# Kimi K3.1 Pro vs GPT-6.1 Sol

Model compare · https://benchgap.net/compare/kimi-3-1-pro/gpt-6-1-sol · data retrieved 2026-11-21

Kimi K3.1 Pro stands at 91.5 on 190 benchmarks, 60 measured (rank #20 of 394), GPT-6.1 Sol at 92.5 on 168 benchmarks, 55 measured (rank #16 of 394) - a frontier model. Of the 161 benchmarks both have a score on, Kimi K3.1 Pro leads on 4 and GPT-6.1 Sol on 24 where both are measured.

| Benchmark | Kimi K3.1 Pro | GPT-6.1 Sol | Δ (pp) |
|---|---|---|---|
| [AA-GPQA Diamond](https://benchgap.net/b/aa-gpqa-diamond/current.md) | 92.4% | 96.0% | -3.6 |
| [AA-HLE](https://benchgap.net/b/aa-hle/current.md) | 52.5% | 52.9% | -0.4 |
| [AA-SciCode](https://benchgap.net/b/aa-sci-code/current.md) | 60.8% | 54.2% | +6.6 |
| [Artificial Analysis Intelligence Index](https://benchgap.net/b/artificialanalysis/current.md) | 46.5% | 54.6% | -8.2 |
| [CritPt](https://benchgap.net/b/critpt/current.md) | 24.6% | 31.7% | -7.1 |
| [GDPval-AA](https://benchgap.net/b/gdpvalaanormalized/current.md) | 67.3% | 54.8% | +12.5 |
| [GPQA Diamond](https://benchgap.net/b/gpqa-diamond/current.md) | 94.2% | 96.2% | -2.0 |
| [HLE](https://benchgap.net/b/hle/current.md) | 70.0% | 69.4% | +0.6 |
| [AA-LCR](https://benchgap.net/b/lcr/current.md) | 86.3% | 83.0% | +3.3 |
| [LiveCodeBench v6](https://benchgap.net/b/livecodebench-v6/current.md) | 100.0% | 94.7% | +5.3 |
| [AA-Omniscience Accuracy](https://benchgap.net/b/omniscienceaccuracy/current.md) | 48.9% | 61.8% | -12.9 |
| [SciCode](https://benchgap.net/b/scicode/current.md) | 60.3% | 53.9% | +6.4 |
| [Terminal-Bench 2.1](https://benchgap.net/b/terminal-bench%23terminal-bench-2-1/current.md) | 89.1% | 88.9% | +0.2 |
| [BrowseComp](https://benchgap.net/b/browsecomp/current.md) | 92.1% | 91.4% | +0.7 |
| [HLE w/ tools](https://benchgap.net/b/hlewithtools/current.md) | 70.0% | 62.4% | +7.6 |
| [LongBench v2](https://benchgap.net/b/longbench-v2/current.md) | 71.5% | 68.4% | +3.2 |
| [AA Coding Index](https://benchgap.net/b/aa-coding-index/current.md) | 76.0% | 78.7% | -2.8 |
| [AA-MMMU-Pro](https://benchgap.net/b/aa-mmmu-pro/current.md) | 83.9% | 86.0% | -2.1 |
| [APEX-Agents](https://benchgap.net/b/apexagents/current.md) | 69.4% | 37.5% | +31.9 |
| [APEX-Agents-AA](https://benchgap.net/b/apexagentsaa/current.md) | 39.0% | 40.0% | -1.0 |
| [BioMysteryBench (human-difficult)](https://benchgap.net/b/biomysterybenchhumandifficult/current.md) | 49.0% | 49.9% | -0.9 |
| [DeepSearchQA](https://benchgap.net/b/deepsearchqa/current.md) | 93.7% | 89.6% | +4.1 |
| [SWE-bench Verified](https://benchgap.net/b/swe-bench-verified/current.md) | 90.8% | 89.0% | +1.7 |
| [AutomationBench](https://benchgap.net/b/automationbench/current.md) | 47.4% | 36.1% | +11.3 |
