RLTasksby ulam.ai
Models / Anthropic

Anthropic / MODEL EVIDENCE

Claude Sonnet 5.5

71 benchmarks · 164 observations · 79 sources · released 2026-09-28

Scores at a glance

71 benchmarks · large dot: Claude Sonnet 5.5; small dots: closest models where reported

AA-Briefcase v1.1 ↗1811.82 Elo
833.061811.82

Claude Sonnet 5.5 (Max, Default Fallback) · AA-Briefcase v1.1 · overall Elo ↗

AutomationBench-AA ↗71.77%
4.9877.51

Claude Sonnet 5.5 (Max, Default Fallback) · AutomationBench-AA · guardrail-gated objective score ↗

GDP.pdf ↗25.80%
7.432.6

Claude Sonnet 5.5 (Max, Default Fallback) · GDP.pdf · all-pass ↗

1 more reported result

31.4% · Claude Sonnet 5.5 (max) · GDP.pdf · GDP.pdf score · % · Epoch AI · GDP.pdf ↗

FrontierCode 2.0 ↗41.70%
3.9246.44

Claude Sonnet 5.5 (Max, Default Fallback) · FrontierCode 2.0 · AA implementation ↗

AA-Omniscience v1.1 ↗30.47 index
-8.2748.13

Claude Sonnet 5.5 (Max, Default Fallback) · AA-Omniscience v1.1 · error-penalized index ↗

1 more reported result

32.30 index · Claude Sonnet 5.5 (Max, Default Fallback) · AA-Omniscience · error-penalized score · Artificial Analysis ↗

GDPval-AA v2.1 ↗1837.82 Elo
1071.981866.27

Claude Sonnet 5.5 (Max, Default Fallback) · GDPval-AA v2.1 · Elo ↗

AA-3D ↗1198.83 Elo
572.551198.83

Claude Sonnet 5.5 (Max, Default Fallback) · AA-3D · Elo ↗

AA-AnalystAgent ↗57.50%
23.7560

Claude Sonnet 5.5 (Max, Default Fallback) · AA-AnalystAgent · strict score ↗

SciCode ↗61.00%
42.9466.9

Claude Sonnet 5.5 (Max, Default Fallback) · SciCode · AA implementation ↗

5 more reported results

61% · Claude Sonnet 5.5 (max) · SciCode · Score · % · Epoch AI · SciCode ↗

57.29% · Claude Sonnet 5.5 (xhigh) · SciCode · Score · % · Epoch AI · SciCode ↗

53.7% · Claude Sonnet 5.5 (high) · SciCode · Score · % · Epoch AI · SciCode ↗

52.89% · Claude Sonnet 5.5 (medium) · SciCode · Score · % · Epoch AI · SciCode ↗

49.07% · Claude Sonnet 5.5 (low) · SciCode · Score · % · Epoch AI · SciCode ↗

MLCR-AA ↗41.67%
6.1141.67

Claude Sonnet 5.5 (Max, Default Fallback) · MLCR-AA · overall ↗

HealthBench ↗62.97%
50.765.98

Claude Sonnet 5.5 (Max, Default Fallback) · HealthBench · HealthBench Professional · length-adjusted ↗

CritPt v2 ↗74.00%
483.14

Claude Sonnet 5.5 (Max, Default Fallback) · CritPt v2 · code tools ↗

CritPt ↗31.43%
4.5732.86

Claude Sonnet 5.5 (Max, Default Fallback) · CritPt · original ↗

5 more reported results

31.43% · Claude Sonnet 5.5 (max) · CritPt · Accuracy · % · Epoch AI · CritPt ↗

31.14% · Claude Sonnet 5.5 (xhigh) · CritPt · Accuracy · % · Epoch AI · CritPt ↗

24.57% · Claude Sonnet 5.5 (high) · CritPt · Accuracy · % · Epoch AI · CritPt ↗

16.86% · Claude Sonnet 5.5 (medium) · CritPt · Accuracy · % · Epoch AI · CritPt ↗

