Loading page…
Preferred languages
More languages supported by Google Translate
Open the selector to load the current language catalog.
Translations are provided by Google Translate.
Loading page…
Preferred languages
More languages supported by Google Translate
Open the selector to load the current language catalog.
Translations are provided by Google Translate.
Moonshot AI · Open Weight · rank 21 · bench-align-v5
Kimi K3.1 Pro is built for agent work and reasoning. It ranks in the top quarter for multimodal tasks (top 1% of 136 scored models) and knowledge (top 2% of 284 scored models), by BenchLM's published scores.
Kimi K3.1 Pro by Moonshot AI scores 70.1 overall, costs $2.00 per 1M input tokens and $10.00 per 1M output tokens, and carries a context window of 1.05M tokens — observed 2026-11-21.
Every published price component, including cache reads and writes.
Lifecycle events the source associates with this model, plus what this profile does not claim.
That is not evidence the model has no lifecycle plan — only that this source published none.
Seven axes from the ranking source. A missing axis is drawn as a gap.
Each axis shows the ranking source’s score and, beside it, BenchLM’s separate verified score for that axis. The two are published side by side and are not interchangeable.
Measured values with the date they were observed. Nothing is inferred from a sibling model or a provider claim.
Time to first token: latency to the first answer chunk (Artificial Analysis, via BenchLM). Reasoning models include thinking time, so values can run to tens or hundreds of seconds.
Evidence key: Observed
| Measurement | Value | Observed | Last good | Evidence |
|---|---|---|---|---|
| Time to first token | 156.89 s | 2026-11-21 | 2026-11-21 | |
| Throughput | 31 tok/s | 2026-11-21 | 2026-11-21 |
Regional or per-endpoint measurements appear only when the API supplies them; none are modelled here.
10 conversations per day × 8 messages × 22 active days, 1200 input and 400 output tokens per message, no cache. This uses the same calculator as the cost simulator, so an unavailable applicable rate makes the example unavailable too.
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| GPQA Graduate-Level Google-Proof Q&A | 94.2 | #7 | 448 questions | Graduate level | GPQA: A Graduate-Level Google-Proof Q&A Benchmark |
| GPQA-D GPQA Diamond | 94.2 | #8 | Graduate-level science questions | Graduate level | GPQA: A Graduate-Level Google-Proof Q&A Benchmark |
| HLE Humanity's Last Exam | 70 | #2 | Expert-level questions | Frontier expert level | Humanity's Last Exam |
| Artificial Analysis Intelligence Index Artificial Analysis Intelligence Index | 46.5 | #25 | Cross-benchmark intelligence index | Display-only external reference | Artificial Analysis |
| AA-HLE Artificial Analysis Humanity's Last Exam | 52.5 | #11 | Expert-level questions | Frontier expert reasoning | Artificial Analysis Humanity's Last Exam Benchmark Leaderboard |
| AA-Omniscience Index Artificial Analysis Omniscience Index | 29.9 | #19 | Knowledge questions | Broad factual knowledge | AA-Omniscience: Knowledge and Hallucination Benchmark |
| AA-Omniscience Accuracy Artificial Analysis Omniscience Accuracy | 48.9 | #30 | Knowledge questions | Broad knowledge | Artificial Analysis model benchmarks |
| AA-Omniscience Hallucination Rate Artificial Analysis Omniscience Hallucination Rate | 37.3 | #171 | Knowledge questions | Factuality | Artificial Analysis model benchmarks |
| HLE w/o tools Humanity's Last Exam without tools | 51.1 | #9 | Expert-level questions | Frontier expert level | Introducing GPT-5.4 mini and nano |
