APEX-Agents Original Effort: xHigh 36.4% mercor.com for Muse Spark 1.2 (xhigh) on APEX-Agents Original (opens in a new tab) Archived copy (opens in a new tab) Pass rate Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Muse Spark 1.2 on APEX-Agents Original BrowseComp 130-question subset — Mercor web research agent Effort: xHigh Configuration: Mercor web research agent, 100 steps, 3 hours 75.2% mercor.com for Muse Spark 1.2 (xhigh) on BrowseComp 130-question subset — Mercor web research agent (opens in a new tab) Archived copy (opens in a new tab) BrowseComp Accuracy Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Muse Spark 1.2 on BrowseComp 130-question subset — Mercor web research agent Chartography October 2026 leaderboard Effort: xHigh 32.1% surgehq.ai for Muse Spark 1.2 (xHigh) on Chartography October 2026 leaderboard (opens in a new tab) Archived copy (opens in a new tab) Chartography Pass@1 Reported October 7, 2026 Benchmark leaderboard Surge AI Independent Record for Muse Spark 1.2 on Chartography October 2026 leaderboard CharXiv Descriptive and reasoning — Mercor single-shot Effort: xHigh Configuration: Mercor single-shot agent 95.3% mercor.com for Muse Spark 1.2 (xhigh) on CharXiv Descriptive and reasoning — Mercor single-shot (opens in a new tab) Archived copy (opens in a new tab) CharXiv Accuracy Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Muse Spark 1.2 on CharXiv Descriptive and reasoning — Mercor single-shot DeepSearchQA 900-prompt set Effort: xHigh 85.9% dev.meta.ai for Muse Spark 1.2 (xhigh) on DeepSearchQA 900-prompt set (opens in a new tab) F1 score Reported September 2, 2026 Model page Meta Self-reported Record for Muse Spark 1.2 on DeepSearchQA 900-prompt set DeepSWE 1.1 — mini-swe-agent Effort: xHigh Configuration: mini-swe-agent harness 55.0% research.meta.ai for Muse Spark 1.2 (xhigh) on DeepSWE 1.1 — mini-swe-agent (opens in a new tab) DeepSWE Pass@1 Reported September 2, 2026 Launch post Meta Self-reported DataCurve Record for Muse Spark 1.2 on DeepSWE 1.1 — mini-swe-agent DeepSWE 1.1 — Muse Code Effort: xHigh Configuration: Muse Code harness 59.3% research.meta.ai for Muse Spark 1.2 (xhigh) on DeepSWE 1.1 — Muse Code (opens in a new tab) DeepSWE Pass@1 Reported September 2, 2026 Launch post Meta Self-reported Record for Muse Spark 1.2 on DeepSWE 1.1 — Muse Code Finance Agent Benchmark 2 — October 2026 evaluation Effort: xHigh 60.6% vals.ai for Muse Spark 1.2 (xhigh) on Finance Agent Benchmark 2 — October 2026 evaluation (opens in a new tab) Archived copy (opens in a new tab) Finance Agent Accuracy Reported October 6, 2026 Benchmark leaderboard Vals AI Independent Record for Muse Spark 1.2 on Finance Agent Benchmark 2 — October 2026 evaluation FrontierSWE 2 — October 2026 evaluation Configuration: Proximus harness, 5 trials, 20-hour budget 12.0% frontierswe.com for Muse Spark 1.2 on FrontierSWE 2 — October 2026 evaluation (opens in a new tab) Archived copy (opens in a new tab) FrontierSWE Score Reported October 7, 2026 Benchmark leaderboard Proximal Independent Record for Muse Spark 1.2 on FrontierSWE 2 — October 2026 evaluation HLAB October 2026 evaluation Effort: xHigh 25.4% vals.ai for Muse Spark 1.2 (xhigh) on Harvey's Legal Agent Benchmark October 2026 evaluation (opens in a new tab) Archived copy (opens in a new tab) HLAB Task Pass Rate