11.43% · Claude Sonnet 5.5 (low) · CritPt · Accuracy · % · Epoch AI · CritPt ↗

GPQA Diamond ↗95.58%
9.2896.4

Claude Sonnet 5.5 (max) · GPQA diamond · Best score (across scorers) · % ↗

Chess Puzzles ↗59%
076

Claude Sonnet 5.5 (max) · Chess Puzzles · Best score (across scorers) · % ↗

WeirdML (v3) ↗36.99%
4.3854.05

Claude Sonnet 5.5 (xhigh) · WeirdML v3 · Max performance · % ↗

SpireClimb ↗1.33%
025.67

Claude Sonnet 5.5 (max) · SpireClimb · Best score (across scorers) · % ↗

MedCode ↗52.92 %
19.7263.57

Claude Sonnet 5.5 · MedCode · Accuracy ↗

SAFE-Teen ↗23%
1556

Claude Sonnet 5.5 · Urgent safety · share of applicable ratings marked fail ↗

2 more reported results

43% · Claude Sonnet 5.5 · Health advice · share of applicable ratings marked fail · Vals AI · SAFE-Teen ↗

37% · Claude Sonnet 5.5 · Relationship boundaries · share of applicable ratings marked fail · Vals AI · SAFE-Teen ↗

GDPx v1.0 ↗8.2%
1.6712.03

Claude Sonnet 5.5 · GDPx v1.0 · Overall · intended grading ↗

53 more reported results

9.7% · Claude Sonnet 5.5 · GDPx v1.0 · Eight-domain subset · intended grading · GDPx v1.0 — SemiAnalysis ↗

22.9% · Claude Sonnet 5.5 · GDPx v1.0 · Recursive Self-Improvement · intended grading · GDPx v1.0 — SemiAnalysis ↗

3.5% · Claude Sonnet 5.5 · GDPx v1.0 · Chip Design · intended grading · GDPx v1.0 — SemiAnalysis ↗

3.7% · Claude Sonnet 5.5 · GDPx v1.0 · Cybersecurity · intended grading · GDPx v1.0 — SemiAnalysis ↗

5.1% · Claude Sonnet 5.5 · GDPx v1.0 · Biology · intended grading · GDPx v1.0 — SemiAnalysis ↗

0.0% · Claude Sonnet 5.5 · GDPx v1.0 · Finance · intended grading · GDPx v1.0 — SemiAnalysis ↗

0.0% · Claude Sonnet 5.5 · GDPx v1.0 · Legal · intended grading · GDPx v1.0 — SemiAnalysis ↗

13.0% · Claude Sonnet 5.5 · GDPx v1.0 · Quant Trading · intended grading · GDPx v1.0 — SemiAnalysis ↗

10.0% · Claude Sonnet 5.5 · GDPx v1.0 · Hardware Design · intended grading · GDPx v1.0 — SemiAnalysis ↗

16.7% · Claude Sonnet 5.5 · GDPx v1.0 · Materials Science · intended grading · GDPx v1.0 — SemiAnalysis ↗

4.3% · Claude Sonnet 5.5 · GDPx v1.0 · Alignment · intended grading · GDPx v1.0 — SemiAnalysis ↗

11.1% · Claude Sonnet 5.5 · GDPx v1.0 · Software Engineering · intended grading · GDPx v1.0 — SemiAnalysis ↗

16.9% · Claude Sonnet 5.5 · GDPx v1.0 · Overall · partial credit · GDPx v1.0 — SemiAnalysis ↗

20.7% · Claude Sonnet 5.5 · GDPx v1.0 · Eight-domain subset · partial credit · GDPx v1.0 — SemiAnalysis ↗

22.9% · Claude Sonnet 5.5 · GDPx v1.0 · Recursive Self-Improvement · partial credit · GDPx v1.0 — SemiAnalysis ↗

10.2% · Claude Sonnet 5.5 · GDPx v1.0 · Chip Design · partial credit · GDPx v1.0 — SemiAnalysis ↗

3.7% · Claude Sonnet 5.5 · GDPx v1.0 · Cybersecurity · partial credit · GDPx v1.0 — SemiAnalysis ↗

12.0% · Claude Sonnet 5.5 · GDPx v1.0 · Biology · partial credit · GDPx v1.0 — SemiAnalysis ↗

44.8% · Claude Sonnet 5.5 · GDPx v1.0 · Finance · partial credit · GDPx v1.0 — SemiAnalysis ↗

27.8% · Claude Sonnet 5.5 · GDPx v1.0 · Legal · partial credit · GDPx v1.0 — SemiAnalysis ↗