| Kimi Hallu Bench Kimi Hallucination Benchmark without tools (Internal) | 5.4 | #1 | Internal work-task prompts without tools | Factuality stress test | Kimi K3.1 Pro Tech Blog: Advancing Open Intelligence |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| Bug Hunt Bench Bug Hunt Bench | 36.0 | #15 | 105 planted bugs across two production TypeScript repositories | Blind production-repository bug finding and repair | Bug Hunt Bench method, caveats, and definitions |
| Kimi Code Bench v2 Kimi Code Bench v2 | 77.1 | #1 | Realistic coding-agent tasks | Production software engineering | Kimi K2.7 Code |
| AA-SciCode Artificial Analysis SciCode | 60.8 |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| AA-LCR Artificial Analysis Long Context Reasoning | 86.3 | #3 | Long-context reasoning tasks | Long-context reasoning | Artificial Analysis model benchmarks |
| MLCR-AA Medical Long Context Reasoning (MLCR-AA) | 38.3 | #10 | Long, fragmented medical-record reasoning | Long-context medical reasoning | Medical Long Context Reasoning (MLCR-AA) |
| CritPt Critical Physics Tasks | 24.6 |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| Terminal-Bench 4.0 Terminal-Bench 4.0 | 65.70 | #5 | 66 professional computer-work tasks | Frontier autonomous knowledge work | Terminal-Bench 4.0 |
| Terminal-Bench-Science 0.1 Terminal-Bench-Science 0.1 | 38.1 | #12 | 70 expert-curated scientific research workflows | Frontier scientific research workflows | Terminal-Bench-Science 0.1 |
| AA Briefcase Artificial Analysis Briefcase | 1674 |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| Chartography (tools) Chartography with image and code tools | 90.2 | #2 | 100 specialized chart types | Professional chart reasoning | Chartography |
| BenchCAD Vision2Code (no tools) BenchCAD Vision2Code voxel IoU without tools | 0.728 | #3 | 1,000-file Vision2Code subset | Programmatic CAD generation | BenchCAD: A comprehensive, industry-standard benchmark for programmatic CAD |
| BenchCAD Vision2Code (tools) |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| ExploitBench ExploitBench v8-bench | 75 | #9 | V8 exploit synthesis runs | Browser exploitation and cybersecurity | ExploitBench |
| SpireClimb SpireClimb (Slay the Spire 1 and 2) | 0.0 | #11 | 60 Slay the Spire 1 runs (Ascension 20, Heart kill) and 75 Slay the Spire 2 runs (Ascension 10) per model | Maximum game difficulty, long-horizon computer use | SpireClimb (Epoch AI) |
| Chess Puzzles Chess Puzzles (Epoch AI) | 45.0 |
| #9 |
| Scientific coding subproblems |
| Scientific programming |
| Artificial Analysis SciCode Benchmark Leaderboard |
| DeepSWE DeepSWE | 75.5 | #6 | 113 software engineering tasks across 91 repositories and 5 languages | Long-horizon software engineering | DeepSWE benchmark blog |
| OpenHarmony Bench v1.2 OpenHarmony Bench v1.2 | 52.38 | #4 | App-development, bug-fix and migration tasks (count not published) | End-to-end OpenHarmony application development and migration | OpenHarmony Bench: Evaluating LLMs and Coding Agents on OpenHarmony App Development |
| FrontierCode 2.0 FrontierCode 2.0 | 19.9 | #26 | 132 private software-engineering tasks | Frontier coding-agent quality | FrontierCode 2.0 |
| Kimi Code Bench 3.0 Long-horizon Kimi Code Bench 3.0 Long-horizon (Internal) | 61.2 | #1 | Internal long-horizon coding-agent tasks | Long-horizon software engineering | Kimi K3.1 Pro Tech Blog: Advancing Open Intelligence |
| PostTrainBench PostTrainBench v1.2 | 36.5 | #9 | Post-training four base models on six benchmarks | Autonomous ML engineering | PostTrainBench |
| ProgramBench (binary) ProgramBench binary score (task counts only at 95% or higher) | 31.5 | #1 | Cleanroom executable reimplementation | Whole-program reconstruction | ProgramBench |
