI ↗

93.5% · Claude Opus 4.7 (high) · ARC-AGI · Score · % · Epoch AI · ARC-AGI ↗

92% · Claude Opus 4.7 (max) · ARC-AGI · Score · % · Epoch AI · ARC-AGI ↗

GSO ↗44.12%
9.888.24

Claude Opus 4.7 (high) · GSO-Bench · Score OPT@1 · % ↗

1 more reported result

44.12% · Claude Opus 4.7 (no thinking) · GSO-Bench · Score OPT@1 · % · Epoch AI · GSO-Bench ↗

ARC-AGI-2 ↗75.83%
75.875.83

Claude Opus 4.7 (max) · ARC-AGI-2 · Score · % ↗

5 more reported results

75.8% · Claude Opus 4.7 (max) · ARC-AGI-2 · Score · % · Epoch AI · ARC-AGI-2 ↗

68.33% · Claude Opus 4.7 (high) · ARC-AGI-2 · Score · % · Epoch AI · ARC-AGI-2 ↗

68.3% · Claude Opus 4.7 (high) · ARC-AGI-2 · Score · % · Epoch AI · ARC-AGI-2 ↗

67.5% · Claude Opus 4.7 (medium) · ARC-AGI-2 · Score · % · Epoch AI · ARC-AGI-2 ↗

62.08% · Claude Opus 4.7 (low) · ARC-AGI-2 · Score · % · Epoch AI · ARC-AGI-2 ↗

CritPt ↗12%
032.29

Claude Opus 4.7 (max) · CritPt · Accuracy · % ↗

LMCA ↗52.2%
2.7868.26

Claude Opus 4.7 (max) · LMCA · Score · % ↗

DTBench ↗94.65%
41.6598.93

Claude Opus 4.7 (max) · DTBench · Accuracy · % ↗

GDP.pdf ↗21%
235

Claude Opus 4.7 (max) · GDP.pdf · GDP.pdf score · % ↗

SciCode ↗54.51%
1.2766.9

Claude Opus 4.7 (max) · SciCode · Score · % ↗

Vals RSI Index ↗0.31 reference score
00.46

Claude Opus 4.7 (max) · Compression · reference-anchored score ↗

3 more reported results

0.39 reference score · Claude Opus 4.7 (max) · LM training · reference-anchored score · Vals RSI Index · LM training ↗

0.06 reference score · Claude Opus 4.7 (max) · Harness engineering · reference-anchored score · Vals RSI Index · Harness engineering ↗

0.00 reference score · Claude Opus 4.7 (max) · Post-training · reference-anchored score · Vals RSI Index · Post-training ↗

MedCode ↗54.86 %
19.7263.57

Claude Opus 4.7 · MedCode · Accuracy ↗

Closest models by score

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

13.2 percentile-point gap

38 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. ARC Prize - Leaderboard ↗

