Benchmarks

81 results across 29 benchmarks

Benchmark results for Claude Opus 5
BenchmarkScoreSource
APEX-Agents OriginalEffort: Max65.8%mercor.com for Claude Opus 5 (max) on APEX-Agents Original (opens in a new tab)Archived copy (opens in a new tab)Pass rateReported Benchmark leaderboardMercorIndependentRecord for Claude Opus 5 on APEX-Agents Original
AutomationBench 1.0.6Effort: Low20.4%zapier.com for Claude Opus 5 (low) on AutomationBench 1.0.6 (opens in a new tab)Archived copy (opens in a new tab)Task pass rateReported Benchmark leaderboardZapierIndependentZapier AutomationBench TeamRecord for Claude Opus 5 on AutomationBench 1.0.6
AutomationBench 1.0.6Effort: Medium23.9%zapier.com for Claude Opus 5 (medium) on AutomationBench 1.0.6 (opens in a new tab)Archived copy (opens in a new tab)Task pass rateReported Benchmark leaderboardZapierIndependentZapier AutomationBench TeamRecord for Claude Opus 5 on AutomationBench 1.0.6
AutomationBench 1.0.6Effort: High20.6%zapier.com for Claude Opus 5 (high) on AutomationBench 1.0.6 (opens in a new tab)Archived copy (opens in a new tab)Task pass rateReported Benchmark leaderboardZapierIndependentZapier AutomationBench TeamRecord for Claude Opus 5 on AutomationBench 1.0.6
AutomationBench 1.0.6Effort: xHigh25.3%zapier.com for Claude Opus 5 (xhigh) on AutomationBench 1.0.6 (opens in a new tab)Archived copy (opens in a new tab)Task pass rateReported Benchmark leaderboardZapierIndependentZapier AutomationBench TeamRecord for Claude Opus 5 on AutomationBench 1.0.6
AutomationBench 1.0.6Effort: Max26.9%zapier.com for Claude Opus 5 (max) on AutomationBench 1.0.6 (opens in a new tab)Archived copy (opens in a new tab)Task pass rateReported Benchmark leaderboardZapierIndependentZapier AutomationBench TeamRecord for Claude Opus 5 on AutomationBench 1.0.6
BrowseComp 130-question subset — Mercor web research agentEffort: MaxConfiguration: Mercor web research agent, 100 steps, 3 hours84.6%mercor.com for Claude Opus 5 (max) on BrowseComp 130-question subset — Mercor web research agent (opens in a new tab)Archived copy (opens in a new tab)BrowseComp AccuracyReported Benchmark leaderboardMercorIndependentRecord for Claude Opus 5 on BrowseComp 130-question subset — Mercor web research agent
BrowseCompEffort: Low84.4%www-cdn.anthropic.com for Claude Opus 5 (low) on BrowseComp BrowseComp (opens in a new tab)BrowseComp AccuracyReported System cardAnthropicSelf-reportedRecord for Claude Opus 5 on BrowseComp BrowseComp
BrowseCompEffort: Medium88.9%www-cdn.anthropic.com for Claude Opus 5 (medium) on BrowseComp BrowseComp (opens in a new tab)BrowseComp AccuracyReported System cardAnthropicSelf-reportedRecord for Claude Opus 5 on BrowseComp BrowseComp
BrowseCompEffort: High90.2%www-cdn.anthropic.com for Claude Opus 5 (high) on BrowseComp BrowseComp (opens in a new tab)BrowseComp AccuracyReported System cardAnthropicSelf-reportedRecord for Claude Opus 5 on BrowseComp BrowseComp
BrowseCompEffort: xHigh90.7%www-cdn.anthropic.com for Claude Opus 5 (xhigh) on BrowseComp BrowseComp (opens in a new tab)BrowseComp AccuracyReported System cardAnthropicSelf-reportedRecord for Claude Opus 5 on BrowseComp BrowseComp
BrowseCompEffort: Max90.8%www-cdn.anthropic.com for Claude Opus 5 (max) on BrowseComp BrowseComp (opens in a new tab)BrowseComp AccuracyReported System cardAnthropicSelf-reportedRecord for Claude Opus 5 on BrowseComp BrowseComp
Chartography October 2026 leaderboardEffort: MaxReported as: Adaptive/Max27.3%surgehq.ai for Claude Opus 5 (Adaptive/Max) on Chartography October 2026 leaderboard (opens in a new tab)Archived copy (opens in a new tab)Chartography Pass@1Reported Benchmark leaderboardSurge AIIndependentRecord for Claude Opus 5 on Chartography October 2026 leaderboard