| #22 |
| Research-level physics questions |
| Research-level physics reasoning |
| CritPt Benchmark Leaderboard |
| #8 |
| Professional knowledge-work tasks |
| Professional work |
| Artificial Analysis Briefcase Benchmark Leaderboard |
| AA AutomationBench Artificial Analysis AutomationBench | 73.3 | #7 | Business-process automation tasks | Agentic automation | Artificial Analysis AutomationBench Benchmark Leaderboard |
| BrowseComp BrowseComp | 92.1 | #3 | Research questions requiring browsing | Hard web research | BrowseComp |
| HLE w/ tools Humanity's Last Exam with tools | 70.0 | #1 | Expert questions with tool use | Frontier tool-augmented reasoning | DeepSeek-V4 Technical Report |
| GDPval-AA GDPval-AA | 1861 | #2 | Agentic real-world work tasks | Professional agentic workflows | DeepSeek-V4 Technical Report |
| GDPval-AA GDPval-AA normalized | 67.3 | #3 | Economically valuable tasks | Professional agentic workflows | Artificial Analysis model benchmarks |
| AA Terminal-Bench 4.0 Artificial Analysis Terminal-Bench v4.0 | 67.2 | #1 | Terminal-based agent tasks | Agentic software engineering | Artificial Analysis Terminal-Bench v4.0 Benchmark Leaderboard |
| GDP.pdf Artificial Analysis GDP.pdf | 31.4 | #2 | Professional document-production tasks | Professional knowledge work | GDP.pdf Benchmark Leaderboard |
| AA-AnalystAgent Artificial Analysis AnalystAgent | 38.8 | #28 | Spreadsheet and document analysis questions | Business and data analysis | AA-AnalystAgent Benchmark Leaderboard |
| OSWorld 2.0 OSWorld 2.0 | 79.6 | #1 | 108 long-horizon computer-use workflows | Long-horizon professional workflows | OSWorld2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks |
| ExploitGym ExploitGym | 20.7 | #13 | 898 exploitation tasks | Advanced cybersecurity exploitation | ExploitGym: Can AI Agents Turn Security Vulnerabilities into Real Attacks? |
| Agents' Last Exam Agents' Last Exam | 43.2 | #6 | Agent tasks | Advanced agentic work | DeepSeek V4 Flash 0731 update |
| APEX-Agents APEX-Agents | 69.4 | #2 | Professional-services agent tasks | Long-horizon professional work | Kimi K3: Open Frontier Intelligence |
| MazeBench MazeBench: visual spatial reasoning in a 3D open world | 2 | #20 | 100 hidden gems across 256 rooms in one open world | Long-horizon spatial planning, with single puzzles that can take over one hundred moves | MazeBench Results |
| CWE-bench CWE-bench v2 | 45.3 | #19 | Audit and patch C/C++, Go, Java, TypeScript/JavaScript, Python, and Rust repositories; 100 public and 150 held-out tasks | Frontier agent evaluation | CWE-bench v2 leaderboard and methodology |
| Terminal-Bench 4.1 Terminal-Bench 4.1 | 59.70 | #10 | 66 professional computer-work tasks | Frontier autonomous knowledge work | Terminal-Bench 4.1 |
| OSWorld 2.1 OSWorld 2.1 (all 108 tasks) | 79.6 | #4 | 108 long-horizon computer-use workflows | Long-horizon professional workflows | OSWorld 2.1 release (xlang-ai/OSWorld-V2, tag osworld-v2.1) |
| AA Cyber Index Artificial Analysis Cyber Index | 64.1 | #1 | Three defensive cybersecurity evaluations | Real-world vulnerability discovery and patching | Artificial Analysis Cyber Index |
| CWE-Bench-AA Artificial Analysis CWE-Bench-AA | 60.8 | #8 | Real-world vulnerability patching tasks | Automated vulnerability remediation | CWE-Bench-AA Benchmark Leaderboard |
| DeepsecBench-AA Artificial Analysis DeepsecBench-AA | 36.7 | #5 | Vulnerability discovery in real codebases | Security code review | DeepsecBench-AA Benchmark Leaderboard |
| CyberGym-E2E-AA Artificial Analysis CyberGym-E2E-AA | 94.7 | #1 | 131 end-to-end vulnerability reproduction and patching tasks | Real-world cybersecurity | CyberGym-E2E-AA Benchmark Leaderboard |
