RLTasksby ulam.ai
Models / Anthropic

Anthropic / MODEL EVIDENCE

Claude Haiku 5.5

72 benchmarks · 168 observations · 78 sources · released 2026-10-07

Scores at a glance

72 benchmarks · large dot: Claude Haiku 5.5; small dots: closest models where reported

GDP.pdf ↗20.80%
7.432.6

Claude Haiku 5.5 (Max) · GDP.pdf · all-pass ↗

HLE-Diamond ↗29.60%
8.867.9

Claude Haiku 5.5 (Max) · HLE-Diamond · AA implementation ↗

AA-Omniscience v1.1 ↗12.30 index
-8.2748.13

Claude Haiku 5.5 (Max) · AA-Omniscience v1.1 · error-penalized index ↗

1 more reported result

10.67 index · Claude Haiku 5.5 (Max) · AA-Omniscience · error-penalized score · Artificial Analysis ↗

AA-3D ↗997.77 Elo
572.551198.83

Claude Haiku 5.5 (Max) · AA-3D · Elo ↗

SciCode ↗54.98%
42.9466.9

Claude Haiku 5.5 (Max) · SciCode · AA implementation ↗

5 more reported results

54.98% · Claude Haiku 5.5 (max) · SciCode · Score · % · Epoch AI · SciCode ↗

51.74% · Claude Haiku 5.5 (xhigh) · SciCode · Score · % · Epoch AI · SciCode ↗

49.19% · Claude Haiku 5.5 (low) · SciCode · Score · % · Epoch AI · SciCode ↗

48.96% · Claude Haiku 5.5 (medium) · SciCode · Score · % · Epoch AI · SciCode ↗

48.73% · Claude Haiku 5.5 (high) · SciCode · Score · % · Epoch AI · SciCode ↗

MLCR-AA ↗35.00%
6.1141.67

Claude Haiku 5.5 (Max) · MLCR-AA · overall ↗

HealthBench ↗58.36%
50.765.98

Claude Haiku 5.5 (Max) · HealthBench · HealthBench Professional · length-adjusted ↗

CritPt ↗18.86%
4.5732.86

Claude Haiku 5.5 (Max) · CritPt · original ↗

5 more reported results

22.57% · Claude Haiku 5.5 (xhigh) · CritPt · Accuracy · % · Epoch AI · CritPt ↗

18.86% · Claude Haiku 5.5 (max) · CritPt · Accuracy · % · Epoch AI · CritPt ↗

18.57% · Claude Haiku 5.5 (high) · CritPt · Accuracy · % · Epoch AI · CritPt ↗

12.86% · Claude Haiku 5.5 (medium) · CritPt · Accuracy · % · Epoch AI · CritPt ↗

9.14% · Claude Haiku 5.5 (low) · CritPt · Accuracy · % · Epoch AI · CritPt ↗

GPQA Diamond ↗89.65%
9.2896.4

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

WeirdML (v3) ↗24.13%
4.3854.05

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

MedCode ↗51.54 %
19.7263.57

Claude Haiku 5.5 · MedCode · Accuracy ↗

Fortress ↗9.48%
5.7874.39

Claude Haiku 5.5 · Scale Labs · Risk elicitation score ↗

GDPx v1.0 ↗4.9%
1.6712.03

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

53 more reported results

4.5% · Claude Haiku 5.5 · GDPx v1.0 · Eight-domain subset · intended grading · GDPx v1.0 — SemiAnalysis ↗

11.3% · Claude Haiku 5.5 · GDPx v1.0 · Recursive Self-Improvement · intended grading · GDPx v1.0 — SemiAnalysis ↗

0.7% · Claude Haiku 5.5 · GDPx v1.0 · Chip Design · intended grading · GDPx v1.0 — SemiAnalysis ↗

9.3% · Claude Haiku 5.5 · GDPx v1.0 · Cybersecurity · intended grading · GDPx v1.0 — SemiAnalysis ↗

7.7% · Claude Haiku 5.5 · GDPx v1.0 · Biology · intended grading · GDPx v1.0 — SemiAnalysis ↗

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

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

6.7% · Claude Haiku 5.5 · GDPx v1.0 · Quant Trading · intended grading · GDPx v1.0 — SemiAnalysis ↗

3.1% · Claude Haiku 5.5 · GDPx v1.0 · Hardware Design · intended grading · GDPx v1.0 — SemiAnalysis ↗

7.2% · Claude Haiku 5.5 · GDPx v1.0 · Materials Science · intended grading · GDPx v1.0 — SemiAnalysis ↗

1.8% · Claude Haiku 5.5 · GDPx v1.0 · Alignment · intended grading · GDPx v1.0 — SemiAnalysis ↗

6.7% · Claude Haiku 5.5 · GDPx v1.0 · Software Engineering · intended grading · GDPx v1.0 — SemiAnalysis ↗