CharXiv Descriptive and reasoning — Mercor single-shotEffort: MaxConfiguration: Mercor single-shot agent94.6%mercor.com for Claude Opus 5 (max) on CharXiv Descriptive and reasoning — Mercor single-shot (opens in a new tab)Archived copy (opens in a new tab)CharXiv AccuracyReported Benchmark leaderboardMercorIndependentRecord for Claude Opus 5 on CharXiv Descriptive and reasoning — Mercor single-shot
CursorBench 4.0Effort: Low40.7%cursor.com for Claude Opus 5 (low) on CursorBench 4.0 (opens in a new tab)Archived copy (opens in a new tab)CursorBench AccuracyReported Benchmark leaderboardCursorIndependentRecord for Claude Opus 5 on CursorBench 4.0
CursorBench 4.0Effort: Medium43.3%cursor.com for Claude Opus 5 (medium) on CursorBench 4.0 (opens in a new tab)Archived copy (opens in a new tab)CursorBench AccuracyReported Benchmark leaderboardCursorIndependentRecord for Claude Opus 5 on CursorBench 4.0
CursorBench 4.0Effort: High44.7%cursor.com for Claude Opus 5 (high) on CursorBench 4.0 (opens in a new tab)Archived copy (opens in a new tab)CursorBench AccuracyReported Benchmark leaderboardCursorIndependentRecord for Claude Opus 5 on CursorBench 4.0
CursorBench 4.0Effort: xHigh46.1%cursor.com for Claude Opus 5 (xhigh) on CursorBench 4.0 (opens in a new tab)Archived copy (opens in a new tab)CursorBench AccuracyReported Benchmark leaderboardCursorIndependentRecord for Claude Opus 5 on CursorBench 4.0
CursorBench 4.0Effort: Max46.6%cursor.com for Claude Opus 5 (max) on CursorBench 4.0 (opens in a new tab)CursorBench AccuracyReported Benchmark leaderboardCursorIndependentRecord for Claude Opus 5 on CursorBench 4.0
DeepSearchQA 900-prompt setEffort: Low91.0%www-cdn.anthropic.com for Claude Opus 5 (low) on DeepSearchQA 900-prompt set (opens in a new tab)F1 scoreReported System cardAnthropicSelf-reportedRecord for Claude Opus 5 on DeepSearchQA 900-prompt set
DeepSearchQA 900-prompt setEffort: Medium92.8%www-cdn.anthropic.com for Claude Opus 5 (medium) on DeepSearchQA 900-prompt set (opens in a new tab)F1 scoreReported System cardAnthropicSelf-reportedRecord for Claude Opus 5 on DeepSearchQA 900-prompt set
DeepSearchQA 900-prompt setEffort: High94.1%www-cdn.anthropic.com for Claude Opus 5 (high) on DeepSearchQA 900-prompt set (opens in a new tab)F1 scoreReported System cardAnthropicSelf-reportedRecord for Claude Opus 5 on DeepSearchQA 900-prompt set
DeepSearchQA 900-prompt setEffort: xHigh94.6%www-cdn.anthropic.com for Claude Opus 5 (xhigh) on DeepSearchQA 900-prompt set (opens in a new tab)F1 scoreReported System cardAnthropicSelf-reportedRecord for Claude Opus 5 on DeepSearchQA 900-prompt set
DeepSearchQA 900-prompt setEffort: Max95.0%www-cdn.anthropic.com for Claude Opus 5 (max) on DeepSearchQA 900-prompt set (opens in a new tab)F1 scoreReported System cardAnthropicSelf-reportedRecord for Claude Opus 5 on DeepSearchQA 900-prompt set
DeepSWE 1.1Effort: Low57.7%www-cdn.anthropic.com for Claude Opus 5 (low) on DeepSWE 1.1 (opens in a new tab)DeepSWE Pass@1Reported System cardAnthropicSelf-reportedRecord for Claude Opus 5 on DeepSWE 1.1
DeepSWE 1.1Effort: Medium66.9%www-cdn.anthropic.com for Claude Opus 5 (medium) on DeepSWE 1.1 (opens in a new tab)DeepSWE Pass@1Reported System cardAnthropicSelf-reportedRecord for Claude Opus 5 on DeepSWE 1.1
DeepSWE 1.1Effort: High68.0%www-cdn.anthropic.com for Claude Opus 5 (high) on DeepSWE 1.1 (opens in a new tab)DeepSWE Pass@1Reported System cardAnthropicSelf-reportedRecord for Claude Opus 5 on DeepSWE 1.1
DeepSWE 1.1Effort: xHigh69.7%www-cdn.anthropic.com for Claude Opus 5 (xhigh) on DeepSWE 1.1 (opens in a new tab)DeepSWE Pass@1Reported System cardAnthropicSelf-reportedRecord for Claude Opus 5 on DeepSWE 1.1
