Name: Claude Opus 4.6 vs Claude Opus 4.7
Creator: Benchmark Registry

Shared benchmarks

Shared benchmarks for Claude Opus 4.6 and Claude Opus 4.7
Benchmark	Claude Opus 4.6	Claude Opus 4.7
GPQA Diamond	91.3%	94.2%
Evaluation details for GPQA Diamond The recorded benchmark version, metric, and evaluator sets match. Evaluation methodology is not recorded by the registry. Claude Opus 4.6 Score 91.3% Evaluator Anthropic Version GPQA Diamond Metric GPQA Diamond Accuracy (percent) Reasoning adaptive thinking, max Reported February 5, 2026 Source Evaluation source for Claude Opus 4.6 on GPQA Diamond (opens in a new tab) Claude Opus 4.7 Score 94.2% Evaluator Anthropic Version GPQA Diamond Metric GPQA Diamond Accuracy (percent) Reasoning adaptive thinking, max Reported April 16, 2026 Source Evaluation source for Claude Opus 4.7 on GPQA Diamond (opens in a new tab)
Humanity's Last Exam Full set — No tools	40.0%	46.9%
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 4.6 Score 40.0% Evaluator Anthropic Version Humanity's Last Exam Full set — No tools Metric Humanity's Last Exam Accuracy (percent) Reasoning adaptive thinking, max Reported February 5, 2026 Source Evaluation source for Claude Opus 4.6 on Humanity's Last Exam Full set — No tools (opens in a new tab) Claude Opus 4.7 Score 46.9% Evaluator Anthropic Version Humanity's Last Exam Full set — No tools Metric Humanity's Last Exam Accuracy (percent) Reasoning adaptive thinking, max Reported April 16, 2026 Source Evaluation source for Claude Opus 4.7 on Humanity's Last Exam Full set — No tools (opens in a new tab)
Humanity's Last Exam Full set — With tools	53.0%	43.0%Full set — With tools · Humanity's Last Exam Accuracy Anthropic 53.2%Full set — With tools · Humanity's Last Exam Accuracy Anthropic 55.4%Full set — With tools · Humanity's Last Exam Accuracy Anthropic 48.4%Full set — With tools · Humanity's Last Exam Accuracy Anthropic 54.7%Full set — With tools · Humanity's Last Exam Accuracy Anthropic
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 4.6 Score 53.0% Evaluator Anthropic Version Humanity's Last Exam Full set — With tools Metric Humanity's Last Exam Accuracy (percent) Reasoning adaptive thinking, max Reported February 5, 2026 Source Evaluation source for Claude Opus 4.6 on Humanity's Last Exam Full set — With tools (opens in a new tab) Claude Opus 4.7 Score 43.0% Evaluator Anthropic Version Humanity's Last Exam Full set — With tools Metric Humanity's Last Exam Accuracy (percent) Reasoning adaptive thinking, low Reported April 16, 2026 Source Evaluation source for Claude Opus 4.7 on Humanity's Last Exam Full set — With tools (opens in a new tab) Score 53.2% Evaluator Anthropic Version Humanity's Last Exam Full set — With tools Metric Humanity's Last Exam Accuracy (percent) Reasoning adaptive thinking, high Reported April 16, 2026 Source Evaluation source for Claude Opus 4.7 on Humanity's Last Exam Full set — With tools (opens in a new tab) Score 55.4% Evaluator Anthropic Version Humanity's Last Exam Full set — With tools Metric Humanity's Last Exam Accuracy (percent) Reasoning adaptive thinking, xhigh Reported April 16, 2026 Source Evaluation source for Claude Opus 4.7 on Humanity's Last Exam Full set — With tools (opens in a new tab) Score 48.4% Evaluator Anthropic Version Humanity's Last Exam Full set — With tools Metric Humanity's Last Exam Accuracy (percent) Reasoning adaptive thinking, medium Reported April 16, 2026 Source Evaluation source for Claude Opus 4.7 on Humanity's Last Exam Full set — With tools (opens in a new tab) Score 54.7% Evaluator Anthropic Version Humanity's Last Exam Full set — With tools Metric Humanity's Last Exam Accuracy (percent) Reasoning adaptive thinking, max Reported April 16, 2026 Source Evaluation source for Claude Opus 4.7 on Humanity's Last Exam Full set — With tools (opens in a new tab)
MCP Atlas Public, April 2026 update	76.8%	79.1%
Evaluation details for MCP Atlas Public, April 2026 update The recorded benchmark version, metric, and evaluator sets match. Evaluation methodology is not recorded by the registry. Claude Opus 4.6 Score 76.8% Evaluator Scale AI Version MCP Atlas Public, April 2026 update Metric Pass rate (percent) Reasoning max Reported September 24, 2026 Source Evaluation source for Claude Opus 4.6 on MCP Atlas Public, April 2026 update (opens in a new tab) Claude Opus 4.7 Score 79.1% Evaluator Scale AI Version MCP Atlas Public, April 2026 update Metric Pass rate (percent) Reasoning max Reported September 24, 2026 Source Evaluation source for Claude Opus 4.7 on MCP Atlas Public, April 2026 update (opens in a new tab)
SWE-bench Multilingual	77.8%	80.5%
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 4.6 Score 77.8% Evaluator Anthropic Version SWE-bench Multilingual Metric Resolved Tasks (percent) Reasoning adaptive thinking, max Reported February 5, 2026 Source Evaluation source for Claude Opus 4.6 on SWE-bench Multilingual (opens in a new tab) Claude Opus 4.7 Score 80.5% Evaluator Anthropic Version SWE-bench Multilingual Metric Resolved Tasks (percent) Reasoning adaptive thinking, max Reported April 16, 2026 Source Evaluation source for Claude Opus 4.7 on SWE-bench Multilingual (opens in a new tab)
SWE-bench Verified	80.8%	87.6%
Evaluation details for SWE-bench Verified The recorded benchmark version, metric, and evaluator sets match. Evaluation methodology is not recorded by the registry. Claude Opus 4.6 Score 80.8% Evaluator Anthropic Version SWE-bench Verified Metric Resolved Tasks (percent) Reasoning adaptive thinking, max Reported February 5, 2026 Source Evaluation source for Claude Opus 4.6 on SWE-bench Verified (opens in a new tab) Claude Opus 4.7 Score 87.6% Evaluator Anthropic Version SWE-bench Verified Metric Resolved Tasks (percent) Reasoning adaptive thinking, max Reported April 16, 2026 Source Evaluation source for Claude Opus 4.7 on SWE-bench Verified (opens in a new tab)
Terminal-Bench 2.0	65.4%	69.4%
Evaluation details for Terminal-Bench 2.0 The recorded benchmark version, metric, and evaluator sets match. Evaluation methodology is not recorded by the registry. Claude Opus 4.6 Score 65.4% Evaluator Anthropic Version Terminal-Bench 2.0 Metric Terminal-Bench Accuracy (percent) Reasoning adaptive thinking, max Reported February 5, 2026 Source Evaluation source for Claude Opus 4.6 on Terminal-Bench 2.0 (opens in a new tab) Claude Opus 4.7 Score 69.4% Evaluator Anthropic Version Terminal-Bench 2.0 Metric Terminal-Bench Accuracy (percent) Reasoning no thinking Reported April 16, 2026 Source Evaluation source for Claude Opus 4.7 on Terminal-Bench 2.0 (opens in a new tab)