Data as of November 17, 2026 · How the score is built
Kimi K3
Decision readingKimi K3 scores 67 out of 100 and ranks #20 of 218. This profile shows 77 source-displayable benchmark rows; its strongest eligible category is Multimodal & Grounded at #19. API pricing is $3 input and $15 output per million tokens, with cached input at $0.3.
Email me when its price, rank or availability changes.
Capability
67/100
field median 49.5#20 of 218 ranked models
Public
#20of 218
Verified #11 of 79
Price
$3input / $15 output
input median $0.60cached $0.30 · blended $9
Speed
38tok/s
field median 89 tok/sFirst token 56.25 s
Context
1.05Mtokens
field median 256,000Reported for this model; direct source link not stored
Decision snapshot
Where this model sits in the ranked field, its strongest published evidence, and what to validate before choosing it. The marker compares it with the current ranked catalog, not with an absolute quality threshold.
Strongest published evidence
Multimodal & Grounded ranks #19. Particularly strong for screenshots, documents, charts, and grounded multimodal workflows.
Validate before choosing
77 published rows leave some tracked benchmark slots empty. Coding is its lowest eligible category at #23.
Source-linked · 77 displayable benchmark rows
Is Kimi K3 right for your job?
Its place on the LLM Selector’s job rankings, the same order the job pages publish. Describe your own job to see where it stands for that.
Kimi K3 has a newer version, Kimi K3.1 Pro. Where Kimi K3.1 Pro ranks by benchmark score:
We keep what you type here, drafts included, for 180 days, and after that only the job and requirements read from it. Nothing is tied to your IP address or account. Leave out names and other personal details. Privacy
Category score record
Scores and ranks appear only where published evidence can be displayed. The table keeps the score, weight, cohort, and evidence state together.
| Category | Score | Rank | Percentile | Weight | Benchmarks | Evidence |
|---|---|---|---|---|---|---|
| AgenticRank #21 of 140Percentile 86thWeight 22%19 benchmarksMixed sources | 65.1 | 19 benchmarks | Mixed sources | |||
| CodingRank #23 of 163Percentile 86thWeight 20%18 benchmarksVerified | 56.3 | 18 benchmarks | Verified | |||
| ReasoningRank #21 of 161Percentile 88thWeight 17%2 benchmarksVerified | 65.4 | 2 benchmarks | Verified | |||
| MultimodalRank #19 of 67Percentile 73rdWeight 12%14 benchmarksVerified | 66.7 | 14 benchmarks | Verified | |||
| KnowledgeRank #20 of 181Percentile 89thWeight 12%6 benchmarksVerified | 67.5 | 6 benchmarks | Verified | |||
| MultilingualWeight 7%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| Inst. FollowingWeight 5%1 benchmarkVerified | Score pending | 1 benchmark | Verified | |||
| MathWeight 5%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured |
77 of 922 tracked benchmark slots have displayable evidence · bars run 0–100
Coverage detailsHow much of this is verified
Coverage is split by category so a strong number never hides a thin evidence base. Verified means the row is tied to a published source; provisional rows remain visible but separate.
- Agentic16/19 verified
- Coding18/18 verified
- Reasoning2/2 verified
- Multimodal14/14 verified
- Knowledge6/6 verified
- MultilingualNot measured
- Inst. Following1/1 verified
- MathNot measured
Capability shape
Each axis shows percentile within that category’s eligible cohort. The comparison outline is the median of the six nearest public-score peers; a collapsed vertex means the category is not rank-eligible.
Kimi K3 category percentile values
- Agentic86th percentile
- Coding86th percentile
- Reasoning88th percentile
- Multimodal73rd percentile
- Knowledge89th percentile
- MultilingualNot eligible
- Instruction followingNot eligible
- MathNot eligible
The dashed outline is median of 6 nearest peers.
