Shared benchmarks

31
Shared benchmarks for Claude Opus 5 and Claude Opus 5.5
BenchmarkClaude Opus 5Claude Opus 5.5
  • 65.8%
  • 52.5%medium
  • 73.5%max
Evaluation details for APEX-Agents Original

The recorded benchmark version, metric, and evaluator sets match. Evaluation methodology is not recorded by the registry.

Claude Opus 5

Record for Claude Opus 5 on APEX-Agents Original

Claude Opus 5.5

Record for Claude Opus 5.5 on APEX-Agents Original
Record for Claude Opus 5.5 on APEX-Agents Original
  • 20.4%low
  • 23.9%medium
  • 20.6%high
  • 25.3%xhigh
  • 26.9%max
  • 40.0%
Evaluation details for AutomationBench 1.0.6

The recorded benchmark version, metric, and evaluator sets match. Evaluation methodology is not recorded by the registry.

Claude Opus 5

Record for Claude Opus 5 on AutomationBench 1.0.6
Record for Claude Opus 5 on AutomationBench 1.0.6
Record for Claude Opus 5 on AutomationBench 1.0.6
Record for Claude Opus 5 on AutomationBench 1.0.6
Record for Claude Opus 5 on AutomationBench 1.0.6

Claude Opus 5.5

Record for Claude Opus 5.5 on AutomationBench 1.0.6
  • 84.6%
  • 88.5%
Evaluation details for BrowseComp 130-question subset — Mercor web research agent

The recorded benchmark version, metric, and evaluator sets match. Evaluation methodology is not recorded by the registry.

Claude Opus 5

  • 27.3%
  • 66.3%
Evaluation details for Chartography October 2026 leaderboard

The recorded benchmark version, metric, and evaluator sets match. Evaluation methodology is not recorded by the registry.

Claude Opus 5

Record for Claude Opus 5 on Chartography October 2026 leaderboard

Claude Opus 5.5

Record for Claude Opus 5.5 on Chartography October 2026 leaderboard
  • 94.6%
  • 96.4%
Evaluation details for CharXiv Descriptive and reasoning — Mercor single-shot

The recorded benchmark version, metric, and evaluator sets match. Evaluation methodology is not recorded by the registry.

  • 40.7%low
  • 43.3%medium
  • 44.7%high
  • 46.1%xhigh
  • 46.6%max
  • 43.7%low
  • 52.5%medium
  • 56.0%high
  • 56.0%xhigh
  • 57.8%max
Evaluation details for CursorBench 4.0

The recorded benchmark version, metric, and evaluator sets match. Evaluation methodology is not recorded by the registry.

Claude Opus 5

Record for Claude Opus 5 on CursorBench 4.0
Record for Claude Opus 5 on CursorBench 4.0
Record for Claude Opus 5 on CursorBench 4.0
Record for Claude Opus 5 on CursorBench 4.0
Record for Claude Opus 5 on CursorBench 4.0

Claude Opus 5.5

Record for Claude Opus 5.5 on CursorBench 4.0
Record for Claude Opus 5.5 on CursorBench 4.0
Record for Claude Opus 5.5 on CursorBench 4.0
Record for Claude Opus 5.5 on CursorBench 4.0
Record for Claude Opus 5.5 on CursorBench 4.0
DeepSWE 1.1Potentially non-equivalent: Evaluator sets differ.
  • 57.7%low · 1.1 · Anthropic
  • 66.9%medium · 1.1 · Anthropic
  • 68.0%high · 1.1 · Anthropic
  • 69.7%xhigh · 1.1 · Anthropic
  • 68.8%max · 1.1 · Anthropic
  • 74.0%max · 1.1 · DataCurve
  • 74.2%1.1 · Anthropic
Potentially non-equivalent · Evaluation details for DeepSWE 1.1

Evaluator sets differ. Evaluation methodology is not recorded by the registry.

Claude Opus 5

Record for Claude Opus 5 on DeepSWE 1.1
Record for Claude Opus 5 on DeepSWE 1.1
Record for Claude Opus 5 on DeepSWE 1.1
Record for Claude Opus 5 on DeepSWE 1.1
Record for Claude Opus 5 on DeepSWE 1.1
Record for Claude Opus 5 on DeepSWE 1.1

Claude Opus 5.5

Record for Claude Opus 5.5 on DeepSWE 1.1
  • 70.2%xhigh
  • 71.4%max
  • 72.3%
Evaluation details for DeepSWE 1.1 — Mercor mini-swe-agent, 500 steps

The recorded benchmark version, metric, and evaluator sets match. Evaluation methodology is not recorded by the registry.