13.0% · Claude Sonnet 5.5 · GDPx v1.0 · Quant Trading · partial credit · GDPx v1.0 — SemiAnalysis ↗

10.0% · Claude Sonnet 5.5 · GDPx v1.0 · Hardware Design · partial credit · GDPx v1.0 — SemiAnalysis ↗

26.1% · Claude Sonnet 5.5 · GDPx v1.0 · Materials Science · partial credit · GDPx v1.0 — SemiAnalysis ↗

4.3% · Claude Sonnet 5.5 · GDPx v1.0 · Alignment · partial credit · GDPx v1.0 — SemiAnalysis ↗

11.1% · Claude Sonnet 5.5 · GDPx v1.0 · Software Engineering · partial credit · GDPx v1.0 — SemiAnalysis ↗

6.7% · Claude Sonnet 5.5 · GDPx v1.0 · Aria · Chip Design · intended grading · GDPx v1.0 — SemiAnalysis ↗

0.0% · Claude Sonnet 5.5 · GDPx v1.0 · Arcverex · Chip Design · intended grading · GDPx v1.0 — SemiAnalysis ↗

3.9% · Claude Sonnet 5.5 · GDPx v1.0 · Ergodex · Chip Design · intended grading · GDPx v1.0 — SemiAnalysis ↗

3.7% · Claude Sonnet 5.5 · GDPx v1.0 · Arithmetic · Cybersecurity · intended grading · GDPx v1.0 — SemiAnalysis ↗

5.1% · Claude Sonnet 5.5 · GDPx v1.0 · LatchBio · Biology · intended grading · GDPx v1.0 — SemiAnalysis ↗

0.0% · Claude Sonnet 5.5 · GDPx v1.0 · Living Context · Finance · intended grading · GDPx v1.0 — SemiAnalysis ↗

0.0% · Claude Sonnet 5.5 · GDPx v1.0 · Chakra · Legal · intended grading · GDPx v1.0 — SemiAnalysis ↗

13.0% · Claude Sonnet 5.5 · GDPx v1.0 · Third Moment · Quant Trading · intended grading · GDPx v1.0 — SemiAnalysis ↗

22.9% · Claude Sonnet 5.5 · GDPx v1.0 · Extrapolate · Recursive Self-Improvement · intended grading · GDPx v1.0 — SemiAnalysis ↗

10.0% · Claude Sonnet 5.5 · GDPx v1.0 · Beautiful Machines · Hardware Design · intended grading · GDPx v1.0 — SemiAnalysis ↗

18.3% · Claude Sonnet 5.5 · GDPx v1.0 · ValenceForge · Materials Science · intended grading · GDPx v1.0 — SemiAnalysis ↗

15.1% · Claude Sonnet 5.5 · GDPx v1.0 · Emulated · Materials Science · intended grading · GDPx v1.0 — SemiAnalysis ↗

4.3% · Claude Sonnet 5.5 · GDPx v1.0 · Fleet · Alignment · intended grading · GDPx v1.0 — SemiAnalysis ↗

11.1% · Claude Sonnet 5.5 · GDPx v1.0 · Datacurve · Software Engineering · intended grading · GDPx v1.0 — SemiAnalysis ↗

26.6% · Claude Sonnet 5.5 · GDPx v1.0 · Aria · Chip Design · partial credit · GDPx v1.0 — SemiAnalysis ↗

0.0% · Claude Sonnet 5.5 · GDPx v1.0 · Arcverex · Chip Design · partial credit · GDPx v1.0 — SemiAnalysis ↗

3.9% · Claude Sonnet 5.5 · GDPx v1.0 · Ergodex · Chip Design · partial credit · GDPx v1.0 — SemiAnalysis ↗

3.7% · Claude Sonnet 5.5 · GDPx v1.0 · Arithmetic · Cybersecurity · partial credit · GDPx v1.0 — SemiAnalysis ↗

12.0% · Claude Sonnet 5.5 · GDPx v1.0 · LatchBio · Biology · partial credit · GDPx v1.0 — SemiAnalysis ↗

44.8% · Claude Sonnet 5.5 · GDPx v1.0 · Living Context · Finance · partial credit · GDPx v1.0 — SemiAnalysis ↗

