Benchmarks

39 results across 22 benchmarks

Benchmark results for Grok 4.6
BenchmarkScoreSource
APEX-Agents OriginalEffort: xHigh65.3%mercor.com for Grok 4.6 (xhigh) on APEX-Agents Original (opens in a new tab)Archived copy (opens in a new tab)Pass rateReported Benchmark leaderboardMercorIndependentRecord for Grok 4.6 on APEX-Agents Original
BrowseComp 130-question subset — Mercor web research agentEffort: xHighConfiguration: Mercor web research agent, 100 steps, 3 hours84.0%mercor.com for Grok 4.6 (xhigh) 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 Grok 4.6 on BrowseComp 130-question subset — Mercor web research agent
Chartography October 2026 leaderboardEffort: xHigh20.5%surgehq.ai for Grok 4.6 (xHigh) on Chartography October 2026 leaderboard (opens in a new tab)Archived copy (opens in a new tab)Chartography Pass@1Reported Benchmark leaderboardSurge AIIndependentRecord for Grok 4.6 on Chartography October 2026 leaderboard
CharXiv Descriptive and reasoning — Mercor single-shotEffort: xHighConfiguration: Mercor single-shot agent92.9%mercor.com for Grok 4.6 (xhigh) 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 Grok 4.6 on CharXiv Descriptive and reasoning — Mercor single-shot
CursorBench 3.2.0Effort: High69.9%x.ai for Grok 4.6 (high) on CursorBench 3.2.0 (opens in a new tab)CursorBench AccuracyReported Launch postSpaceXAISelf-reportedRecord for Grok 4.6 on CursorBench 3.2.0
CursorBench 4.0Effort: Low33.4%cursor.com for Grok 4.6 (low) on CursorBench 4.0 (opens in a new tab)Archived copy (opens in a new tab)CursorBench AccuracyReported Benchmark leaderboardCursorIndependentRecord for Grok 4.6 on CursorBench 4.0
CursorBench 4.0Effort: Medium36.1%cursor.com for Grok 4.6 (medium) on CursorBench 4.0 (opens in a new tab)Archived copy (opens in a new tab)CursorBench AccuracyReported Benchmark leaderboardCursorIndependentRecord for Grok 4.6 on CursorBench 4.0
CursorBench 4.0Effort: High40.4%cursor.com for Grok 4.6 (high) on CursorBench 4.0 (opens in a new tab)CursorBench AccuracyReported Benchmark leaderboardCursorIndependentRecord for Grok 4.6 on CursorBench 4.0
CursorBench 4.0Effort: xHigh41.4%cursor.com for Grok 4.6 (xhigh) on CursorBench 4.0 (opens in a new tab)Archived copy (opens in a new tab)CursorBench AccuracyReported Benchmark leaderboardCursorIndependentRecord for Grok 4.6 on CursorBench 4.0
CWE-bench 1 — OpenCodeEffort: HighConfiguration: OpenCode harness57.0%cwe-bench.com for Grok 4.6 (high) on CWE-bench 1 — OpenCode (opens in a new tab)Archived copy (opens in a new tab)CWE-bench Programmatic Pass@1Reported Benchmark leaderboardCollinear AIIndependentRecord for Grok 4.6 on CWE-bench 1 — OpenCode
CyberGym OriginalEffort: High79.7%media.x.ai for Grok 4.6 (high) on CyberGym Original (opens in a new tab)Vulnerability reproduction successReported Model cardSpaceXAISelf-reportedRecord for Grok 4.6 on CyberGym Original
DeepSWE 1.1Effort: Medium67.0%deepswe.datacurve.ai for Grok 4.6 (medium) on DeepSWE 1.1 (opens in a new tab)DeepSWE Pass@1Reported Benchmark leaderboardDatacurveIndependentRecord for Grok 4.6 on DeepSWE 1.1
DeepSWE 1.1Effort: High65.9%x.ai for Grok 4.6 (high) on DeepSWE 1.1 (opens in a new tab)DeepSWE Pass@1Reported Launch postSpaceXAISelf-reportedRecord for Grok 4.6 on DeepSWE 1.1
DeepSWE 1.1 — Mercor mini-swe-agent, 500 stepsEffort: HighConfiguration: Mercor mini-swe-agent, 500 steps, 2 hours63.7%mercor.com for Grok 4.6 (high) 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 Grok 4.6 on DeepSWE 1.1 — Mercor mini-swe-agent, 500 steps
DeepSWE 1.1 — Mercor mini-swe-agent, 500 stepsEffort: xHighConfiguration: Mercor mini-swe-agent, 500 steps, 2 hours24.8%mercor.com for Grok 4.6 (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 Grok 4.6 on DeepSWE 1.1 — Mercor mini-swe-agent, 500 steps