| [CyberGym](https://benchgap.net/b/cybergym/current.md) | 96.3% | 83.0% | +13.3 |
| [JobBench](https://benchgap.net/b/jobbench/current.md) | 66.5% | 59.3% | +7.2 |
| [SWE-bench Pro](https://benchgap.net/b/swe-bench-pro/current.md) | 77.0% | 81.4% | -4.4 |
| [WideResearch](https://benchgap.net/b/wideresearch/current.md) | 83.1% | 84.3% | -1.1 |
| [AA Agentic Index](https://benchgap.net/b/aa-agentic-index/current.md) | 68.0% | 50.6% | +17.4 |
| [MMLU-Pro](https://benchgap.net/b/mmlu-pro/current.md) | 85.9% | 85.5% | +0.3 |
| [FailureSensorIQ](https://benchgap.net/b/failuresensoriq/current.md) | 68.3% | 68.6% | -0.3 |
| [GPQA](https://benchgap.net/b/gpqa/current.md) | 94.2% | 95.8% | -1.6 |
| [Vals GPQA Diamond](https://benchgap.net/b/vals-gpqa-diamond/current.md) | 93.1% | 98.8% | -5.7 |
| [Vals LiveCodeBench](https://benchgap.net/b/valslivecodebench/current.md) | 89.0% | 85.8% | +3.2 |
| [Vals MMLU-Pro](https://benchgap.net/b/vals-mmlu-pro/current.md) | 89.9% | 89.8% | +0.1 |
| [MMMLU](https://benchgap.net/b/mmmlu/current.md) | 91.2% | 92.0% | -0.8 |
| [MMMU](https://benchgap.net/b/mmmu/current.md) | 88.5% | 89.9% | -1.4 |
| [Chess Puzzles](https://benchgap.net/b/chesspuzzles/current.md) | 45.0% | 68.0% | -23.0 |
| [AA MMLU-Pro](https://benchgap.net/b/aa-mmlu-pro/current.md) | 88.5% | 90.5% | -2.0 |
| [Gert Labs](https://benchgap.net/b/gertlabs/current.md) | 80.3% | 73.2% | +7.1 |
| [AA-AnalystAgent](https://benchgap.net/b/aa-analyst-agent/current.md) | 38.8% | 50.0% | -11.2 |
| [AA Tau3 Banking](https://benchgap.net/b/aa-tau3-banking/current.md) | 100.0% | 45.7% | +54.3 |
| [ApprenticeBench](https://benchgap.net/b/apprenticebench/current.md) | 17.6% | 51.7% | -34.1 |
| [ARC-AGI-1](https://benchgap.net/b/arcagi1/current.md) | 95.1% | 96.5% | -1.4 |
| [ARC-AGI-2](https://benchgap.net/b/arc-agi-2/current.md) | 79.9% | 94.2% | -14.2 |
| [BabaIsBench](https://benchgap.net/b/babaisbench/current.md) | 98.6% | 100.0% | -1.4 |
| [CursorBench 3.1](https://benchgap.net/b/cursor-bench31/current.md) | 70.6% | 54.4% | +16.3 |
| [CursorBench 3.2](https://benchgap.net/b/cursor-bench32/current.md) | 61.1% | 68.2% | -7.2 |
| [EBR-bench](https://benchgap.net/b/ebrbench/current.md) | 37.1% | 54.3% | -17.2 |
| [Terminal-Bench 3.0](https://benchgap.net/b/terminal-bench%23terminal-bench-3-0/current.md) | 46.4% | 47.1% | -0.8 |
| [FrontierCode 1.1 Main](https://benchgap.net/b/frontiercode/current.md) | 50.9% | 52.4% | -1.4 |
| [FrontierSWE v2](https://benchgap.net/b/frontierswev2/current.md) | 32.7% | 56.0% | -23.3 |
| [Furniture Assembly](https://benchgap.net/b/furnitureassembly/current.md) | 55.8% | 80.0% | -24.2 |