Eligible category ranks
- Agentic#21/140
- Coding#23/163
- Reasoning#21/161
- Multimodal#19/67
- Knowledge#20/181
- MultilingualNot ranked
- Inst. FollowingNot ranked
- MathNot ranked
Benchmark ledger
Every result says who ran the test. For this model, Moonshot AI ran 34 of 77. Coding opens by default. The tick marks the best source-verified result in the catalog; provisional leaders do not set the reference.
Coding18 rows
| Benchmark | Score | Versus best verified row | Gap | Who ran it | Use in ranking |
|---|---|---|---|---|---|
| FrontierSWE v2 | 25.9% | Best verified: Claude Fable 5.2 · 69.9% | Gap44 behind | Run by FrontierSWE v2 | Counts8% ref. weight |
| LiveCodeBench (Vals)LiveCodeBench, Vals AI run | 87.2% | Best verified: Claude Fable 5.1 · 90.5% | Gap3.3 behind | Independent run: Vals AI | Counts8% ref. weight |
| FrontierCode 2.0 | 18.9% | Best verified: Claude Fable 5.2 · 50.2% | Gap31.3 behind | Run by FrontierCode 2.0 | Counts4% ref. weight |
| DeepSWE | 67.5% | Best verified: Muse Wonder Full · 79.0% | Gap11.5 behind | Reported by Moonshot AI | Shown only |
| ScarfBenchScarfBench: Cross-Framework Application Migration in Enterprise Java | 61.3% | Best verified: Gemini 4 Argon · 75.2% | Gap13.9 behind | Run by ScarfBench | Shown only |
| CursorBench 3.2 | 60.8% | Best verified: Claude Fable 5.1 · 73.4% | Gap12.6 behind | Run by CursorBench 3.2 | Shown only |
| FrontierSWE | 81.2% | Best verified: Kimi K3 · 81.2% | GapHighest listed | Reported by Moonshot AI | Shown only |
| ProgramBenchProgramBench: Can Language Models Rebuild Programs From Scratch? | 77.8% | Best verified: Claude Opus 5 · 93.0% | Gap15.2 behind | Reported by Moonshot AI | Shown only |
| Kimi Code Bench v2 | 72.9% | Best verified: Kimi K3.1 Pro · 77.1% | Gap4.2 behind | Reported by Moonshot AI | Shown only |
| sweMarathon | 42% | Best verified: Step 5 Preview · 72.7% | Gap30.7 behind | Reported by Moonshot AI | Shown only |
| PostTrainBench (lab runs)PostTrainBench lab-run results with no stated version | 36.6% | Best verified: GLM-5.3 · 39.8% | Gap3.2 behind | Reported by Moonshot AI | Shown only |
| MLS-Bench Lite | 48.3% | Best verified: Kimi K3 · 48.3% | GapHighest listed | Reported by Moonshot AI | Shown only |
| VulcanBench v3 | 73.7% | Best verified: Grok 4.5 · 89.9% | Gap16.2 behind | Run by VulcanBench v3 | Shown only |
| OpenHarmony Bench v1.0 | 57.3% | Best verified: Qwen3.8 Max · 60.8% | Gap3.5 behind | Run by OpenHarmony Bench v1.0 | Shown only |
| SWE-bench (Vals)SWE-bench, Vals AI run | 93.4% | Best verified: Claude Opus 5 · 97.0% | Gap3.6 behind | Independent run: Vals AI | Shown only |
| PostTrainBench v1.1 | 32.0% | Best verified: Claude Opus 5.5 · 49.3% | Gap17.3 behind | Run by PostTrainBench v1.1 | Shown only |
| Bug Hunt Bench | 21.0 fixes | Best verified: Claude Fable 5.2 · 58.0 fixes | Gap37 behind | Run by Bug Hunt Bench | Shown only |
| PostTrainBenchPostTrainBench v1.2 | 31.5% | Best verified: Claude Opus 5.5 · 43.8% | Gap12.3 behind | Run by PostTrainBench | Shown only |
Agentic19 rows
| Benchmark | Score | Versus best verified row | Gap | Who ran it | Use in ranking |
|---|---|---|---|---|---|