    ARC Prize Foundation

  2. Arena leaderboard — WebDev evaluation ↗

    Arena

  3. AA-AnalystAgent Benchmark | Artificial Analysis ↗

    Artificial Analysis

  4. ITBench-AA Benchmark | Artificial Analysis ↗

    Artificial Analysis

  5. SciCode Benchmark | Artificial Analysis ↗

    Artificial Analysis

  6. Terminal-Bench 2.1 Benchmark | Artificial Analysis ↗

    Artificial Analysis

  7. Terminal-Bench Hard Benchmark | Artificial Analysis ↗

    Artificial Analysis

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

    Jaffe, Oliver, Sherburn, Dane · 2026

  9. DTBench — Conceptual Reasoning Index ↗

    Conceptual Reasoning Index

  10. LMCA — Conceptual Reasoning Index ↗

    Conceptual Reasoning Index

  11. APEX-Agents ↗

    Epoch AI

  12. ARC-AGI-1 ↗

    Epoch AI

  13. ARC-AGI-2 ↗

    Epoch AI

  14. Chess Puzzles ↗

    Epoch AI

  15. CritPt v1 ↗

    Epoch AI

  16. Earthborne Rangers (EBR-bench) ↗

    Epoch AI

  17. ExploitBench v0.1 ↗

    Epoch AI

  18. FrontierMath Tier 4 (v1, old) ↗

    Epoch AI

  19. FrontierMath Tier 4 (v2) ↗

    Epoch AI

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

    Epoch AI

  21. FrontierMath Tiers 1-3 (v2) ↗

    Epoch AI

  22. Furniture Assembly Benchmark ↗

    Epoch AI

  23. GPQA Diamond ↗

    Epoch AI

  24. MirrorCode ↗

    Epoch AI

  25. Mystery Game Puzzles ↗

    Epoch AI

  26. OTIS Mock AIME 2024-2025 ↗

    Epoch AI

  27. PostTrainBench v1.1 ↗

    Epoch AI

  28. SimpleQA Verified ↗

    Epoch AI

  29. SWE-bench Verified ↗

    Epoch AI

  30. Capabilities & benchmarking — retained external evaluation records ↗

    Epoch AI · 2026

  31. Vending Bench 2 — methodology and published results ↗

    Epoch AI · 2026

  32. AI benchmarks & capabilities ↗

    Epoch AI

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

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

  34. WeirdML ↗

    Håvard Tveit Ihle

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

    Scale Labs / SEAL · 2026

  36. Scale Labs — evaluation methodology and results ↗

    Scale Labs / SEAL · 2026

  37. Scale Labs — evaluation methodology and results ↗

    Scale Labs / SEAL · 2026

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

    Scale Labs / SEAL · 2026

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

    Scale Labs / SEAL · 2026

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

    OSWorld Team

  41. GDP.pdf Benchmark | Surge AI ↗

    Surge AI

  42. AIME — evaluation methodology and results ↗

    Vals AI · 2026

  43. CaseLaw — evaluation methodology and results ↗

    Vals AI · 2026

  44. Code Migration v1 — evaluation methodology and results ↗

    Vals AI · 2026

  45. CorpFin — evaluation methodology and results ↗

    Vals AI · 2026

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

    Vals AI · 2026

  47. Finance Agent v2 — evaluation methodology and results ↗

    Vals AI · 2026

  48. GPQA Diamond — evaluation methodology and results ↗

    Vals AI · 2026

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

    Vals AI · 2026

  50. LiveCodeBench — evaluation methodology and results ↗

    Vals AI · 2026

  51. LegalBench — evaluation methodology and results ↗

    Vals AI · 2026

  52. Legal Research Bench — evaluation methodology and results ↗

    Vals AI · 2026

  53. MedCode — evaluation methodology and results ↗

    Vals AI · 2026

  54. MedScribe — evaluation methodology and results ↗

    Vals AI · 2026

  55. MMLU Pro — evaluation methodology and results ↗

    Vals AI · 2026

  56. MMMU Pro — evaluation methodology and results ↗

    Vals AI · 2026

  57. MortgageTax — evaluation methodology and results ↗

    Vals AI · 2026

  58. ProgramBench — evaluation methodology and results ↗

    Vals AI · 2026

  59. ProofBench — evaluation methodology and results ↗

    Vals AI · 2026

  60. Vals RSI Index — evaluation methodology and results ↗

    Vals AI · 2026

  61. SAGE — evaluation methodology and results ↗

    Vals AI · 2026

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

    Vals AI · 2026

  63. Tax Agent Bench — evaluation methodology and results ↗

    Vals AI · 2026

  64. TaxEval — evaluation methodology and results ↗

    Vals AI · 2026

  65. Vals Multimodal Index — evaluation methodology and results ↗

    Vals AI · 2026

  66. Vibe Code Bench — evaluation methodology and results ↗

    Vals AI · 2026

Names used in source tables

Claude Opus 4.7 · Claude Opus 4.7 (Max) · Claude Opus 4.7 (Mini-SWE-agent) · Claude Opus 4.7 (Non-reasoning, High) · Claude Opus 4.7 (OpenHands) · Claude Opus 4.7 (high) · Claude Opus 4.7 (low) · Claude Opus 4.7 (max) · Claude Opus 4.7 (medium) · Claude Opus 4.7 (no thinking) · Claude Opus 4.7 (xhigh) · Opus 4.7 (Claude Code) · Opus 4.7 (max) · Opus-4.7 (Claude Code) · claude-opus-4-7 (max)