APEX-Agents Original 21.3% mercor.com for DeepSeek-V3.2 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 DeepSeek-V3.2 on APEX-Agents Original BrowseComp 130-question subset — Mercor web research agent Configuration: Mercor web research agent, 100 steps, 3 hours 38.1% mercor.com for DeepSeek-V3.2 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 DeepSeek-V3.2 on BrowseComp 130-question subset — Mercor web research agent DeepSWE 1.1 — Mercor mini-swe-agent, 500 steps Configuration: Mercor mini-swe-agent, 500 steps, 2 hours 0.6% mercor.com for DeepSeek-V3.2 on DeepSWE 1.1 — Mercor mini-swe-agent, 500 steps (opens in a new tab) Archived copy (opens in a new tab) DeepSWE Pass@1 Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for DeepSeek-V3.2 on DeepSWE 1.1 — Mercor mini-swe-agent, 500 steps GPQA Diamond — Mercor single-shot Configuration: Mercor single-shot agent 85.2% mercor.com for DeepSeek-V3.2 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 Accuracy Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for DeepSeek-V3.2 on Graduate-Level Google-Proof Q&A Diamond — Mercor single-shot GPQA Diamond — Vals AI harness Effort: None Configuration: Vals AI harness: mean of zero-shot and few-shot CoT 76.3% vals.ai for DeepSeek-V3.2 (none) 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 Accuracy Reported September 1, 2026 Benchmark leaderboard Vals AI Independent Record for DeepSeek-V3.2 on Graduate-Level Google-Proof Q&A Diamond — Vals AI harness GPQA Diamond — Vals AI harness Effort: High Configuration: Vals AI harness: mean of zero-shot and few-shot CoT 80.3% vals.ai for DeepSeek-V3.2 (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 Accuracy Reported September 1, 2026 Benchmark leaderboard Vals AI Independent Record for DeepSeek-V3.2 on Graduate-Level Google-Proof Q&A Diamond — Vals AI harness Humanity's Last Exam Text only — Mercor single-shot Configuration: Mercor single-shot agent 22.3% mercor.com for DeepSeek-V3.2 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 Accuracy Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for DeepSeek-V3.2 on Humanity's Last Exam Text only — Mercor single-shot MMLU-Pro Original — Mercor single-shot Configuration: Mercor single-shot agent 76.5% mercor.com for DeepSeek-V3.2 on MMLU-Pro Original — 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 DeepSeek-V3.2 on MMLU-Pro Original — Mercor single-shot MMLU-Pro Original — Vals AI harness Configuration: Vals AI harness 83.1% vals.ai for DeepSeek-V3.2 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 DeepSeek-V3.2 on MMLU-Pro Original — Vals AI harness MMLU-Pro Original — Vals AI harness Reported as: thinking Configuration: Vals AI harness 84.9% vals.ai for DeepSeek-V3.2 (thinking) 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 DeepSeek-V3.2 on MMLU-Pro Original — Vals AI harness Riemann-bench October 2026 leaderboard Effort: High 8.0% surgehq.ai for DeepSeek-V3.2 (High) 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 DeepSeek-V3.2 on Riemann-bench October 2026 leaderboard SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps Configuration: Mercor mini-swe-agent, 250 steps, 1 hour 5.9% mercor.com for DeepSeek-V3.2 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@1 Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for DeepSeek-V3.2 on SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps SWE-bench Multilingual — Mercor mini-swe-agent, 1000 steps Configuration: Mercor mini-swe-agent, 1000 steps, 3 hours 60.7% mercor.com for DeepSeek-V3.2 on SWE-bench Multilingual — Mercor mini-swe-agent, 1000 steps (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for DeepSeek-V3.2 on SWE-bench Multilingual — Mercor mini-swe-agent, 1000 steps SWE-bench Multilingual — mini-swe-agent Configuration: mini-swe-agent harness 59.0% github.com for DeepSeek-V3.2 on SWE-bench Multilingual — mini-swe-agent (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported February 13, 2026 Benchmark repository SWE-bench Independent SWE-bench Team Record for DeepSeek-V3.2 on SWE-bench Multilingual — mini-swe-agent SWE-bench Verified — Mercor mini-swe-agent, 1000 steps Configuration: Mercor mini-swe-agent, 1000 steps, 3 hours 66.0% mercor.com for DeepSeek-V3.2 on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for DeepSeek-V3.2 on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps SWE-bench Verified — mini-swe-agent Effort: High Configuration: mini-swe-agent harness 70.0% github.com for DeepSeek-V3.2 (high) on SWE-bench Verified — mini-swe-agent (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported February 17, 2026 Benchmark repository SWE-bench Independent SWE-bench Team Record for DeepSeek-V3.2 on SWE-bench Verified — mini-swe-agent SWE-bench Verified — Vals AI mini-swe-agent Effort: High Configuration: mini-swe-agent harness 67.6% vals.ai for DeepSeek-V3.2 (high) 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 DeepSeek-V3.2 on SWE-bench Verified — Vals AI mini-swe-agent SWE-bench Pro Public — Scale AI SWE-Agent Configuration: SWE-Agent harness, 250 turns, uncapped cost 15.6% labs.scale.com for DeepSeek-V3.2 on SWE-bench Pro Public — Scale AI SWE-Agent (opens in a new tab) Archived copy (opens in a new tab) Public tasks resolved Reported October 7, 2026 Benchmark leaderboard Scale AI Independent Record for DeepSeek-V3.2 on SWE-bench Pro Public — Scale AI SWE-Agent Terminal-Bench 2.0 — Vals AI Terminus 2 Effort: None Configuration: Terminus-2 harness 34.8% vals.ai for DeepSeek-V3.2 (none) on Terminal-Bench 2.0 — Vals AI Terminus 2 (opens in a new tab) Archived copy (opens in a new tab) Terminal-Bench Accuracy Reported June 4, 2026 Benchmark leaderboard Vals AI Independent Record for DeepSeek-V3.2 on Terminal-Bench 2.0 — Vals AI Terminus 2 Terminal-Bench 2.0 — Vals AI Terminus 2 Effort: High Configuration: Terminus-2 harness 36.0% vals.ai for DeepSeek-V3.2 (high) on Terminal-Bench 2.0 — Vals AI Terminus 2 (opens in a new tab) Archived copy (opens in a new tab) Terminal-Bench Accuracy Reported June 4, 2026 Benchmark leaderboard Vals AI Independent Record for DeepSeek-V3.2 on Terminal-Bench 2.0 — Vals AI Terminus 2 Terminal-Bench 2.1 — Mercor Terminus 2 Configuration: Mercor Terminus 2, 1000 steps, 3 hours 44.6% mercor.com for DeepSeek-V3.2 on Terminal-Bench 2.1 — Mercor Terminus 2 (opens in a new tab) Archived copy (opens in a new tab) Terminal-Bench Accuracy Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for DeepSeek-V3.2 on Terminal-Bench 2.1 — Mercor Terminus 2 Vibe Code Bench 1.1 — OpenHands, October 2026 evaluation Effort: High Configuration: OpenHands harness 5.1% vals.ai for DeepSeek-V3.2 (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 Score Reported October 6, 2026 Benchmark leaderboard Vals AI Independent Record for DeepSeek-V3.2 on Vibe Code Bench 1.1 — OpenHands, October 2026 evaluation