Reported October 6, 2026 Benchmark leaderboard Vals AI Independent Record for Muse Spark 1.2 on Harvey's Legal Agent Benchmark October 2026 evaluation JobBench Main 65 tasks Effort: xHigh 61.6% dev.meta.ai for Muse Spark 1.2 (xhigh) on JobBench Main 65 tasks (opens in a new tab) Mean rubric score Reported September 2, 2026 Model page Meta Self-reported Record for Muse Spark 1.2 on JobBench Main 65 tasks MedXpertQA MM — Mercor single-shot Effort: xHigh Configuration: Mercor single-shot agent 75.7% mercor.com for Muse Spark 1.2 (xhigh) on MedXpertQA MM — Mercor single-shot (opens in a new tab) Archived copy (opens in a new tab) Accuracy Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Muse Spark 1.2 on MedXpertQA MM — Mercor single-shot MMLU-Pro Original — Vals AI harness Effort: xHigh Configuration: Vals AI harness 88.3% vals.ai for Muse Spark 1.2 (xhigh) on MMLU-Pro Original — Vals AI harness (opens in a new tab) Archived copy (opens in a new tab) Accuracy Reported September 1, 2026 Benchmark leaderboard Vals AI Independent Record for Muse Spark 1.2 on MMLU-Pro Original — Vals AI harness MMMU-Pro 1,730 questions — Mercor single-shot Effort: xHigh Configuration: Mercor single-shot agent 80.7% mercor.com for Muse Spark 1.2 (xhigh) on MMMU-Pro 1,730 questions — Mercor single-shot (opens in a new tab) Archived copy (opens in a new tab) MMMU-Pro accuracy Setting: Not stated Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Muse Spark 1.2 on MMMU-Pro 1,730 questions — Mercor single-shot MMMU-Pro Vals AI harness Effort: xHigh Configuration: Vals AI harness 86.1% vals.ai for Muse Spark 1.2 (xhigh) on MMMU-Pro Vals AI harness (opens in a new tab) Archived copy (opens in a new tab) MMMU-Pro accuracy Setting: Standard (4 options) Reported September 1, 2026 Benchmark leaderboard Vals AI Independent Record for Muse Spark 1.2 on MMMU-Pro Vals AI harness MRCR v2 8-needle 256K–512K (o200k_base) Effort: xHigh 66.3% dev.meta.ai for Muse Spark 1.2 (xhigh) on MRCR v2 8-needle 256K–512K (o200k_base) (opens in a new tab) Mean sequence-matcher ratio Reported September 2, 2026 Model page Meta Self-reported Record for Muse Spark 1.2 on MRCR v2 8-needle 256K–512K (o200k_base) MRCR v2 8-needle 512K–1M (o200k_base) Effort: xHigh 55.5% dev.meta.ai for Muse Spark 1.2 (xhigh) on MRCR v2 8-needle 512K–1M (o200k_base) (opens in a new tab) Mean sequence-matcher ratio Reported September 2, 2026 Model page Meta Self-reported Record for Muse Spark 1.2 on MRCR v2 8-needle 512K–1M (o200k_base) OSWorld 2.0 v2026.06.24 — Binary Effort: xHigh 17.9% dev.meta.ai for Muse Spark 1.2 (xhigh) on OSWorld 2.0 v2026.06.24 — Binary (opens in a new tab) OSWorld Strict Score Reported September 2, 2026 Model page Meta Self-reported Record for Muse Spark 1.2 on OSWorld 2.0 v2026.06.24 — Binary OSWorld 2.0 v2026.06.24 — Partial Effort: xHigh 47.6% dev.meta.ai for Muse Spark 1.2 (xhigh) on OSWorld 2.0 v2026.06.24 — Partial (opens in a new tab) OSWorld Partial Score Reported September 2, 2026 Model page Meta Self-reported Record for Muse Spark 1.2 on OSWorld 2.0 v2026.06.24 — Partial Riemann-bench October 2026 leaderboard Effort: xHigh 23.2% surgehq.ai for Muse Spark 1.2 (xHigh) on Riemann-bench October 2026 leaderboard (opens in a new tab) Archived copy (opens in a new tab) Riemann-bench Pass@1 Reported October 7, 2026 Benchmark leaderboard