Claude Opus 5

Record for Claude Opus 5 on DeepSWE 1.1 — Mercor mini-swe-agent, 500 steps
Record for Claude Opus 5 on DeepSWE 1.1 — Mercor mini-swe-agent, 500 steps

Claude Opus 5.5

  • 58.6%
  • 58.6%
Evaluation details for Finance Agent Benchmark 2 — October 2026 evaluation

The recorded benchmark version, metric, and evaluator sets match. Evaluation methodology is not recorded by the registry.

  • 52.0%
  • 62.3%
Evaluation details for FrontierSWE 2 — October 2026 evaluation

The recorded benchmark version, metric, and evaluator sets match. Evaluation methodology is not recorded by the registry.

Claude Opus 5

Record for Claude Opus 5 on FrontierSWE 2 — October 2026 evaluation

Claude Opus 5.5

Record for Claude Opus 5.5 on FrontierSWE 2 — October 2026 evaluation
  • 92.5%
  • 94.3%
Evaluation details for Global MMLU Original

The recorded benchmark version, metric, and evaluator sets match. Evaluation methodology is not recorded by the registry.

Claude Opus 5

Record for Claude Opus 5 on Global MMLU Original

Claude Opus 5.5

Record for Claude Opus 5.5 on Global MMLU Original
  • 87.9%low
  • 93.9%max
  • 92.9%
  • 90.6%
Evaluation details for GPQA Diamond — Epoch AI harness

The recorded benchmark version, metric, and evaluator sets match. Evaluation methodology is not recorded by the registry.

Claude Opus 5

Record for Claude Opus 5 on Graduate-Level Google-Proof Q&A Diamond — Epoch AI harness

Claude Opus 5.5

  • 93.6%
  • 91.3%
Evaluation details for GPQA Diamond — Mercor single-shot

The recorded benchmark version, metric, and evaluator sets match. Evaluation methodology is not recorded by the registry.

Claude Opus 5

Record for Claude Opus 5 on Graduate-Level Google-Proof Q&A Diamond — Mercor single-shot

Claude Opus 5.5

  • 6.7%
  • 3.8%
Evaluation details for HLAB October 2026 evaluation

The recorded benchmark version, metric, and evaluator sets match. Evaluation methodology is not recorded by the registry.

Claude Opus 5

Record for Claude Opus 5 on Harvey's Legal Agent Benchmark October 2026 evaluation

Claude Opus 5.5

Record for Claude Opus 5.5 on Harvey's Legal Agent Benchmark October 2026 evaluation
  • 47.8%low
  • 54.2%medium
  • 56.0%high
  • 56.4%xhigh
  • 56.3%max
  • 52.9%low
  • 59.0%medium
  • 59.6%high
  • 62.8%xhigh
  • 64.4%max
Evaluation details for Humanity's Last Exam Full set — No tools

The recorded benchmark version, metric, and evaluator sets match. Evaluation methodology is not recorded by the registry.

Claude Opus 5

Record for Claude Opus 5 on Humanity's Last Exam Full set — No tools

Claude Opus 5.5

Record for Claude Opus 5.5 on Humanity's Last Exam Full set — No tools
Record for Claude Opus 5.5 on Humanity's Last Exam Full set — No tools
Record for Claude Opus 5.5 on Humanity's Last Exam Full set — No tools
  • 56.1%low
  • 61.3%medium
  • 63.2%high
  • 64.8%xhigh
  • 64.7%max
  • 57.4%low
  • 63.0%medium
  • 63.9%high
  • 66.4%xhigh
  • 67.7%adaptive thinking, max; with tools
Evaluation details for Humanity's Last Exam Full set — With tools

The recorded benchmark version, metric, and evaluator sets match. Evaluation methodology is not recorded by the registry.

Claude Opus 5

Claude Opus 5.5

Record for Claude Opus 5.5 on Humanity's Last Exam Full set — With tools
Record for Claude Opus 5.5 on Humanity's Last Exam Full set — With tools
  • 52.0%high
  • 53.2%max
  • 57.4%
Evaluation details for Humanity's Last Exam Text only — Mercor single-shot

The recorded benchmark version, metric, and evaluator sets match. Evaluation methodology is not recorded by the registry.

  • 79.8%
  • 85.7%
Evaluation details for MedXpertQA MM — Mercor single-shot

The recorded benchmark version, metric, and evaluator sets match. Evaluation methodology is not recorded by the registry.

Claude Opus 5

Record for Claude Opus 5 on MedXpertQA MM — Mercor single-shot

Claude Opus 5.5

Record for Claude Opus 5.5 on MedXpertQA MM — Mercor single-shot
  • 92.1%
  • 93.1%
Evaluation details for MILU Original

The recorded benchmark version, metric, and evaluator sets match. Evaluation methodology is not recorded by the registry.

