BrowseComp Reported as: thinking 60.6% huggingface.co for Kimi K2.5 (thinking) on BrowseComp BrowseComp (opens in a new tab) BrowseComp Accuracy Reported January 27, 2026 Model card Moonshot AI Self-reported Record for Kimi K2.5 on BrowseComp BrowseComp Chartography October 2026 leaderboard Reported as: Thinking on 12.6% surgehq.ai for Kimi K2.5 (Thinking on) 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 Kimi K2.5 on Chartography October 2026 leaderboard CharXiv Reasoning — No tools Reported as: thinking Configuration: No tools 77.5% huggingface.co for Kimi K2.5 (thinking) on CharXiv Reasoning — No tools (opens in a new tab) CharXiv Accuracy Reported January 27, 2026 Model card Moonshot AI Self-reported Record for Kimi K2.5 on CharXiv Reasoning — No tools Finance Agent Benchmark 2 — October 2026 evaluation Reported as: thinking 35.8% vals.ai for Kimi K2.5 (thinking) 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 Kimi K2.5 on Finance Agent Benchmark 2 — October 2026 evaluation GPQA Diamond Reported as: thinking 87.6% huggingface.co for Kimi K2.5 (thinking) on Graduate-Level Google-Proof Q&A Diamond (opens in a new tab) GPQA Diamond Accuracy Reported January 27, 2026 Model card Moonshot AI Self-reported Record for Kimi K2.5 on Graduate-Level Google-Proof Q&A Diamond GPQA Diamond — Epoch AI harness Configuration: Epoch AI harness 87.6% epoch.ai for Kimi K2.5 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 Accuracy Reported October 7, 2026 Evaluated February 2, 2026 at 11:01 AM UTC Benchmark leaderboard Epoch AI Independent Record for Kimi K2.5 on Graduate-Level Google-Proof Q&A Diamond — Epoch AI harness GPQA Diamond — Vals AI harness Reported as: thinking Configuration: Vals AI harness: mean of zero-shot and few-shot CoT 84.1% vals.ai for Kimi K2.5 (thinking) 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 Kimi K2.5 on Graduate-Level Google-Proof Q&A Diamond — Vals AI harness HLAB October 2026 evaluation Reported as: thinking 0.0% vals.ai for Kimi K2.5 (thinking) 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 Kimi K2.5 on Harvey's Legal Agent Benchmark October 2026 evaluation Humanity's Last Exam Full set — No tools Reported as: thinking Configuration: No tools 30.1% huggingface.co for Kimi K2.5 (thinking) on Humanity's Last Exam Full set — No tools (opens in a new tab) Humanity's Last Exam Accuracy Reported January 27, 2026 Model card Moonshot AI Self-reported Record for Kimi K2.5 on Humanity's Last Exam Full set — No tools Humanity's Last Exam Full set — Scale AI evaluation 24.4% labs.scale.com for Kimi K2.5 on Humanity's Last Exam Full set — Scale AI evaluation (opens in a new tab) Archived copy (opens in a new tab) Humanity's Last Exam Accuracy Reported October 3, 2026 Benchmark leaderboard Scale AI Independent Record for Kimi K2.5 on Humanity's Last Exam Full set — Scale AI evaluation Humanity's Last Exam Full set — With tools Reported as: thinking Configuration: With tools 50.2% huggingface.co for Kimi K2.5 (thinking) on Humanity's Last Exam Full set — With tools (opens in a new tab) Humanity's Last Exam Accuracy Reported January 27, 2026 Model card Moonshot AI Self-reported Record for Kimi K2.5 on Humanity's Last Exam Full set — With tools MCP Atlas Public, April 2026 update 64.4% labs.scale.com for Kimi K2.5 on MCP Atlas Public, April 2026 update (opens in a new tab) Pass rate Reported September 24, 2026 Benchmark leaderboard Scale AI Independent Record for Kimi K2.5 on MCP Atlas Public, April 2026 update MMLU-Pro Original Reported as: thinking 87.1% huggingface.co for Kimi K2.5 (thinking) on MMLU-Pro Original (opens in a new tab) Accuracy Reported January 27, 2026 Model card Moonshot AI Self-reported Record for Kimi K2.5 on MMLU-Pro Original MMLU-Pro Original — Vals AI harness Reported as: thinking Configuration: Vals AI harness 85.9% vals.ai for Kimi K2.5 (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 Kimi K2.5 on MMLU-Pro Original — Vals AI harness MMMU-Pro No tools Reported as: thinking Configuration: No tools 78.5% huggingface.co for Kimi K2.5 (thinking) on MMMU-Pro No tools (opens in a new tab) MMMU-Pro accuracy Setting: Not stated Reported January 27, 2026 Model card Moonshot AI Self-reported Record for Kimi K2.5 on MMMU-Pro No tools MMMU-Pro Vals AI harness Reported as: thinking Configuration: Vals AI harness 84.3% vals.ai for Kimi K2.5 (thinking) 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 Kimi K2.5 on MMMU-Pro Vals AI harness OSWorld Verified — 100 steps Configuration: 100-step limit 63.3% os-world.github.io for Kimi K2.5 on OSWorld Verified — 100 steps (opens in a new tab) Archived copy (opens in a new tab) OSWorld-Verified success rate Reported January 31, 2026 Benchmark leaderboard OSWorld Independent XLang Lab Record for