Surge AI Independent Record for Muse Spark 1.2 on Riemann-bench October 2026 leaderboard SimpleQA Verified Original — Epoch AI harness Effort: xHigh Configuration: Epoch AI harness 60.3% epoch.ai for Muse Spark 1.2 (xhigh) on SimpleQA Verified Original — Epoch AI harness (opens in a new tab) Archived copy (opens in a new tab) Accuracy Reported October 7, 2026 Evaluated August 27, 2026 at 7:36 PM UTC Benchmark leaderboard Epoch AI Independent Record for Muse Spark 1.2 on SimpleQA Verified Original — Epoch AI harness SWE Atlas Codebase QnA — Public; mini-swe-agent Effort: xHigh Configuration: mini-swe-agent harness 46.2% dev.meta.ai for Muse Spark 1.2 (xhigh) on SWE Atlas Codebase QnA — Public; mini-swe-agent (opens in a new tab) Mean pass@1 Reported September 2, 2026 Model page Meta Self-reported Record for Muse Spark 1.2 on SWE Atlas Codebase QnA — Public; mini-swe-agent SWE-bench Verified — Vals AI mini-swe-agent Effort: xHigh Configuration: mini-swe-agent harness 86.6% vals.ai for Muse Spark 1.2 (xhigh) on SWE-bench Verified — Vals AI mini-swe-agent (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported September 1, 2026 Benchmark leaderboard Vals AI Independent Record for Muse Spark 1.2 on SWE-bench Verified — Vals AI mini-swe-agent Terminal-Bench 2.1 — Muse Code Effort: xHigh Configuration: Muse Code harness 82.9% research.meta.ai for Muse Spark 1.2 (xhigh) on Terminal-Bench 2.1 — Muse Code (opens in a new tab) Terminal-Bench Accuracy Reported September 2, 2026 Launch post Meta Self-reported Record for Muse Spark 1.2 on Terminal-Bench 2.1 — Muse Code Terminal-Bench 2.1 — Vals AI Terminus 2 Effort: xHigh Configuration: Terminus-2 harness 69.7% vals.ai for Muse Spark 1.2 (xhigh) on Terminal-Bench 2.1 — Vals AI Terminus 2 (opens in a new tab) Archived copy (opens in a new tab) Terminal-Bench Accuracy Reported September 28, 2026 Benchmark leaderboard Vals AI Independent Record for Muse Spark 1.2 on Terminal-Bench 2.1 — Vals AI Terminus 2 Terminal-Bench 4.0 — Vals AI mini-swe-agent Effort: xHigh Configuration: mini-swe-agent harness 6.1% vals.ai for Muse Spark 1.2 (xhigh) on Terminal-Bench 4.0 — Vals AI mini-swe-agent (opens in a new tab) Archived copy (opens in a new tab) Terminal-Bench Accuracy Reported October 6, 2026 Benchmark leaderboard Vals AI Independent Record for Muse Spark 1.2 on Terminal-Bench 4.0 — Vals AI mini-swe-agent Toolathlon Verified Effort: xHigh 75.9% toolathlon.xyz for Muse Spark 1.2 (xhigh) on Toolathlon Verified (opens in a new tab) Archived copy (opens in a new tab) Tasks completed Reported August 5, 2026 Benchmark leaderboard Toolathlon Independent Toolathlon Authors Record for Muse Spark 1.2 on Toolathlon Verified Vals Index 2.1 Effort: xHigh 49.3% vals.ai for Muse Spark 1.2 (xhigh) on Vals Index 2.1 (opens in a new tab) Archived copy (opens in a new tab) Vals Index GDP-weighted Accuracy Reported October 6, 2026 Benchmark leaderboard Vals AI Independent Record for Muse Spark 1.2 on Vals Index 2.1 Vibe Code Bench 1.1 — OpenHands, October 2026 evaluation Effort: xHigh Configuration: OpenHands harness 79.1% vals.ai for Muse Spark 1.2 (xhigh) 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 Score Reported October 6, 2026 Benchmark leaderboard Vals AI Independent Record for Muse Spark 1.2 on Vibe Code Bench 1.1 — OpenHands, October 2026 evaluation