| MKA Multimodal Knowledge Agent Benchmark | 43.9 | #12 | 200 multimodal professional tasks across 10 industry verticals | Expert multimodal knowledge work | MKA Benchmark Leaderboard |
| Agents' Last Exam (CLI) Agents' Last Exam v1.1, CLI subset | 44.2 | #1 | 86 CLI agent tasks | Advanced agentic work | Kimi K3.1 Pro Tech Blog: Advancing Open Intelligence |
| BioMysteryBench BioMysteryBench (overall, v11 release) | 80.6 | #1 | Biological data investigations | Expert scientific analysis | Kimi K3.1 Pro Tech Blog: Advancing Open Intelligence |
| Frontier Finance Frontier Finance | 58.6 | #1 | Investment research workflows | Professional finance | Kimi K3.1 Pro Tech Blog: Advancing Open Intelligence |
| Harvey Legal Agent (public 1,251) Harvey's Legal Agent Benchmark, public 1,251-task set, all-pass | 23.7 | #1 | 1,251 public legal tasks | Professional legal work | Kimi K3.1 Pro Tech Blog: Advancing Open Intelligence |
| HANDBOOK.md HANDBOOK.md | 44.6 | #1 | Agent tasks (v1 release) | Advanced agentic work | Kimi K3.1 Pro Tech Blog: Advancing Open Intelligence |
| Business Operation Business Operation (Internal) | 37.8 | #1 | Simulated business management | Long-horizon decision-making | Kimi K3.1 Pro Tech Blog: Advancing Open Intelligence |
| Financial Modeling Financial Modeling (Internal) | 57.6 | #1 | Spreadsheet financial models | Professional financial modeling | Kimi K3.1 Pro Tech Blog: Advancing Open Intelligence |
| Financial Research Financial Research (Internal) | 70.4 | #1 | Source-grounded research reports | Professional financial research | Kimi K3.1 Pro Tech Blog: Advancing Open Intelligence |
| DECK-Arena DECK-Arena (Internal, Elo) | 1456 | #1 | Real-world presentation requests | Professional presentation creation | Kimi K3.1 Pro Tech Blog: Advancing Open Intelligence |
| Design Bench Design Bench (Internal, Elo) | 957 | #1 | Graphic design requests | Professional graphic design | Kimi K3.1 Pro Tech Blog: Advancing Open Intelligence |
| Kimi Hallu Bench Hard (tools) Kimi Hallucination Benchmark Hard with tools (Internal) | 8.3 | #1 | Hard internal work-task prompts with tools | Factuality stress test | Kimi K3.1 Pro Tech Blog: Advancing Open Intelligence |
| 0.927 |
| #4 |
| 1,000-file Vision2Code subset |
| Programmatic CAD generation |
| BenchCAD: A comprehensive, industry-standard benchmark for programmatic CAD |
| MMMU-Pro Massive Multi-discipline Multimodal Understanding Pro | 84.1 | #2 | Multimodal academic reasoning | Frontier multimodal | MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark |
| AA-MMMU-Pro Artificial Analysis MMMU-Pro | 83.9 | #10 | Multimodal academic reasoning | Frontier multimodal | Artificial Analysis MMMU-Pro Benchmark Leaderboard |
| Design Arena Website Design Arena Website Elo | 1314 | #9 | Website generation comparisons | Design and website generation | OpenRouter Grok 4.3 benchmarks |
| OfficeQA Pro OfficeQA Pro | 67.4 | #4 | Document and spreadsheet tasks | Enterprise grounded reasoning | OfficeQA Pro: An Enterprise Benchmark for End-to-End Grounded Reasoning |
| BabyVision w/ Python BabyVision with Python | 95.4 | #1 | Visual perception tasks with Python | Fine-grained visual perception | Kimi K3: Open Frontier Intelligence |
| ZeroBench w/ Python ZeroBench_main with Python | 63.0 | #1 | Visual reasoning questions with Python | Tool-augmented visual reasoning | Kimi K3: Open Frontier Intelligence |
| PerceptionBench PerceptionBench (Internal) | 68.3 | #1 | Internal atomic visual-perception tasks | Fine-grained visual perception | Kimi K3: Open Frontier Intelligence |