27.8% · Claude Sonnet 5.5 · GDPx v1.0 · Chakra · Legal · partial credit · GDPx v1.0 — SemiAnalysis ↗

13.0% · Claude Sonnet 5.5 · GDPx v1.0 · Third Moment · Quant Trading · partial credit · GDPx v1.0 — SemiAnalysis ↗

22.9% · Claude Sonnet 5.5 · GDPx v1.0 · Extrapolate · Recursive Self-Improvement · partial credit · GDPx v1.0 — SemiAnalysis ↗

10.0% · Claude Sonnet 5.5 · GDPx v1.0 · Beautiful Machines · Hardware Design · partial credit · GDPx v1.0 — SemiAnalysis ↗

33.0% · Claude Sonnet 5.5 · GDPx v1.0 · ValenceForge · Materials Science · partial credit · GDPx v1.0 — SemiAnalysis ↗

19.1% · Claude Sonnet 5.5 · GDPx v1.0 · Emulated · Materials Science · partial credit · GDPx v1.0 — SemiAnalysis ↗

4.3% · Claude Sonnet 5.5 · GDPx v1.0 · Fleet · Alignment · partial credit · GDPx v1.0 — SemiAnalysis ↗

11.1% · Claude Sonnet 5.5 · GDPx v1.0 · Datacurve · Software Engineering · partial credit · GDPx v1.0 — SemiAnalysis ↗

Closest models by score

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

18.6 percentile-point gap

57 of 61 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. Arena leaderboard — WebDev evaluation ↗