Finance Agent Benchmark 2 — October 2026 evaluationEffort: High53.7%vals.ai for Grok 4.6 (high) 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 Grok 4.6 on Finance Agent Benchmark 2 — October 2026 evaluation
FrontierSWE 2 — October 2026 evaluationConfiguration: Proximus harness, 5 trials, 20-hour budget25.3%frontierswe.com for Grok 4.6 on FrontierSWE 2 — October 2026 evaluation (opens in a new tab)Archived copy (opens in a new tab)FrontierSWE ScoreReported Benchmark leaderboardProximalIndependentRecord for Grok 4.6 on FrontierSWE 2 — October 2026 evaluation
GPQA Diamond — Epoch AI harnessEffort: HighConfiguration: Epoch AI harness94.0%epoch.ai for Grok 4.6 (high) 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 Grok 4.6 on Graduate-Level Google-Proof Q&A Diamond — Epoch AI harness
GPQA Diamond — Epoch AI harnessEffort: xHighConfiguration: Epoch AI harness93.2%epoch.ai for Grok 4.6 (xhigh) 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 Grok 4.6 on Graduate-Level Google-Proof Q&A Diamond — Epoch AI harness
GPQA Diamond — Mercor single-shotEffort: xHighConfiguration: Mercor single-shot agent93.8%mercor.com for Grok 4.6 (xhigh) 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 Grok 4.6 on Graduate-Level Google-Proof Q&A Diamond — Mercor single-shot
GPQA Diamond — Vals AI harnessEffort: HighConfiguration: Vals AI harness: mean of zero-shot and few-shot CoT94.7%vals.ai for Grok 4.6 (high) 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 Grok 4.6 on Graduate-Level Google-Proof Q&A Diamond — Vals AI harness
HLAB October 2026 evaluationEffort: High15.8%vals.ai for Grok 4.6 (high) 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 Grok 4.6 on Harvey's Legal Agent Benchmark October 2026 evaluation
Humanity's Last Exam Text only — Mercor single-shotEffort: xHighConfiguration: Mercor single-shot agent41.3%mercor.com for Grok 4.6 (xhigh) on Humanity's Last Exam Text only — Mercor single-shot (opens in a new tab)Archived copy (opens in a new tab)Humanity's Last Exam AccuracyReported Benchmark leaderboardMercorIndependentRecord for Grok 4.6 on Humanity's Last Exam Text only — Mercor single-shot
MedXpertQA MM — Mercor single-shotEffort: xHighConfiguration: Mercor single-shot agent75.2%mercor.com for Grok 4.6 (xhigh) on MedXpertQA MM — Mercor single-shot (opens in a new tab)Archived copy (opens in a new tab)AccuracyReported Benchmark leaderboardMercorIndependentRecord for Grok 4.6 on MedXpertQA MM — Mercor single-shot
MMLU-Pro Original — Mercor single-shotEffort: xHighConfiguration: Mercor single-shot agent89.4%mercor.com for Grok 4.6 (xhigh) on MMLU-Pro Original — Mercor single-shot (opens in a new tab)Archived copy (opens in a new tab)AccuracyReported Benchmark leaderboardMercorIndependentRecord for Grok 4.6 on MMLU-Pro Original — Mercor single-shot
MMLU-Pro Original — Vals AI harnessEffort: HighConfiguration: Vals AI harness89.4%vals.ai for Grok 4.6 (high) on MMLU-Pro Original — Vals AI harness (opens in a new tab)Archived copy (opens in a new tab)AccuracyReported Benchmark leaderboardVals AIIndependentRecord for Grok 4.6 on MMLU-Pro Original — Vals AI harness
MMMU-Pro 1,730 questions — Mercor single-shotEffort: xHighConfiguration: Mercor single-shot agent80.5%mercor.com for Grok 4.6 (xhigh) on MMMU-Pro 1,730 questions — Mercor single-shot (opens in a new tab)Archived copy (opens in a new tab)MMMU-Pro accuracySetting: Not statedReported Benchmark leaderboardMercorIndependentRecord for Grok 4.6 on MMMU-Pro 1,730 questions — Mercor single-shot
SimpleQA Verified Original — Epoch AI harnessEffort: HighConfiguration: Epoch AI harness49.3%epoch.ai for Grok 4.6 (high) on SimpleQA Verified Original — Epoch AI harness (opens in a new tab)Archived copy (opens in a new tab)AccuracyReported Evaluated Benchmark leaderboardEpoch AIIndependentRecord for Grok 4.6 on SimpleQA Verified Original — Epoch AI harness