DeepSWE 1.1Effort: Max74.0%deepswe.datacurve.ai for Claude Opus 5 (max) on DeepSWE 1.1 (opens in a new tab)DeepSWE Pass@1Reported Benchmark leaderboardDatacurveIndependentRecord for Claude Opus 5 on DeepSWE 1.1
DeepSWE 1.1Effort: Max68.8%www-cdn.anthropic.com for Claude Opus 5 (max) on DeepSWE 1.1 (opens in a new tab)DeepSWE Pass@1Reported System cardAnthropicSelf-reportedRecord for Claude Opus 5 on DeepSWE 1.1
DeepSWE 1.1 — Mercor mini-swe-agent, 500 stepsEffort: xHighConfiguration: Mercor mini-swe-agent, 500 steps, 2 hours70.2%mercor.com for Claude Opus 5 (xhigh) on DeepSWE 1.1 — Mercor mini-swe-agent, 500 steps (opens in a new tab)Archived copy (opens in a new tab)DeepSWE Pass@1Reported Benchmark leaderboardMercorIndependentRecord for Claude Opus 5 on DeepSWE 1.1 — Mercor mini-swe-agent, 500 steps
DeepSWE 1.1 — Mercor mini-swe-agent, 500 stepsEffort: MaxConfiguration: Mercor mini-swe-agent, 500 steps, 2 hours71.4%mercor.com for Claude Opus 5 (max) on DeepSWE 1.1 — Mercor mini-swe-agent, 500 steps (opens in a new tab)Archived copy (opens in a new tab)DeepSWE Pass@1Reported Benchmark leaderboardMercorIndependentRecord for Claude Opus 5 on DeepSWE 1.1 — Mercor mini-swe-agent, 500 steps
Finance Agent Benchmark 2 — October 2026 evaluation58.6%vals.ai for Claude Opus 5 on Finance Agent Benchmark 2 — October 2026 evaluation (opens in a new tab)Archived copy (opens in a new tab)Finance Agent AccuracyReported Benchmark leaderboardVals AIIndependentRecord for Claude Opus 5 on Finance Agent Benchmark 2 — October 2026 evaluation
FrontierSWE 2 — October 2026 evaluationConfiguration: Proximus harness, 5 trials, 20-hour budget52.0%frontierswe.com for Claude Opus 5 on FrontierSWE 2 — October 2026 evaluation (opens in a new tab)Archived copy (opens in a new tab)FrontierSWE ScoreReported Benchmark leaderboardProximalIndependentRecord for Claude Opus 5 on FrontierSWE 2 — October 2026 evaluation
Global MMLU OriginalEffort: Max92.5%www-cdn.anthropic.com for Claude Opus 5 (max) on Global MMLU Original (opens in a new tab)Average accuracyReported System cardAnthropicSelf-reportedRecord for Claude Opus 5 on Global MMLU Original
GPQA Diamond — Epoch AI harnessEffort: LowConfiguration: Epoch AI harness87.9%epoch.ai for Claude Opus 5 (low) on Graduate-Level Google-Proof Q&A Diamond — Epoch AI harness (opens in a new tab)Archived copy (opens in a new tab)GPQA Diamond AccuracyReported Evaluated Benchmark leaderboardEpoch AIIndependentRecord for Claude Opus 5 on Graduate-Level Google-Proof Q&A Diamond — Epoch AI harness
GPQA Diamond — Epoch AI harnessEffort: MaxConfiguration: Epoch AI harness93.9%epoch.ai for Claude Opus 5 (max) on Graduate-Level Google-Proof Q&A Diamond — Epoch AI harness (opens in a new tab)Archived copy (opens in a new tab)GPQA Diamond AccuracyReported Evaluated Benchmark leaderboardEpoch AIIndependentRecord for Claude Opus 5 on Graduate-Level Google-Proof Q&A Diamond — Epoch AI harness
GPQA Diamond — Epoch AI harnessConfiguration: Epoch AI harness92.9%epoch.ai for Claude Opus 5 on Graduate-Level Google-Proof Q&A Diamond — Epoch AI harness (opens in a new tab)Archived copy (opens in a new tab)GPQA Diamond AccuracyReported Evaluated Benchmark leaderboardEpoch AIIndependentRecord for Claude Opus 5 on Graduate-Level Google-Proof Q&A Diamond — Epoch AI harness
GPQA Diamond — Mercor single-shotEffort: MaxConfiguration: Mercor single-shot agent93.6%mercor.com for Claude Opus 5 (max) on Graduate-Level Google-Proof Q&A Diamond — Mercor single-shot (opens in a new tab)Archived copy (opens in a new tab)GPQA Diamond AccuracyReported Benchmark leaderboardMercorIndependentRecord for Claude Opus 5 on Graduate-Level Google-Proof Q&A Diamond — Mercor single-shot