    Arena

  2. AA-3D: Interactive 3D Experience Benchmark | Artificial Analysis ↗

    Artificial Analysis

  3. AA-AnalystAgent Benchmark | Artificial Analysis ↗

    Artificial Analysis

  4. AA-Briefcase v1.1: Agentic Knowledge Work Benchmark | Artificial Analysis ↗

    Artificial Analysis

  5. Artificial Analysis Intelligence Index v5.0 — Artificial Analysis ↗

    Artificial Analysis

  6. AA-LCR v1.1: Long Context Reasoning Benchmark | Artificial Analysis ↗

    Artificial Analysis

  7. AutomationBench-AA: Agentic SaaS Workflow Benchmark | Artificial Analysis ↗

    Artificial Analysis

  8. CritPt Benchmark | Artificial Analysis ↗

    Artificial Analysis

  9. CritPt v2 Benchmark | Artificial Analysis ↗

    Artificial Analysis

  10. CritPt v2 — Hard Subset — Artificial Analysis ↗

    Artificial Analysis

  11. FrontierCode 1.1 Benchmark | Artificial Analysis ↗

    Artificial Analysis

  12. FrontierCode 2.0 Benchmark — Artificial Analysis ↗

    Artificial Analysis

  13. GDP.pdf Benchmark | Artificial Analysis ↗

    Artificial Analysis

  14. GDPval-AA v2.1 Benchmark | Artificial Analysis ↗

    Artificial Analysis

  15. Harvey LAB-AA v1.1 Benchmark | Artificial Analysis ↗

    Artificial Analysis

  16. HealthBench Professional Benchmark | Artificial Analysis ↗

    Artificial Analysis

  17. HLE-Diamond Benchmark — Artificial Analysis ↗

    Artificial Analysis

  18. Humanity's Last Exam Benchmark | Artificial Analysis ↗

    Artificial Analysis

  19. MLCR-AA: Medical Long Context Reasoning Benchmark | Artificial Analysis ↗

    Artificial Analysis

  20. AA-Omniscience v1.1: Knowledge and Hallucination Benchmark — Artificial Analysis ↗

    Artificial Analysis

  21. SciCode Benchmark | Artificial Analysis ↗

    Artificial Analysis

  22. Terminal-Bench-Science 0.1 Benchmark | Artificial Analysis ↗

    Artificial Analysis

  23. Terminal-Bench 4.0 Benchmark | Artificial Analysis ↗

    Artificial Analysis

  24. FrontierCode Leaderboard ↗

    Cognition

  25. DTBench — Conceptual Reasoning Index ↗

    Conceptual Reasoning Index

  26. LMCA — Conceptual Reasoning Index ↗

    Conceptual Reasoning Index

  27. Cursor · CursorBench ↗

    Cursor

  28. APEX-Agents ↗

    Epoch AI

  29. Chess Puzzles ↗

    Epoch AI

  30. CritPt v1 ↗

    Epoch AI

  31. FrontierMath Erdős ↗

    Epoch AI

  32. FrontierMath Tier 4 (v2) ↗

    Epoch AI

  33. FrontierMath Tiers 1-3 (v2) ↗

    Epoch AI

  34. Furniture Assembly Benchmark ↗

    Epoch AI

  35. GPQA Diamond ↗

    Epoch AI

  36. Humanity's Last Exam ↗

    Epoch AI

  37. Mystery Game Puzzles ↗

    Epoch AI

  38. OTIS Mock AIME 2024-2025 ↗

    Epoch AI

  39. SimpleQA Verified ↗

    Epoch AI

  40. SpireClimb ↗

    Epoch AI

  41. Vending Bench 2 — methodology and published results ↗

    Epoch AI · 2026

  42. AI benchmarks & capabilities ↗

    Epoch AI

  43. GDPx v1.0: The General Agentic Benchmark — SemiAnalysis ↗

    SemiAnalysis · 2026

  44. WeirdML ↗

    Håvard Tveit Ihle

  45. Scale Labs — evaluation methodology and results ↗

    Scale Labs / SEAL · 2026

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

    Scale Labs / SEAL · 2026

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

    Scale Labs / SEAL · 2026

  48. GDP.pdf Benchmark | Surge AI ↗

    Surge AI

  49. FrontierSWE — software engineering benchmark ↗

    FrontierSWE

  50. BioMysteryBench — evaluation methodology and results ↗

    Vals AI · 2026

  51. Code Migration v1 — evaluation methodology and results ↗

    Vals AI · 2026

  52. Code Migration — evaluation methodology and results ↗

    Vals AI · 2026

  53. CyberBench — evaluation methodology and results ↗

    Vals AI · 2026

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

    Vals AI · 2026

  55. Excel Modeling Benchmark — evaluation methodology and results ↗

    Vals AI · 2026

  56. Finance Agent v2 — evaluation methodology and results ↗

    Vals AI · 2026

  57. Finance Agent — evaluation methodology and results ↗

    Vals AI · 2026

  58. Vals Finance Index — evaluation methodology and results ↗

    Vals AI · 2026

  59. HLAB-Vals-1.1 — evaluation methodology and results ↗

    Vals AI · 2026

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

    Vals AI · 2026

  61. IOI — evaluation methodology and results ↗

    Vals AI · 2026

  62. Vals Legal Index — evaluation methodology and results ↗

    Vals AI · 2026

  63. Legal Research Bench — evaluation methodology and results ↗

    Vals AI · 2026

  64. MedCode — evaluation methodology and results ↗

    Vals AI · 2026

  65. MedScribe — evaluation methodology and results ↗

    Vals AI · 2026

  66. SAFE-Teen: Teen Mental Health & Safety | Vals AI A conversation branches after the chatbot turns down a request — evaluation methodology and results ↗

    Vals AI · 2026

  67. MysteryMechanism — 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. SAGE — evaluation methodology and results ↗

    Vals AI · 2026

  72. Vals Science Index — evaluation methodology and results ↗

    Vals AI · 2026

  73. SRE Bench — evaluation methodology and results ↗

    Vals AI · 2026

  74. SWE-bench Multimodal — evaluation methodology and results ↗

    Vals AI · 2026

  75. Tax Agent Bench — evaluation methodology and results ↗

    Vals AI · 2026

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

    Vals AI · 2026

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

    Vals AI · 2026

  78. Vals Index — evaluation methodology and results ↗

    Vals AI · 2026

  79. Vibe Code Bench — evaluation methodology and results ↗

    Vals AI · 2026

Names used in source tables

Claude Sonnet 5.5 · Claude Sonnet 5.5 (Max, Default Fallback) · Claude Sonnet 5.5 (Mini-SWE-agent) · Claude Sonnet 5.5 (OpenHands) · Claude Sonnet 5.5 (high) · Claude Sonnet 5.5 (low) · Claude Sonnet 5.5 (max) · Claude Sonnet 5.5 (medium) · Claude Sonnet 5.5 (xhigh) · Sonnet 5.5 (mini-swe-agent) xhigh · claude-sonnet-5-5