| Terminal-Bench 4.1 | 23.00% | Best verified: Claude Fable 5.2 · 65.80% | Gap42.8 behind | Run by Terminal-Bench 4.1 | Counts9% ref. weight |
| Terminal-Bench 2.1 | 88.3% | Best verified: SWE-2 · 92.8% | Gap4.5 behind | Reported by Moonshot AI | Counts9% ref. weight |
| BrowseComp | 91.2% | Best verified: Atria Dawn Preview · 92.5% | Gap1.3 behind | Reported by Moonshot AI | Counts9% ref. weight |
| Terminal-Bench 2.1 (Vals)Terminal-Bench 2.1, Vals AI run | 80.9% | Best verified: Claude Opus 5.5 · 87.6% | Gap6.7 behind | Independent run: Vals AI | Counts4% ref. weight |
| AutomationBench | 30.8% | Best verified: MiniMax M3.1 Flash · 62.2% | Gap31.4 behind | Reported by Moonshot AI | Shown only |
| JobBench | 52.9% | Best verified: Muse Wonder Full · 75.3% | Gap22.4 behind | Reported by Moonshot AI | Shown only |
| MCP Atlas | 84.2% | Best verified: Muse Spark Open · 89.2% | Gap5 behind | Reported by Moonshot AI | Shown only |
| Toolathlon-Verified | 73.2% | Best verified: Claude Opus 5 · 80.6% | Gap7.4 behind | Reported by Moonshot AI | Shown only |
| DeepSearchQA | 95.0% | Best verified: Atria Dawn Preview · 96.0% | Gap1 behind | Reported by Moonshot AI | Shown only |
| FinchFinch (FinWorkBench): Finance & Accounting across Spreadsheet-Centric Enterprise Workflows | 77.3% | Best verified: Mistral Large 4 · 73.3% | Gap4 behind | Reported by a third party | Shown only |
| b3 Agent Securityb3: Backbone Breaker Benchmark | 88.0% | Best verified: Mistral Large 4 · 97.1% | Gap9.1 behind | Reported by a third party | Shown only |
| Cyber Misuse RefusalRefusal of harmful cyber requests (JailbreakBench, StrongREJECT, AgentHarm) | 94.0% | Best verified: Mistral Large 4 · 96.6% | Gap2.6 behind | Reported by a third party | Shown only |
| APEX-Agents | 37.6% | Best verified: Hy4 · 75.2% | Gap37.6 behind | Reported by Moonshot AI | Shown only |
| SpreadsheetBench 2 | 34.8% | Best verified: ERNIE 5.5 Flash Preview · 36.4% | Gap1.6 behind | Reported by Moonshot AI | Shown only |
| DECK-BenchDECK-Bench (Internal) | 73.5% | Best verified: Kimi K3 · 73.5% | GapHighest listed | Reported by Moonshot AI | Shown only |
| ApprenticeBenchApprenticeBench: end-to-end computer use, continual learning, and long-horizon agency on a real accounts-payable job | 18% | Best verified: Claude Fable 5.1 · 72% | Gap54 behind | Run by ApprenticeBench | Shown only |
| Hermes IndexHermes Index: agentic capability and cost per task inside Hermes Agent | 39.2% | Best verified: Claude Opus 5.5 · 63.3% | Gap24.2 behind | Run by Hermes Index | Shown only |
| Hermes BenchHermes Bench: 150 agent tasks graded on the files and state the agent leaves behind | 71.5% | Best verified: Claude Opus 5.5 · 76.7% | Gap5.2 behind | Run by Hermes Bench | Shown only |
| MazeBenchMazeBench: visual spatial reasoning in a 3D open world | 1% | Best verified: GPT-6 Astra · 24% | Gap23 behind | Run by MazeBench | Shown only |
Reasoning2 rows
| Benchmark | Score | Versus best verified row | Gap | Who ran it | Use in ranking |
|---|---|---|---|---|---|
| ARC-AGI-2Abstraction and Reasoning Corpus for AGI v2 | 60.4% | Best verified: GPT-6.2 Astra · 95.8% | Gap35.4 behind | Run by ARC-AGI-2 | Counts15% ref. weight |