Kimi K2.5 on OSWorld Verified — 100 steps Riemann-bench October 2026 leaderboard Reported as: Thinking on 12.0% surgehq.ai for Kimi K2.5 (Thinking on) 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 Kimi K2.5 on Riemann-bench October 2026 leaderboard SimpleQA Verified Original — Epoch AI harness Configuration: Epoch AI harness 34.3% epoch.ai for Kimi K2.5 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 7:35 PM UTC Benchmark leaderboard Epoch AI Independent Record for Kimi K2.5 on SimpleQA Verified Original — Epoch AI harness SWE Atlas Codebase QnA — Public; mini-swe-agent Configuration: mini-swe-agent harness 13.1% labs.scale.com for Kimi K2.5 on SWE Atlas Codebase QnA — Public; mini-swe-agent (opens in a new tab) Archived copy (opens in a new tab) Mean pass@1 Reported October 7, 2026 Benchmark leaderboard Scale AI Independent Record for Kimi K2.5 on SWE Atlas Codebase QnA — Public; mini-swe-agent SWE Atlas Refactoring — mini-swe-agent Configuration: mini-swe-agent harness 21.0% labs.scale.com for Kimi K2.5 on SWE Atlas Refactoring — mini-swe-agent (opens in a new tab) Archived copy (opens in a new tab) Mean pass@1 Reported October 7, 2026 Benchmark leaderboard Scale AI Independent Record for Kimi K2.5 on SWE Atlas Refactoring — mini-swe-agent SWE-bench Multilingual Effort: None Reported as: non-thinking 73.0% huggingface.co for Kimi K2.5 (non-thinking) on SWE-bench Multilingual (opens in a new tab) Resolved Tasks Reported January 27, 2026 Model card Moonshot AI Self-reported Record for Kimi K2.5 on SWE-bench Multilingual SWE-bench Multilingual — mini-swe-agent Configuration: mini-swe-agent harness 67.3% github.com for Kimi K2.5 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 Kimi K2.5 on SWE-bench Multilingual — mini-swe-agent SWE-bench Verified Effort: None Reported as: non-thinking 76.8% huggingface.co for Kimi K2.5 (non-thinking) on SWE-bench Verified (opens in a new tab) Resolved Tasks Reported January 27, 2026 Model card Moonshot AI Self-reported Record for Kimi K2.5 on SWE-bench Verified SWE-bench Verified — Epoch AI harness Configuration: Epoch AI harness 73.8% epoch.ai for Kimi K2.5 on SWE-bench Verified — Epoch AI harness (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported October 7, 2026 Evaluated February 17, 2026 at 2:43 PM UTC Benchmark leaderboard Epoch AI Independent Record for Kimi K2.5 on SWE-bench Verified — Epoch AI harness SWE-bench Verified — mini-swe-agent Effort: High Configuration: mini-swe-agent harness 70.8% github.com for Kimi K2.5 (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 Kimi K2.5 on SWE-bench Verified — mini-swe-agent SWE-bench Verified — Vals AI mini-swe-agent Reported as: thinking Configuration: mini-swe-agent harness 70.0% vals.ai for Kimi K2.5 (thinking) 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 Kimi K2.5 on SWE-bench Verified — Vals AI mini-swe-agent SWE-bench Pro Public Effort: None Reported as: non-thinking 50.7% huggingface.co for Kimi K2.5 (non-thinking) on SWE-bench Pro Public (opens in a new tab) Public tasks resolved Reported January 27, 2026 Model card Moonshot AI Self-reported Record for Kimi K2.5 on SWE-bench Pro Public Terminal-Bench 2.0 Effort: None Reported as: non-thinking 50.8% huggingface.co for Kimi K2.5 (non-thinking) on Terminal-Bench 2.0 (opens in a new tab) Terminal-Bench Accuracy Reported January 27, 2026 Model card Moonshot AI Self-reported Record for Kimi K2.5 on Terminal-Bench 2.0 Terminal-Bench 2.0 — Vals AI Terminus 2 Reported as: thinking Configuration: Terminus-2 harness 40.4% vals.ai for Kimi K2.5 (thinking) 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 Kimi K2.5 on Terminal-Bench 2.0 — Vals AI Terminus 2 Terminal-Bench 2.1 — Vals AI Terminus 2 Reported as: thinking Configuration: Terminus-2 harness 41.9% vals.ai for Kimi K2.5 (thinking) 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 Kimi K2.5 on Terminal-Bench 2.1 — Vals AI Terminus 2 Toolathlon Original 27.8% toolathlon.xyz for Kimi K2.5 on Toolathlon Original (opens in a new tab) Archived copy (opens in a new tab) Tasks completed Reported February 4, 2026 Benchmark leaderboard Toolathlon Independent Toolathlon Authors Record for Kimi K2.5 on Toolathlon Original Toolathlon Verified 33.0% toolathlon.xyz for Kimi K2.5 on Toolathlon Verified (opens in a new tab) Archived copy (opens in a new tab) Tasks completed Reported July 15, 2026 Benchmark leaderboard Toolathlon Independent Toolathlon Authors Record for Kimi K2.5 on Toolathlon Verified Vibe Code Bench 1.1 — OpenHands, October 2026 evaluation Reported as: thinking Configuration: OpenHands harness 17.5% vals.ai for Kimi K2.5 (thinking) 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 Kimi K2.5 on Vibe Code Bench 1.1 — OpenHands, October 2026 evaluation