| [MaxxBench](https://benchgap.net/b/maxxbench/current.md) | 62.6% | 69.4% | -6.8 |
| [MazeBench](https://benchgap.net/b/mazebench/current.md) | 2.0% | 17.0% | -15.0 |
| [MirrorCode](https://benchgap.net/b/mirrorcode/current.md) | 43.3% | 61.1% | -17.8 |
| [Mystery Game Puzzles](https://benchgap.net/b/mysterygamepuzzles/current.md) | 42.0% | 80.0% | -38.0 |
| [NYT Connections](https://benchgap.net/b/nyt-connections/current.md) | 93.4% | 97.8% | -4.4 |
| [OfficeQA Pro](https://benchgap.net/b/officeqapro/current.md) | 67.4% | 67.6% | -0.2 |
| [OSWorld-Verified](https://benchgap.net/b/osworld-verified/current.md) | 87.1% | 84.4% | +2.7 |
| [ParseBench-1](https://benchgap.net/b/parse-bench-llama-index/current.md) | 71.2% | 69.6% | +1.6 |
| [Terminal-Bench 4.1](https://benchgap.net/b/terminal-bench41/current.md) | 59.7% | 60.9% | -1.2 |
| [Terminal-Bench Hard](https://benchgap.net/b/terminal-bench-hard/current.md) | 69.0% | 69.4% | -0.3 |
| [Vals SWE-bench](https://benchgap.net/b/valsswebench/current.md) | 95.3% | 97.4% | -2.1 |
| [Terminal-Bench 2.1 (Vals AI)](https://benchgap.net/b/vals-terminal-bench21/current.md) | 85.3% | 79.9% | +5.4 |
| [VulcanBench v3](https://benchgap.net/b/vulcanbench%23vulcanbench-v3/current.md) | 87.6% | 87.6% | +0.0 |
| [CWE-Bench-AA](https://benchgap.net/b/aa-cwe-bench/current.md) | 60.8% | 63.3% | -2.5 |
| [AA Cyber Index](https://benchgap.net/b/aa-cyber-index/current.md) | 64.1% | 30.4% | +33.7 |
| [DeepsecBench-AA](https://benchgap.net/b/aa-deepsec-bench/current.md) | 36.7% | 30.8% | +5.9 |
| [Harvey LAB-AA v1.1](https://benchgap.net/b/aa-harvey-lab-v11/current.md) | 12.5% | 6.9% | +5.6 |
| [HealthBench Professional (length-adjusted, Artificial Analysis)](https://benchgap.net/b/aa-health-bench-professional/current.md) | 60.0% | 62.5% | -2.5 |
| [HealthBench Professional (raw, Artificial Analysis)](https://benchgap.net/b/aa-health-bench-professional-raw/current.md) | 67.9% | 70.4% | -2.5 |
| [AA ITBench](https://benchgap.net/b/aa-itbench/current.md) | 50.9% | 47.6% | +3.3 |
| [Bug Hunt Bench](https://benchgap.net/b/bug-hunt-bench/current.md) | 36.0% | 44.3% | -8.3 |
| [Chartography (tools)](https://benchgap.net/b/chartographywithtools/current.md) | 90.2% | 86.9% | +3.3 |
| [CursorBench 4.0](https://benchgap.net/b/cursor-bench40/current.md) | 46.7% | 54.7% | -8.0 |
| [CWE-bench v1](https://benchgap.net/b/cwe-bench%23cwe-bench-v1/current.md) | 56.4% | 63.9% | -7.4 |
| [DeepSWE](https://benchgap.net/b/deepswe/current.md) | 75.5% | 71.9% | +3.6 |
| [DRACO](https://benchgap.net/b/draco/current.md) | 86.9% | 87.9% | -1.0 |
| [FrontierCode 2.0](https://benchgap.net/b/frontiercode-2/current.md) | 19.9% | 39.6% | -19.7 |
| [FrontierPhysics](https://benchgap.net/b/frontierphysics/current.md) | 6.5% | 19.6% | -13.1 |