| ARC-AGI-1ARC-AGI-1 Semi-Private Evaluation | 94.50% | Best verified: Claude Fable 5 · 98.50% | Gap4 behind | Run by ARC-AGI-1 | Shown only |
Multimodal14 rows
| Benchmark | Score | Versus best verified row | Gap | Who ran it | Use in ranking |
|---|---|---|---|---|---|
| MMMU-ProMassive Multi-discipline Multimodal Understanding Pro | 81.6% | Best verified: GPT-6.1 Terra · 85.5% | Gap3.9 behind | Reported by Moonshot AI | Counts28% ref. weight |
| OfficeQA Pro | 63.3% | Best verified: Claude Fable 5.2 · 72.9% | Gap9.6 behind | Reported by Moonshot AI | Counts19% ref. weight |
| CharXivCharXiv Reasoning | 91.3% | Best verified: Qwen3.8 Max · 93.5% | Gap2.2 behind | Reported by Moonshot AI | Counts16% ref. weight |
| CharXiv w/o toolsCharXiv Reasoning without tools | 84.8% | Best verified: Kimi K3.1 Pro · 89% | Gap4.2 behind | Reported by Moonshot AI | Shown only |
| ExtractBench (LlamaIndex)ExtractBench: schema-guided enterprise document extraction (LlamaIndex leaderboard) | 83.17% | Best verified: GPT-6.1 Sol · 95.31% | Gap12.1 behind | Run by ExtractBench (LlamaIndex) | Shown only |
| MMMU-Pro w/ PythonMMMU-Pro with Python | 83.4% | Best verified: Kimi K3.1 Pro · 90% | Gap6.6 behind | Reported by Moonshot AI | Shown only |
| MathVision | 94.3% | Best verified: Qwen3.8 Max · 95.2% | Gap0.9 behind | Reported by Moonshot AI | Shown only |
| MathVision w/ PythonMathVision with Python | 97.8% | Best verified: Kimi K3 · 97.8% | GapHighest listed | Reported by Moonshot AI | Shown only |
| BabyVision w/ PythonBabyVision with Python | 85.7% | Best verified: Kimi K3.1 Pro · 95.4% | Gap9.7 behind | Reported by Moonshot AI | Shown only |
| ZeroBench | 23.0% | Best verified: Muse Spark Open · 50.0% | Gap27 behind | Reported by Moonshot AI | Shown only |
| ZeroBench w/ PythonZeroBench_main with Python | 41.0% | Best verified: Kimi K3.1 Pro · 63.0% | Gap22 behind | Reported by Moonshot AI | Shown only |
| WorldVQA ForceAnswer | 51.0% | Best verified: Kimi K3 · 51.0% | GapHighest listed | Reported by Moonshot AI | Shown only |
| OmniDocBench | 91.1% | Best verified: Kimi K3 · 91.1% | GapHighest listed | Reported by Moonshot AI | Shown only |
| PerceptionBenchPerceptionBench (Internal) | 58.5% | Best verified: Kimi K3.1 Pro · 68.3% | Gap9.8 behind | Reported by Moonshot AI | Shown only |
Knowledge6 rows
| Benchmark | Score | Versus best verified row | Gap | Who ran it | Use in ranking |
|---|---|---|---|---|---|
| HLEHumanity's Last Exam | 56% | Best verified: Claude Fable 5.2 · 74.2% | Gap18.2 behind | Reported by Moonshot AI | Counts44% ref. weight |
| MMLU-Pro (Vals)MMLU-Pro, Vals AI run | 88.0% | Best verified: Claude Fable 5.1 · 92.4% | Gap4.4 behind | Independent run: Vals AI | Counts6% ref. weight |
| GPQAGraduate-Level Google-Proof Q&A | 93.5% | Best verified: GPT-6 Astra · 96% | Gap2.5 behind | Reported by Moonshot AI | Counts3% ref. weight |
| GPQA Diamond (Vals)GPQA Diamond, Vals AI run | 92.9% | Best verified: Gemini 3.1 Pro · 95.5% | Gap2.6 behind | Independent run: Vals AI | Counts2% ref. weight |
| HLE w/o toolsHumanity's Last Exam without tools | 43.5% | Best verified: Claude Fable 5.2 · 73.2% | Gap29.7 behind | Reported by Moonshot AI | Shown only |