GPQA Diamond — Vals AI harnessConfiguration: Vals AI harness: mean of zero-shot and few-shot CoT93.4%vals.ai for Claude Opus 5 on Graduate-Level Google-Proof Q&A Diamond — Vals AI harness (opens in a new tab)Archived copy (opens in a new tab)GPQA Diamond AccuracyReported Benchmark leaderboardVals AIIndependentRecord for Claude Opus 5 on Graduate-Level Google-Proof Q&A Diamond — Vals AI harness
HLAB October 2026 evaluation6.7%vals.ai for Claude Opus 5 on Harvey's Legal Agent Benchmark October 2026 evaluation (opens in a new tab)Archived copy (opens in a new tab)HLAB Task Pass RateReported Benchmark leaderboardVals AIIndependentRecord for Claude Opus 5 on Harvey's Legal Agent Benchmark October 2026 evaluation
Humanity's Last Exam Full set — No toolsEffort: LowConfiguration: No tools47.8%www-cdn.anthropic.com for Claude Opus 5 (low) on Humanity's Last Exam Full set — No tools (opens in a new tab)Humanity's Last Exam AccuracyReported System cardAnthropicSelf-reportedRecord for Claude Opus 5 on Humanity's Last Exam Full set — No tools
Humanity's Last Exam Full set — No toolsEffort: MediumConfiguration: No tools54.2%www-cdn.anthropic.com for Claude Opus 5 (medium) on Humanity's Last Exam Full set — No tools (opens in a new tab)Humanity's Last Exam AccuracyReported System cardAnthropicSelf-reportedRecord for Claude Opus 5 on Humanity's Last Exam Full set — No tools
Humanity's Last Exam Full set — No toolsEffort: HighConfiguration: No tools56.0%www-cdn.anthropic.com for Claude Opus 5 (high) on Humanity's Last Exam Full set — No tools (opens in a new tab)Humanity's Last Exam AccuracyReported System cardAnthropicSelf-reportedRecord for Claude Opus 5 on Humanity's Last Exam Full set — No tools
Humanity's Last Exam Full set — No toolsEffort: xHighConfiguration: No tools56.4%www-cdn.anthropic.com for Claude Opus 5 (xhigh) on Humanity's Last Exam Full set — No tools (opens in a new tab)Humanity's Last Exam AccuracyReported System cardAnthropicSelf-reportedRecord for Claude Opus 5 on Humanity's Last Exam Full set — No tools
Humanity's Last Exam Full set — No toolsEffort: MaxConfiguration: No tools56.3%www-cdn.anthropic.com for Claude Opus 5 (max) on Humanity's Last Exam Full set — No tools (opens in a new tab)Humanity's Last Exam AccuracyReported System cardAnthropicSelf-reportedRecord for Claude Opus 5 on Humanity's Last Exam Full set — No tools
Humanity's Last Exam Full set — With toolsEffort: LowConfiguration: With tools56.1%www-cdn.anthropic.com for Claude Opus 5 (low) on Humanity's Last Exam Full set — With tools (opens in a new tab)Humanity's Last Exam AccuracyReported System cardAnthropicSelf-reportedRecord for Claude Opus 5 on Humanity's Last Exam Full set — With tools
Humanity's Last Exam Full set — With toolsEffort: MediumConfiguration: With tools61.3%www-cdn.anthropic.com for Claude Opus 5 (medium) on Humanity's Last Exam Full set — With tools (opens in a new tab)Humanity's Last Exam AccuracyReported System cardAnthropicSelf-reportedRecord for Claude Opus 5 on Humanity's Last Exam Full set — With tools
Humanity's Last Exam Full set — With toolsEffort: HighConfiguration: With tools63.2%www-cdn.anthropic.com for Claude Opus 5 (high) on Humanity's Last Exam Full set — With tools (opens in a new tab)Humanity's Last Exam AccuracyReported System cardAnthropicSelf-reportedRecord for Claude Opus 5 on Humanity's Last Exam Full set — With tools
Humanity's Last Exam Full set — With toolsEffort: xHighConfiguration: With tools64.8%www-cdn.anthropic.com for Claude Opus 5 (xhigh) on Humanity's Last Exam Full set — With tools (opens in a new tab)Humanity's Last Exam AccuracyReported System cardAnthropicSelf-reportedRecord for Claude Opus 5 on Humanity's Last Exam Full set — With tools