10.4% · Claude Haiku 5.5 · GDPx v1.0 · Overall · partial credit · GDPx v1.0 — SemiAnalysis ↗

11.6% · Claude Haiku 5.5 · GDPx v1.0 · Eight-domain subset · partial credit · GDPx v1.0 — SemiAnalysis ↗

11.3% · Claude Haiku 5.5 · GDPx v1.0 · Recursive Self-Improvement · partial credit · GDPx v1.0 — SemiAnalysis ↗

2.4% · Claude Haiku 5.5 · GDPx v1.0 · Chip Design · partial credit · GDPx v1.0 — SemiAnalysis ↗

9.3% · Claude Haiku 5.5 · GDPx v1.0 · Cybersecurity · partial credit · GDPx v1.0 — SemiAnalysis ↗

11.1% · Claude Haiku 5.5 · GDPx v1.0 · Biology · partial credit · GDPx v1.0 — SemiAnalysis ↗

30.8% · Claude Haiku 5.5 · GDPx v1.0 · Finance · partial credit · GDPx v1.0 — SemiAnalysis ↗

20.3% · Claude Haiku 5.5 · GDPx v1.0 · Legal · partial credit · GDPx v1.0 — SemiAnalysis ↗

6.7% · Claude Haiku 5.5 · GDPx v1.0 · Quant Trading · partial credit · GDPx v1.0 — SemiAnalysis ↗

3.1% · Claude Haiku 5.5 · GDPx v1.0 · Hardware Design · partial credit · GDPx v1.0 — SemiAnalysis ↗

11.6% · Claude Haiku 5.5 · GDPx v1.0 · Materials Science · partial credit · GDPx v1.0 — SemiAnalysis ↗

1.8% · Claude Haiku 5.5 · GDPx v1.0 · Alignment · partial credit · GDPx v1.0 — SemiAnalysis ↗

6.7% · Claude Haiku 5.5 · GDPx v1.0 · Software Engineering · partial credit · GDPx v1.0 — SemiAnalysis ↗

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

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

2.0% · Claude Haiku 5.5 · GDPx v1.0 · Ergodex · Chip Design · intended grading · GDPx v1.0 — SemiAnalysis ↗

9.3% · Claude Haiku 5.5 · GDPx v1.0 · Arithmetic · Cybersecurity · intended grading · GDPx v1.0 — SemiAnalysis ↗

7.7% · Claude Haiku 5.5 · GDPx v1.0 · LatchBio · Biology · intended grading · GDPx v1.0 — SemiAnalysis ↗

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

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

6.7% · Claude Haiku 5.5 · GDPx v1.0 · Third Moment · Quant Trading · intended grading · GDPx v1.0 — SemiAnalysis ↗

11.3% · Claude Haiku 5.5 · GDPx v1.0 · Extrapolate · Recursive Self-Improvement · intended grading · GDPx v1.0 — SemiAnalysis ↗

3.1% · Claude Haiku 5.5 · GDPx v1.0 · Beautiful Machines · Hardware Design · intended grading · GDPx v1.0 — SemiAnalysis ↗

5.8% · Claude Haiku 5.5 · GDPx v1.0 · ValenceForge · Materials Science · intended grading · GDPx v1.0 — SemiAnalysis ↗

8.7% · Claude Haiku 5.5 · GDPx v1.0 · Emulated · Materials Science · intended grading · GDPx v1.0 — SemiAnalysis ↗

1.8% · Claude Haiku 5.5 · GDPx v1.0 · Fleet · Alignment · intended grading · GDPx v1.0 — SemiAnalysis ↗

6.7% · Claude Haiku 5.5 · GDPx v1.0 · Datacurve · Software Engineering · intended grading · GDPx v1.0 — SemiAnalysis ↗

5.1% · Claude Haiku 5.5 · GDPx v1.0 · Aria · Chip Design · partial credit · GDPx v1.0 — SemiAnalysis ↗

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

2.0% · Claude Haiku 5.5 · GDPx v1.0 · Ergodex · Chip Design · partial credit · GDPx v1.0 — SemiAnalysis ↗

9.3% · Claude Haiku 5.5 · GDPx v1.0 · Arithmetic · Cybersecurity · partial credit · GDPx v1.0 — SemiAnalysis ↗

11.1% · Claude Haiku 5.5 · GDPx v1.0 · LatchBio · Biology · partial credit · GDPx v1.0 — SemiAnalysis ↗

30.8% · Claude Haiku 5.5 · GDPx v1.0 · Living Context · Finance · partial credit · GDPx v1.0 — SemiAnalysis ↗

20.3% · Claude Haiku 5.5 · GDPx v1.0 · Chakra · Legal · partial credit · GDPx v1.0 — SemiAnalysis ↗