| GPQA-DGPQA Diamond | 93.5% | Best verified: GPT-6 Astra · 96.0% | Gap2.5 behind | Reported by Moonshot AI | Shown only |
Inst. Following1 row
| Benchmark | Score | Versus best verified row | Gap | Who ran it | Use in ranking |
|---|---|---|---|---|---|
| Gray Swan IPI (15 attempts)Gray Swan Indirect Prompt Injection, attack success at 15 attempts | 52.7% | Best verified: Gemini 4 Carbon · 0.0% | Gap52.7 behind | Lab-reported, from another publisher’s document | Shown only |
External signals17 rows
| Benchmark | Score | Versus best verified row | Gap | Who ran it | Use in ranking |
|---|---|---|---|---|---|
| ASCII Arena | 1301 | Best verified: Gemini 4 Carbon · 2020 | Gap719 behind | Run by ASCII Arena | Shown only |
| Pelican Arena | 1496 | Best verified: GPT-6 Astra · 1817 | Gap321 behind | Run by Pelican Arena | Shown only |
| FrontierPhysicsEnd-to-End Physics Research Benchmark for AI Agents | 2.4% | Best verified: Claude Opus 5.5 · 27.4% | Gap25 behind | Run by FrontierPhysics | Shown only |
| NYT ConnectionsNYT Connections LLM Benchmark (extended version) | 93.6% | Best verified: Gemini 4 Carbon · 99.3% | Gap5.7 behind | Run by NYT Connections | Shown only |
| Landing Page Arena | 1564 | Best verified: GPT-6.1 Sol · 1695 | Gap131 behind | Run by Landing Page Arena | Shown only |
| Code2Video | 1481 | Best verified: Claude Opus 5.5 · 1585 | Gap104 behind | Run by Code2Video | Shown only |
| StealthMarkStealthMark Intelligence Benchmarks (overall score) | 50.6 | Best verified: GPT-6 Astra · 74.6 | Gap24 behind | Run by StealthMark | Shown only |
| BabaIsBenchBabaIsBench (Baba Is You intro levels, pass@1) | 96% | Best verified: Claude Opus 5 · 100% | Gap4 behind | Run by BabaIsBench | Shown only |
| ExploitBenchExploitBench v8-bench | 32% | Best verified: GPT-6 Astra · 100% | Gap68 behind | Run by ExploitBench | Shown only |
| ACE solvedACE Cyber Range Challenges Solved | 0% | Best verified: Kimi K3 · 0% | GapBest verified | Run by ACE solved | Shown only |
| The Last Ones stepsThe Last Ones Average Progress | 17% | Best verified: Kimi K3 · 17% | GapBest verified | Run by The Last Ones steps | Shown only |
| The Last Ones completionThe Last Ones Cyber Range Completion Rate | 10% | Best verified: GPT-5.6 Sol · 70% | Gap60 behind | Run by The Last Ones completion | Shown only |
| Chess PuzzlesChess Puzzles (Epoch AI) | 36.0% | Best verified: Claude Fable 5.2 · 79.0% | Gap43 behind | Run by Chess Puzzles | Shown only |
| Mystery Game PuzzlesMystery Game Puzzles (Epoch AI) | 26.0% | Best verified: GPT-6.2 Astra · 95.0% | Gap69 behind | Run by Mystery Game Puzzles | Shown only |
| Furniture AssemblyFurniture Assembly Benchmark (Epoch AI) | 34.2% | Best verified: Claude Fable 5.2 · 90.0% | Gap55.8 behind | Run by Furniture Assembly | Shown only |
| Epoch Automation Reports | 52.4% | Best verified: Claude Fable 5.1 · 65.3% | Gap12.9 behind | Run by Epoch Automation Reports | Shown only |
| MirrorCodeMirrorCode (Epoch AI and METR) | 54.4% | Best verified: Claude Sonnet 5.5 · 97.8% | Gap43.4 behind | Run by MirrorCode | Shown only |
Outlined bars are lab-reported. Filled bars are benchmark-run or independent.