| [HLE w/o tools](https://benchgap.net/b/hlenotools/current.md) | 51.1% | 59.6% | -8.5 |
| [OSWorld 2.1](https://benchgap.net/b/osworld-2-1/current.md) | 79.6% | 78.8% | +0.8 |
| [OSWorld 2.1 Offline](https://benchgap.net/b/osworld-2-1-offline/current.md) | 86.2% | 70.6% | +15.6 |
| [PostTrainBench v1.1](https://benchgap.net/b/posttrainbench%23posttrainbench-v1-1/current.md) | 39.5% | 41.9% | -2.4 |
| [SpireClimb](https://benchgap.net/b/spireclimb/current.md) | 0.0% | 23.8% | -23.8 |
| [StealthMark](https://benchgap.net/b/stealthmark/current.md) | 56.7% | 67.8% | -11.1 |
| [SWE-bench Multimodal](https://benchgap.net/b/swe-bench-multimodal/current.md) | 55.4% | 56.7% | -1.3 |
| [Terminal-Bench 4.0](https://benchgap.net/b/terminal-bench/current.md) | 65.7% | 62.0% | +3.7 |
| [Terminal-Bench-Science 0.1](https://benchgap.net/b/terminal-bench-science/current.md) | 38.1% | 57.0% | -18.9 |
| [Toolathlon-Verified](https://benchgap.net/b/toolathlonverified/current.md) | 72.8% | 77.9% | -5.2 |
| [VulcanBench Frontier v4](https://benchgap.net/b/vulcanbench/current.md) | 88.0% | 88.8% | -0.8 |
| [AA AutomationBench](https://benchgap.net/b/aa-automation-bench/current.md) | 73.3% | 74.0% | -0.7 |
| [GDP.pdf](https://benchgap.net/b/aa-gdp-pdf/current.md) | 31.4% | 27.0% | +4.4 |
| [AA Terminal-Bench 4.0](https://benchgap.net/b/aa-terminal-bench4/current.md) | 67.2% | 60.5% | +6.7 |
| [ARC-AGI-3](https://benchgap.net/b/arcagi3/current.md) | 12.8% | 52.7% | -39.9 |
| [ARC-AGI-3 Provider Adapter](https://benchgap.net/b/arc-agi-3-provider-adapter/current.md) | 94.5% | 96.2% | -1.6 |
| [cursorBench41](https://benchgap.net/b/cursor-bench41/current.md) | 52.2% | 44.8% | +7.4 |
| [CWE-bench](https://benchgap.net/b/cwe-bench-v2/current.md) | 45.3% | 63.2% | -17.9 |
| [MKA](https://benchgap.net/b/mka/current.md) | 43.9% | 47.7% | -3.8 |
| [SkillsBench official leaderboard (BenchFlow)](https://benchgap.net/b/skillsbench/current.md) | 56.9% | 59.5% | -2.5 |
| [BinaryAudit](https://benchgap.net/b/binaryaudit/current.md) | 35.8% | 35.8% | +0.0 |
| [OTelBench](https://benchgap.net/b/otelbench/current.md) | 22.5% | 22.5% | +0.0 |
| [FACTS Multimodal](https://benchgap.net/b/facts-multimodal/current.md) | 46.4% | 52.6% | -6.2 |
| [Hermes Bench](https://benchgap.net/b/hermesbench/current.md) | 73.2% | 73.9% | -0.7 |
| [Hermes Index](https://benchgap.net/b/hermesindex/current.md) | 92.5% | 57.1% | +35.4 |
| [ParseBench-2](https://benchgap.net/b/parsebench/current.md) | 78.4% | 76.2% | +2.3 |
| [CharXiv](https://benchgap.net/b/charxiv/current.md) | 93.4% | 87.3% | +6.1 |
| [CharXiv w/o tools](https://benchgap.net/b/charxivnotools/current.md) | 89.0% | 84.6% | +4.4 |