| MMMU-Pro w/ Python MMMU-Pro with Python | 90 | #1 | Multimodal academic reasoning | Frontier multimodal | Introducing GPT-5.4 mini and nano |
| ZeroBench ZeroBench | 39.0 | #3 | 100 visual reasoning questions | Tool-augmented visual reasoning | Muse Spark Eval Methodology |
| CharXiv CharXiv Reasoning | 93.4 | #3 | Scientific chart reasoning | Scientific visualization reasoning | CharXiv: Charting Gaps in Realistic Chart Understanding in Multimodal LLMs |
| CharXiv w/o tools CharXiv Reasoning without tools | 89 | #1 | Scientific chart reasoning (tool-free) | Scientific visualization reasoning | CharXiv: Charting Gaps in Realistic Chart Understanding in Multimodal LLMs |
| OfficeQA Pro v2 OfficeQA Pro v2 | 64.4 | #2 | Document and spreadsheet tasks | Enterprise document reasoning | Kimi K3.1 Pro Tech Blog: Advancing Open Intelligence |
| GDP.pdf (Gemini judge) GDP.pdf strict pass rate, page images plus text, Gemini judge | 34.6 | #1 | Professional document prompts | Professional document reasoning | GDP.pdf |
| GDP.pdf w/ Python (Gemini judge) GDP.pdf task-macro rubric pass rate with Python, Gemini judge | 85.7 | #1 | Professional document prompts with Python | Tool-assisted document reasoning | GDP.pdf |
| #29 |
| 100 programmatically generated chess positions with a single best move |
| Novel chess positions, single best move |
| Chess Puzzles (Epoch AI) |
| Mystery Game Puzzles Mystery Game Puzzles (Epoch AI) | 42.0 | #22 | 100 single-best-move positions from an undisclosed game | Unfamiliar game positions, single best move | Mystery Game Puzzles (Epoch AI) |
| Furniture Assembly Furniture Assembly Benchmark (Epoch AI) | 55.8 | #16 | 60 photos of three IKEA builds, some with deliberate assembly mistakes | Spatial reasoning from technical diagrams to real photos | Furniture Assembly Benchmark (Epoch AI) |
| EBR-bench Earthborne Rangers (EBR-bench) | 37.1 | #16 | Ten playthroughs of an Earthborne Rangers campaign segment per sample (eight learning, two scored) | Learning an unfamiliar game over multi-hour playthroughs | Earthborne Rangers (EBR-bench), Epoch AI |
| MirrorCode MirrorCode (Epoch AI and METR) | 43.3 | #21 | 30 reimplementation tasks (15 programs in two languages), three attempts each | Days-long software engineering without source code | MirrorCode (Epoch AI) |
| xdev-bench-hard xdev-bench-hard (Internal, pass@3) | 81.0 | #1 | Vulnerability exploitation tasks | Offensive security research | Kimi K3.1 Pro Tech Blog: Advancing Open Intelligence |
| NYT Connections NYT Connections LLM Benchmark (extended version) | 93.4 | #14 | 940 NYT Connections puzzles, each with up to four added trick words | Wordplay, word knowledge and decoys that fit almost-but-not-quite | NYT Connections LLM Benchmark (Lech Mazur, GitHub) |
| StealthMark StealthMark Intelligence Benchmarks (overall score) | 56.7 | #11 | 8 original tasks: Newton's Mirror, Ground Truth, Latch, Foresight, Mona Lisa, Selfie, Beach and Raccoon | Chained physical reasoning, planning without tools and precise visual construction | StealthMark: The AI Benchmark Explained (Stealth Models) |
| FrontierPhysics End-to-End Physics Research Benchmark for AI Agents | 6.5 | #16 | 56 research projects from 42 physicists across nine fields, three trials each (168 rollouts per setup) | Open-ended research projects that took their authors about 270 days on average | FrontierPhysics: Evaluating Agents for End-to-End Physics Research (arXiv, November 4, 2026) |
| HoneyBench HoneyBench v0.2 (Goodhart Labs) | 71.8 | #10 | 20 private honeypot tasks across 7 domains with exploitable evaluators | Agentic alignment and specification gaming | HoneyBench v0.2 |