Scores by reasoning effort
Kimi K3 has published results at 3 reasoning effort settings on 3 benchmarks, from ARC Prize and Cognition. Each table is one benchmark run at every effort the publisher tested, with the cost it reported. BenchLM's score uses at most one setting per benchmark; these tables show the rest.
ARC-AGI-1 · Semi-Private set
From Low to Max effort, the score goes from 65.7% to 94.5% and the cost per task from $0.18 to $0.77.
| Effort | Score | Cost per task |
|---|---|---|
| Low | 65.7% | $0.18 |
| High | 86.7% | $0.48 |
| Maxtop score | 94.5% | $0.77 |
Source: ARC Prize.
ARC-AGI-2 · Semi-Private set
From Low to Max effort, the score goes from 12.4% to 60.4% and the cost per task from $0.25 to $1.59.
| Effort | Score | Cost per task |
|---|---|---|
| Low | 12.4% | $0.25 |
| High | 55.0% | $0.95 |
| Maxtop score | 60.4% | $1.59 |
Source: ARC Prize.
FrontierCode 2.0 · Devin CLI
From Low to Max effort, the score goes from 11.3% to 18.4% and the cost per task from $2.98 to $5.46. High scores highest, at 18.9% for $4.47 instead of $5.46.
| Effort | Score | Cost per task |
|---|---|---|
| Low | 11.3% | $2.98 |
| Hightop score | 18.9% | $4.47 |
| Max | 18.4% | $5.46 |
Source: Cognition. Cognition’s mean spend per rollout at list API prices.
Publisher scores and costs · display only, not part of the BenchLM score
How the score is builtWhat it costs to get this score
Published API price against the public score. The x-axis uses a log scale; the dashed path marks models that are not beaten by a cheaper, higher-scoring option. Price uses average of published input and output rates.
Kimi K3 · 67.0 score · $9 blended per million tokens
The chart opens on the current model. Scroll horizontally to inspect the full price axis.
Horizontal: blended price per million tokens, log scale · Vertical: public score
Lineage
The sequence follows explicit supersedes links. Each score is estimated for that model; a relative can inform a sparse estimate but never sets a floor, so a newer release can score below an earlier one. Scores and prices remain blank when the corresponding public row or first-party rate is unavailable.
Base entry
Spec sheet
Each documented value carries its source. Missing fields stay visible as not sourced or not published, rather than disappearing from the page.
- API model ID
- Not published
- Context window
- 1.05M
- Maximum output
- Not sourced yet
- Knowledge cutoff
- Not sourced yet
- Input modalities
- text, image, videoKimi-K3 model card
- Output modalities
- textKimi-K3 model card
- Parameters
- Not sourced yet
- Availability
- Not sourced yet
- Cloud regions
- Not tracked yet
- Lifecycle
- Superseded
- API capabilities
- Tool calling, structured outputs, and batch support are not tracked yet
- Prompt caching
- Published at $0.30 per million cached input tokens
- Self-host
- Kimi K3 needs ~2304GB VRAM (8× NVIDIA B300 (288GB)).
- Rate limits
- Not tracked yet
How to read this profile
The visual layer above carries the decisions. These notes preserve the model, ranking, coverage, and family context behind the numbers.
Kimi K3 ranks #20 of 218 on the public leaderboard with a score of 67/100. Its source-verified position is #11 of 79.
Kimi K3 is a open weight model with a 1.05M context window. It uses an explicit reasoning mode, which can improve complex problem solving while adding latency and token use.