| [ExploitBench](https://benchgap.net/b/exploitbench/current.md) | 74.7% | 99.7% | -25.0 |
| [ExploitGym](https://benchgap.net/b/exploitgym/current.md) | 20.7% | 35.1% | -14.4 |
| [AI2D_TEST](https://benchgap.net/b/ai2dtest/current.md) | 93.5% | 94.2% | -0.7 |
| [C-Eval](https://benchgap.net/b/ceval/current.md) | 93.5% | 93.4% | +0.1 |
| [CountBench](https://benchgap.net/b/countbench/current.md) | 100.0% | 100.0% | +0.0 |
| [DynaMath](https://benchgap.net/b/dynamath/current.md) | 88.5% | 85.5% | +3.0 |
| [ERQA](https://benchgap.net/b/erqa/current.md) | 79.1% | 68.8% | +10.3 |
| [MathVision](https://benchgap.net/b/mathvision/current.md) | 95.3% | 95.0% | +0.3 |
| [MCP Atlas](https://benchgap.net/b/mcpatlas/current.md) | 84.7% | 82.1% | +2.6 |
| [MMLU-Redux](https://benchgap.net/b/mmluredux/current.md) | 97.1% | 98.7% | -1.6 |
| [MMMU-Pro](https://benchgap.net/b/mmmu-pro/current.md) | 84.1% | 85.3% | -1.2 |
| [NL2Repo](https://benchgap.net/b/nl2repo/current.md) | 63.2% | 61.6% | +1.5 |
| [PostTrainBench v1](https://benchgap.net/b/posttrainbench%23posttrainbench-v1/current.md) | 40.1% | 42.5% | -2.4 |
| [RealWorldQA](https://benchgap.net/b/realworldqa/current.md) | 88.5% | 89.7% | -1.2 |
| [ScreenSpot Pro](https://benchgap.net/b/screenspot-pro/current.md) | 85.0% | 89.1% | -4.1 |
| [SuperGPQA](https://benchgap.net/b/supergpqa/current.md) | 100.0% | 100.0% | +0.0 |
| [Toolathlon](https://benchgap.net/b/toolathlon/current.md) | 63.4% | 55.9% | +7.5 |
| [V*](https://benchgap.net/b/vstar/current.md) | 100.0% | 100.0% | +0.0 |
| [Video-MME (w/o subtitle)](https://benchgap.net/b/videommenosub/current.md) | 87.5% | 91.3% | -3.7 |
| [Video-MME (with subtitle)](https://benchgap.net/b/videommewithsub/current.md) | 92.0% | 91.8% | +0.2 |
| [HealthBench Hard](https://benchgap.net/b/healthbench-hard/current.md) | 36.5% | 36.2% | +0.3 |
| [MedXpertQA (MM)](https://benchgap.net/b/medxpertqamm/current.md) | 82.7% | 77.8% | +4.9 |
| [React Native Evals](https://benchgap.net/b/reactnativeevals/current.md) | 81.3% | 78.5% | +2.8 |
| [ResearchClawBench](https://benchgap.net/b/researchclawbench/current.md) | 24.0% | 21.6% | +2.4 |
| [PostTrainBench](https://benchgap.net/b/post-train-bench12/current.md) | 36.5% | 38.8% | -2.3 |
| [DAYJOB](https://benchgap.net/b/dayjob/current.md) | 4.7% | 15.5% | -10.8 |
| [DAYJOB Healthcare](https://benchgap.net/b/dayjob-healthcare/current.md) | 1.5% | 10.8% | -9.3 |
| [Finance Agent v2](https://benchgap.net/b/financeagentv2/current.md) | 57.6% | 62.3% | -4.7 |
| [BioMysteryBench (human-solvable)](https://benchgap.net/b/biomysterybenchhumansolvable/current.md) | 89.4% | 89.5% | -0.1 |
