RLTasksby ulam.ai
Models / Anthropic

Anthropic / MODEL EVIDENCE

Claude Sonnet 5

60 benchmarks · 95 observations · 64 sources · released 2026-06-30

Scores at a glance

60 benchmarks · large dot: Claude Sonnet 5; small dots: closest models where reported

GSO ↗37.25%
9.888.24

Claude Sonnet 5 (unknown thinking) · GSO-Bench · Score OPT@1 · % ↗

SimpleBench ↗60.6%
10.781.9

Claude Sonnet 5 (unknown thinking) · SimpleBench · Score (AVG@5) · % ↗

GBAEval ↗65.26%
65.2665.26

Claude Sonnet 5 (unknown thinking) · GBAEval · Overall score · % ↗

SciCode ↗54.28%
48.6154.28

Claude Sonnet 5 (high) · SciCode · Score · % ↗

5 more reported results

54.05% · Claude Sonnet 5 (xhigh) · SciCode · Score · % · Epoch AI · SciCode ↗

53.59% · Claude Sonnet 5 (max) · SciCode · Score · % · Epoch AI · SciCode ↗

51.62% · Claude Sonnet 5 (medium) · SciCode · Score · % · Epoch AI · SciCode ↗

50.12% · Claude Sonnet 5 (low) · SciCode · Score · % · Epoch AI · SciCode ↗

48.61% · Claude Sonnet 5 (high) · SciCode · Score · % · Epoch AI · SciCode ↗

MedCode ↗47.54 %
19.7263.57

Claude Sonnet 5 · MedCode · Accuracy ↗

BTF-3 ↗0.142 Brier scale
0.120.15

Claude Sonnet 5 (xhigh) · Pooled forecasting score ↗

Closest models by score

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

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. Arena leaderboard — WebDev evaluation ↗

    Arena

  3. AA-AnalystAgent Benchmark | Artificial Analysis ↗

    Artificial Analysis

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

    Artificial Analysis

  5. SciCode Benchmark | Artificial Analysis ↗

    Artificial Analysis

  6. 𝜏³-Banking Benchmark | Artificial Analysis ↗

    Artificial Analysis

  7. Terminal-Bench 2.1 Benchmark | Artificial Analysis ↗

    Artificial Analysis

  8. FrontierCode Leaderboard ↗

    Cognition

  9. DTBench — Conceptual Reasoning Index ↗

    Conceptual Reasoning Index

  10. LMCA — Conceptual Reasoning Index ↗

    Conceptual Reasoning Index

  11. Cursor · CursorBench ↗

    Cursor

  12. DeepSWE ↗

    Datacurve

  13. APEX-Agents ↗

    Epoch AI

  14. Chess Puzzles ↗

    Epoch AI

  15. CritPt v1 ↗

    Epoch AI

  16. FrontierMath Tier 4 (v2) ↗

    Epoch AI

  17. FrontierMath Tiers 1-3 (v2) ↗

    Epoch AI

  18. GPQA Diamond ↗

    Epoch AI

  19. Mystery Game Puzzles ↗

    Epoch AI

  20. OTIS Mock AIME 2024-2025 ↗

    Epoch AI

  21. SimpleQA Verified ↗

    Epoch AI

  22. SimpleBench ↗

    Epoch AI

  23. Vending Bench 2 — methodology and published results ↗

    Epoch AI · 2026

  24. AI benchmarks & capabilities ↗

    Epoch AI

  25. FutureSearch Evals ↗

    FutureSearch

  26. Claude Sonnet 5 (unknown thinking) — GBA Eval ↗

    GBA Eval

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

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

  28. WeirdML ↗

    Håvard Tveit Ihle

  29. DistressBench — evaluation methodology and results ↗

    Scale Labs / SEAL · 2026

  30. DrugDiscoveryBench — evaluation methodology and results ↗

    Scale Labs / SEAL · 2026

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

    Scale Labs / SEAL · 2026

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

    Scale Labs / SEAL · 2026

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

    Scale Labs / SEAL · 2026

  34. Code Migration v1 — evaluation methodology and results ↗

    Vals AI · 2026

  35. CorpFin — evaluation methodology and results ↗

    Vals AI · 2026

  36. CyberBench — evaluation methodology and results ↗

    Vals AI · 2026

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

    Vals AI · 2026

  38. Finance Agent v2 — evaluation methodology and results ↗

    Vals AI · 2026

  39. GPQA Diamond — evaluation methodology and results ↗

    Vals AI · 2026

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

    Vals AI · 2026

  41. IOI — evaluation methodology and results ↗

    Vals AI · 2026

  42. LiveCodeBench — evaluation methodology and results ↗

    Vals AI · 2026

  43. LegalBench — evaluation methodology and results ↗

    Vals AI · 2026

  44. Legal Research Bench — evaluation methodology and results ↗

    Vals AI · 2026

  45. MedCode — evaluation methodology and results ↗

    Vals AI · 2026

  46. MedScribe — evaluation methodology and results ↗

    Vals AI · 2026

  47. MMLU Pro — evaluation methodology and results ↗

    Vals AI · 2026

  48. MMMU Pro — evaluation methodology and results ↗

    Vals AI · 2026

  49. MortgageTax — evaluation methodology and results ↗

    Vals AI · 2026

  50. ProgramBench — evaluation methodology and results ↗

    Vals AI · 2026

  51. ProofBench — evaluation methodology and results ↗

    Vals AI · 2026

  52. Public Benefits Bench — evaluation methodology and results ↗

    Vals AI · 2026

  53. SAGE — evaluation methodology and results ↗

    Vals AI · 2026

  54. SkillsBench — evaluation methodology and results ↗

    Vals AI · 2026

  55. SRE Bench — evaluation methodology and results ↗

    Vals AI · 2026

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

    Vals AI · 2026

  57. Tax Agent Bench — evaluation methodology and results ↗

    Vals AI · 2026

  58. TaxEval — evaluation methodology and results ↗

    Vals AI · 2026

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

    Vals AI · 2026

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

    Vals AI · 2026

  61. Vals Multimodal Index — evaluation methodology and results ↗

    Vals AI · 2026

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

    Vals AI · 2026

  63. Vibe Code Bench — evaluation methodology and results ↗

    Vals AI · 2026

  64. Surface Evolver Bench ↗

    yhenon

Names used in source tables

Claude Sonnet 5 · Claude Sonnet 5 (Max) · Claude Sonnet 5 (Mini-SWE-agent) · Claude Sonnet 5 (OpenHands) · Claude Sonnet 5 (high) · Claude Sonnet 5 (low) · Claude Sonnet 5 (max) · Claude Sonnet 5 (medium) · Claude Sonnet 5 (mini-swe-agent) max · Claude Sonnet 5 (no thinking) · Claude Sonnet 5 (unknown thinking) · Claude Sonnet 5 (xhigh) · Claude-Sonnet-5 (max) · Sonnet 5 (Claude Code) xhigh · claude-sonnet-5