SimpleQA Verified Original — Epoch AI harnessEffort: xHighConfiguration: Epoch AI harness48.9%epoch.ai for Grok 4.6 (xhigh) on SimpleQA Verified Original — Epoch AI harness (opens in a new tab)Archived copy (opens in a new tab)AccuracyReported Evaluated Benchmark leaderboardEpoch AIIndependentRecord for Grok 4.6 on SimpleQA Verified Original — Epoch AI harness
SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 stepsEffort: xHighConfiguration: Mercor mini-swe-agent, 250 steps, 1 hour50.3%mercor.com for Grok 4.6 (xhigh) on SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps (opens in a new tab)Archived copy (opens in a new tab)Mean pass@1Reported Benchmark leaderboardMercorIndependentRecord for Grok 4.6 on SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps
SWE-bench Multilingual — Mercor mini-swe-agent, 1000 stepsEffort: xHighConfiguration: Mercor mini-swe-agent, 1000 steps, 3 hours92.7%mercor.com for Grok 4.6 (xhigh) on SWE-bench Multilingual — Mercor mini-swe-agent, 1000 steps (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Benchmark leaderboardMercorIndependentRecord for Grok 4.6 on SWE-bench Multilingual — Mercor mini-swe-agent, 1000 steps
SWE-bench Verified — Mercor mini-swe-agent, 1000 stepsEffort: xHighConfiguration: Mercor mini-swe-agent, 1000 steps, 3 hours84.6%mercor.com for Grok 4.6 (xhigh) on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Benchmark leaderboardMercorIndependentRecord for Grok 4.6 on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps
SWE-bench Verified — Vals AI mini-swe-agentEffort: HighConfiguration: mini-swe-agent harness95.6%vals.ai for Grok 4.6 (high) on SWE-bench Verified — Vals AI mini-swe-agent (opens in a new tab)Archived copy (opens in a new tab)Resolved TasksReported Benchmark leaderboardVals AIIndependentRecord for Grok 4.6 on SWE-bench Verified — Vals AI mini-swe-agent
Terminal-Bench 2.1 — Vals AI Terminus 2Effort: HighConfiguration: Terminus-2 harness78.3%vals.ai for Grok 4.6 (high) on Terminal-Bench 2.1 — Vals AI Terminus 2 (opens in a new tab)Archived copy (opens in a new tab)Terminal-Bench AccuracyReported Benchmark leaderboardVals AIIndependentRecord for Grok 4.6 on Terminal-Bench 2.1 — Vals AI Terminus 2
Terminal-Bench 4.0 — Grok BuildEffort: HighConfiguration: Grok Build harness20.3%tbench.ai for Grok 4.6 (high) on Terminal-Bench 4.0 — Grok Build (opens in a new tab)Archived copy (opens in a new tab)Terminal-Bench AccuracyReported Benchmark leaderboardTerminal-BenchIndependentTerminal-Bench TeamRecord for Grok 4.6 on Terminal-Bench 4.0 — Grok Build
Terminal-Bench 4.0 — Mercor mini-swe-agentEffort: xHighConfiguration: Mercor mini-swe-agent, 1000 steps, 8 hours25.3%mercor.com for Grok 4.6 (xhigh) on Terminal-Bench 4.0 — Mercor mini-swe-agent (opens in a new tab)Archived copy (opens in a new tab)Terminal-Bench AccuracyReported Benchmark leaderboardMercorIndependentRecord for Grok 4.6 on Terminal-Bench 4.0 — Mercor mini-swe-agent
Terminal-Bench 4.0 — Vals AI mini-swe-agentEffort: HighConfiguration: mini-swe-agent harness17.2%vals.ai for Grok 4.6 (high) on Terminal-Bench 4.0 — Vals AI mini-swe-agent (opens in a new tab)Archived copy (opens in a new tab)Terminal-Bench AccuracyReported Benchmark leaderboardVals AIIndependentRecord for Grok 4.6 on Terminal-Bench 4.0 — Vals AI mini-swe-agent
Vals Index 2.1Effort: High52.1%vals.ai for Grok 4.6 (high) on Vals Index 2.1 (opens in a new tab)Archived copy (opens in a new tab)Vals Index GDP-weighted AccuracyReported Benchmark leaderboardVals AIIndependentRecord for Grok 4.6 on Vals Index 2.1
Vibe Code Bench 1.1 — OpenHands, October 2026 evaluationEffort: HighConfiguration: OpenHands harness76.2%vals.ai for Grok 4.6 (high) on Vibe Code Bench 1.1 — OpenHands, October 2026 evaluation (opens in a new tab)Archived copy (opens in a new tab)Vibe Code Bench ScoreReported Benchmark leaderboardVals AIIndependentRecord for Grok 4.6 on Vibe Code Bench 1.1 — OpenHands, October 2026 evaluation