6.7% · Claude Haiku 5.5 · GDPx v1.0 · Third Moment · Quant Trading · partial credit · GDPx v1.0 — SemiAnalysis ↗

11.3% · Claude Haiku 5.5 · GDPx v1.0 · Extrapolate · Recursive Self-Improvement · partial credit · GDPx v1.0 — SemiAnalysis ↗

3.1% · Claude Haiku 5.5 · GDPx v1.0 · Beautiful Machines · Hardware Design · partial credit · GDPx v1.0 — SemiAnalysis ↗

11.6% · Claude Haiku 5.5 · GDPx v1.0 · ValenceForge · Materials Science · partial credit · GDPx v1.0 — SemiAnalysis ↗

11.7% · Claude Haiku 5.5 · GDPx v1.0 · Emulated · Materials Science · partial credit · GDPx v1.0 — SemiAnalysis ↗

1.8% · Claude Haiku 5.5 · GDPx v1.0 · Fleet · Alignment · partial credit · GDPx v1.0 — SemiAnalysis ↗

6.7% · Claude Haiku 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.

24.3 percentile-point gap

54 of 59 shared benchmark comparisons

24.4 percentile-point gap

54 of 59 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. 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. ARC-AGI-2 ↗

    Epoch AI

  30. Chess Puzzles ↗

    Epoch AI

  31. CritPt v1 ↗

    Epoch AI

  32. Earthborne Rangers (EBR-bench) ↗

    Epoch AI

  33. FrontierMath Tier 4 (v2) ↗

    Epoch AI

  34. FrontierMath Tiers 1-3 (v2) ↗

    Epoch AI

  35. Furniture Assembly Benchmark ↗

    Epoch AI

  36. GPQA Diamond ↗

    Epoch AI

  37. Mystery Game Puzzles ↗

    Epoch AI

  38. OTIS Mock AIME 2024-2025 ↗

    Epoch AI

  39. SimpleQA Verified ↗

    Epoch AI

  40. Vending Bench 2 — methodology and published results ↗

    Epoch AI · 2026

  41. AI benchmarks & capabilities ↗

    Epoch AI

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

    SemiAnalysis · 2026

  43. WeirdML ↗

    Håvard Tveit Ihle

  44. Scale Labs — evaluation methodology and results ↗

    Scale Labs / SEAL · 2026

  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. FrontierSWE — software engineering benchmark ↗

    FrontierSWE

  49. BioMysteryBench — evaluation methodology and results ↗

    Vals AI · 2026

  50. Code Migration v1 — evaluation methodology and results ↗

    Vals AI · 2026

  51. Code Migration — evaluation methodology and results ↗

    Vals AI · 2026

  52. CyberBench — evaluation methodology and results ↗

    Vals AI · 2026

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

    Vals AI · 2026

  54. Excel Modeling Benchmark — evaluation methodology and results ↗

    Vals AI · 2026

  55. Finance Agent v2 — evaluation methodology and results ↗

    Vals AI · 2026

  56. Finance Agent — evaluation methodology and results ↗

    Vals AI · 2026

  57. Vals Finance Index — evaluation methodology and results ↗

    Vals AI · 2026

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

    Vals AI · 2026

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

    Vals AI · 2026

  60. IOI — evaluation methodology and results ↗

    Vals AI · 2026

  61. Vals Legal Index — 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. MysteryMechanism — evaluation methodology and results ↗

    Vals AI · 2026

  66. ProgramBench — evaluation methodology and results ↗

    Vals AI · 2026

  67. ProofBench — evaluation methodology and results ↗

    Vals AI · 2026

  68. Public Benefits Bench — evaluation methodology and results ↗

    Vals AI · 2026

  69. SAGE — evaluation methodology and results ↗

    Vals AI · 2026

  70. Vals Science Index — evaluation methodology and results ↗

    Vals AI · 2026

  71. SRE Bench — evaluation methodology and results ↗

    Vals AI · 2026

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

    Vals AI · 2026

  73. Tax Agent Bench — evaluation methodology and results ↗

    Vals AI · 2026

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

    Vals AI · 2026

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

    Vals AI · 2026

  76. Vals Index — evaluation methodology and results ↗

    Vals AI · 2026

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

    Vals AI · 2026

  78. Vibe Code Bench — evaluation methodology and results ↗

    Vals AI · 2026

Names used in source tables

Claude Haiku 5.5 · Claude Haiku 5.5 (Max) · Claude Haiku 5.5 (Mini-SWE-agent) · Claude Haiku 5.5 (OpenHands) · Claude Haiku 5.5 (high) · Claude Haiku 5.5 (low) · Claude Haiku 5.5 (max) · Claude Haiku 5.5 (medium) · Claude Haiku 5.5 (xhigh) · Haiku 5.5 (mini-swe-agent) high