| [HealthBench (raw)](https://benchgap.net/b/healthbench/current.md) | 59.4% | 56.7% | +2.7 |
| [HealthBench (length-adjusted)](https://benchgap.net/b/healthbenchlengthadjusted/current.md) | 58.3% | 58.5% | -0.2 |
| [HealthBench Professional](https://benchgap.net/b/healthbenchprofessional/current.md) | 58.8% | 64.2% | -5.4 |
| [HealthBench Professional (raw)](https://benchgap.net/b/healthbenchprofessionalraw/current.md) | 69.5% | 67.2% | +2.3 |
| [HLE-Verified](https://benchgap.net/b/hleverified/current.md) | 54.4% | 55.4% | -1.1 |
| [LABBench2](https://benchgap.net/b/labbench2/current.md) | 85.1% | 83.1% | +2.0 |
| [ScarfBench](https://benchgap.net/b/scarfbench/current.md) | 69.6% | 68.4% | +1.2 |
| [BlenderWorld (text-only)](https://benchgap.net/b/blenderworld-text-only/current.md) | 75.0% | 85.3% | -10.3 |
| [Cookie-Bench](https://benchgap.net/b/cookie-bench/current.md) | 85.2% | 89.7% | -4.5 |
| [STEMBench](https://benchgap.net/b/stembench/current.md) | 2.6% | 2.8% | -0.2 |
| [Agents' Last Exam](https://benchgap.net/b/agentslastexam/current.md) | 43.2% | 51.7% | -8.5 |
| [BabyVision w/ Python](https://benchgap.net/b/babyvisionpython/current.md) | 95.4% | 94.4% | +1.0 |
| [OpenHarmony Bench v1.0](https://benchgap.net/b/openharmonybench%23openharmonybench-v1-0/current.md) | 58.9% | 58.9% | +0.0 |
| [OpenHarmony Bench v1.2](https://benchgap.net/b/openharmonybench/current.md) | 52.4% | 63.8% | -11.4 |
| [SEC-Bench Pro](https://benchgap.net/b/secbenchpro/current.md) | 77.3% | 78.8% | -1.5 |
| [MRCRv2](https://benchgap.net/b/mrcrv2/current.md) | 86.0% | 85.9% | +0.1 |
| [MMLongBench-Doc](https://benchgap.net/b/mmlongbenchdoc/current.md) | 61.7% | 61.5% | +0.1 |
| [SWE-Marathon](https://benchgap.net/b/swemarathon/current.md) | 51.7% | 59.1% | -7.4 |
| [BioBasicsBench](https://benchgap.net/b/biobasicsbench/current.md) | 41.9% | 62.6% | -20.7 |
| [LifeVal](https://benchgap.net/b/lifeval/current.md) | 80.7% | 80.1% | +0.6 |
| [MMMU-Pro w/ Python](https://benchgap.net/b/mmmupropython/current.md) | 90.0% | 88.1% | +1.9 |
| [ExploitBench Internal Port](https://benchgap.net/b/exploitbenchinternalport/current.md) | 0.9% | 21.5% | -20.6 |
| [SWE-Atlas Codebase QnA](https://benchgap.net/b/swe-atlas-codebase-qna/current.md) | 61.7% | 61.0% | +0.7 |

General performance is the share of benchmark duels a model is expected to win against every other ranked model: a Bradley-Terry fit over every head-to-head result on the listed benchmarks, measured and estimated, each pair held against each other on the benchmarks both have a score on. A model measured only on benchmarks apart from the main field has no standing. The frontier is the strongest tenth. Every estimate carries its error and confidence on the model pages.