Claude Opus 5

Record for Claude Opus 5 on Multi-task Indic Language Understanding Benchmark Original

Claude Opus 5.5

Record for Claude Opus 5.5 on Multi-task Indic Language Understanding Benchmark Original
  • 92.0%
  • 93.4%
Evaluation details for MMLU-Pro Original — Mercor single-shot

The recorded benchmark version, metric, and evaluator sets match. Evaluation methodology is not recorded by the registry.

Claude Opus 5

Claude Opus 5.5

  • 84.2%
  • 87.4%
Evaluation details for MMMU-Pro 1,730 questions — Mercor single-shot

The recorded benchmark version, metric, and evaluator sets match. Evaluation methodology is not recorded by the registry.

Claude Opus 5

Record for Claude Opus 5 on MMMU-Pro 1,730 questions — Mercor single-shot

Claude Opus 5.5

Record for Claude Opus 5.5 on MMMU-Pro 1,730 questions — Mercor single-shot
  • 35.7%
  • 43.8%
Evaluation details for PostTrainBench 1.2 — Claude Code

The recorded benchmark version, metric, and evaluator sets match. Evaluation methodology is not recorded by the registry.

Claude Opus 5

Record for Claude Opus 5 on PostTrainBench 1.2 — Claude Code

Claude Opus 5.5

Record for Claude Opus 5.5 on PostTrainBench 1.2 — Claude Code
  • 68.0%
  • 69.6%
Evaluation details for Riemann-bench October 2026 leaderboard

The recorded benchmark version, metric, and evaluator sets match. Evaluation methodology is not recorded by the registry.

Claude Opus 5

Record for Claude Opus 5 on Riemann-bench October 2026 leaderboard

Claude Opus 5.5

Record for Claude Opus 5.5 on Riemann-bench October 2026 leaderboard
  • 59.9%
  • 72.2%
Evaluation details for SimpleQA Verified Original — Epoch AI harness

The recorded benchmark version, metric, and evaluator sets match. Evaluation methodology is not recorded by the registry.

  • 50.3%
  • 48.9%
Evaluation details for SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps

The recorded benchmark version, metric, and evaluator sets match. Evaluation methodology is not recorded by the registry.

  • 89.5%
  • 93.9%
Evaluation details for SWE-bench Multilingual

The recorded benchmark version, metric, and evaluator sets match. Evaluation methodology is not recorded by the registry.

Claude Opus 5

Record for Claude Opus 5 on SWE-bench Multilingual

Claude Opus 5.5

Record for Claude Opus 5.5 on SWE-bench Multilingual
  • 96.2%
  • 95.5%
Evaluation details for SWE-bench Multilingual — Mercor mini-swe-agent, 1000 steps

The recorded benchmark version, metric, and evaluator sets match. Evaluation methodology is not recorded by the registry.

  • 93.5%
  • 98.2%
Evaluation details for SWE-bench Verified — Mercor mini-swe-agent, 1000 steps

The recorded benchmark version, metric, and evaluator sets match. Evaluation methodology is not recorded by the registry.

Claude Opus 5

  • 34.9%low
  • 44.9%medium
  • 50.3%high
  • 53.9%xhigh
  • 51.8%max
  • 64.9%
Evaluation details for Terminal-Bench 4.0 — Claude Code

The recorded benchmark version, metric, and evaluator sets match. Evaluation methodology is not recorded by the registry.

Claude Opus 5

Record for Claude Opus 5 on Terminal-Bench 4.0 — Claude Code
Record for Claude Opus 5 on Terminal-Bench 4.0 — Claude Code
Record for Claude Opus 5 on Terminal-Bench 4.0 — Claude Code
Record for Claude Opus 5 on Terminal-Bench 4.0 — Claude Code
Record for Claude Opus 5 on Terminal-Bench 4.0 — Claude Code

Claude Opus 5.5

Record for Claude Opus 5.5 on Terminal-Bench 4.0 — Claude Code
  • 49.5%
  • 58.3%
Evaluation details for Terminal-Bench 4.0 — Mercor mini-swe-agent

The recorded benchmark version, metric, and evaluator sets match. Evaluation methodology is not recorded by the registry.

Claude Opus 5

Record for Claude Opus 5 on Terminal-Bench 4.0 — Mercor mini-swe-agent

Claude Opus 5.5

Record for Claude Opus 5.5 on Terminal-Bench 4.0 — Mercor mini-swe-agent
  • 88.4%
  • 90.3%
Evaluation details for Vibe Code Bench 1.1 — OpenHands, October 2026 evaluation

The recorded benchmark version, metric, and evaluator sets match. Evaluation methodology is not recorded by the registry.