Kimi K3 has cybersecurity benchmark results. The cybersecurity benchmark comparison shows them beside other models, one security job at a time, with the access route for restricted models.
Its explicit predecessor is Kimi K2.6. 77 of 922 tracked benchmark slots currently have displayable evidence. Missing categories stay blank.
Its strongest eligible category is Multimodal & Grounded at #19, while its lowest eligible position is Coding at #23. particularly strong for screenshots, documents, charts, and grounded multimodal workflows.
Last updated November 17, 2026. Runtime fields remain blank until a sourced snapshot exists.
Deployment options
Self-host and provider-specific paths stay separate from benchmark evidence so operating constraints are visible before a score becomes the whole decision.
Where to run Kimi K3 by API
7 hosts publish a per-token price for it. DeepInfra has the lowest output rate, $14.25 per million tokens. Prices read from each host’s own pages on November 16, 2026.
| Host | Input /1M | Output /1M | Cached /1M | Context | Listed speed |
|---|---|---|---|---|---|
| DeepInfra | $2.85 | $14.25 | $0.28 | 1.05M | — |
| Baseten | $3.00 | $15.00 | $0.30 | — | — |
| Fireworks AI | $3.00 | $15.00 | $0.30 | — | — |
| Nebius Token Factory | $3.00 | $15.00 | $0.30 | 1.05M | 264.55 tok/s |
| Novita AI | $3.00 | $15.00 | $0.30 | 1.05M | — |
| Together AI | $3.00 | $15.00 | $0.30 | 1.05M | — |
| OpenRouter | $0.19 | $16.00 | $0.18 | 1.05M | — |
Self-host vs API cost
Estimates at 50,000 req/day · 1000 tokens/req average.
Questions
How does Kimi K3 perform overall in AI benchmarks?
Kimi K3 ranks #20 out of 218 models on the public BenchAlign leaderboard, with a score of 67/100. Its evidence status is Supported, and this profile shows 77 source-displayable benchmark rows. The label describes evidence depth, not a provider quality claim; inspect category rows before choosing a workload.
Is Kimi K3 good for knowledge and understanding?
Kimi K3 ranks #20 out of 181 eligible models for knowledge and understanding, with a public category score of 67.5/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.
Is Kimi K3 good for coding and programming?
Kimi K3 ranks #23 out of 163 eligible models for coding and programming, with a public category score of 56.3/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.
Is Kimi K3 good for reasoning and logic?
Kimi K3 ranks #21 out of 161 eligible models for reasoning and logic, with a public category score of 65.4/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.
Is Kimi K3 good for agentic tool use and computer tasks?
Kimi K3 ranks #21 out of 140 eligible models for agentic tool use and computer tasks, with a public category score of 65.1/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.
Is Kimi K3 good for multimodal and grounded tasks?
Kimi K3 ranks #19 out of 67 eligible models for multimodal and grounded tasks, with a public category score of 66.7/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.
Is Kimi K3 good for instruction following?
Kimi K3 has source-displayable benchmark coverage for instruction following, but the public category table does not assign it a rank there. The individual rows remain available for inspection. A missing category position means the evidence threshold was not met; it does not convert the model's unmeasured work into a zero.
Is Kimi K3 open source?
Kimi K3 is an open-weight model from Moonshot AI. Its weights can be downloaded for local or hosted deployment, subject to the published license. Open weight does not automatically mean open source: training data and training code may remain private, and commercial restrictions can still apply.
Does Kimi K3 have full benchmark coverage on BenchLM?
No. Kimi K3 currently has 102 source-displayable rows. The profile exposes published, non-generated evidence and leaves missing categories blank until an exact evaluation is available. Coverage describes how much was measured; it is not a penalty added to an individual benchmark result.
What is the context window size of Kimi K3?
Kimi K3 has a reported context window of 1.05M in the exact-model catalog record. The value stays visible, but the profile marks its source link as unavailable instead of presenting it as directly documented. Maximum output length remains separate because providers often publish a different limit.