Moonshot AILanguage model
Kimi K2
Kimi K2 has no overall index value yet because there are too few independent benchmark results.
Intelligencenot ranked yet
n/aOverall indexhigher is better
SpeedRank 94 of 101
37Tokens per secondhigher is better
Priceno API price
n/aper 1M tokenslower is better
ContextRank 94 of 103
131Ktokens at once≈ 200 A4 pages
PopularityRank 406 of 785
35out of 100-2 vs. last month
based on two data groups, mostly search
Summary
At 37 tokens per second it writes slower than a typical model (87).
Kimi K2 is Moonshot’s open K2 Instruct release. The repository describes 1 trillion total parameters, 32 billion active parameters, and about 131,000 tokens of context. This entry represents the foundational K2 Instruct release.
The dated checkpoints Kimi K2 0711 and Kimi K2 0905 remain separate model identities. Moonshot has discontinued the K2 API series; the open weights and external deployments are separate from that service.
All benchmark results
Every published result with its source, test setup and comparison models.
Show all 45 published benchmark results
Page 1 of 4
Measurements without matching peer values
These measurements have no matching peer values under the same test conditions. Their original values and sources remain available here.
CritPt v2: Overall (Show measurement, test conditions, and source)
- Source value
- 0
- Score
- 0
- Metric
- pass@1 accuracy
- Unit
- %
- Benchmark version
- v2
- Category
- reasoning
- Task
- overall
- Task label
- Overall
- Direction
- Higher is better
- Source type
- independent-evaluator
- Evaluator
- Artificial Analysis
- Status
- disputed
- Retrieved at
- 2026-11-02
- Methodology
- Exact AA configuration: Kimi K2 (release kimi-k2, row kimi-k2, UUID 441734a9-8901-4850-9bae-b474c370291f, reasoning=false, effort=not specified, suffix=not specified). AA marks this model variant as non-reasoning and reports 0 reasoning tokens. The full CritPt v2 run covers 70 questions with five repeats. The official grading server reports pass@1.. Source model ID: artificial-analysis/441734a9-8901-4850-9bae-b474c370291f/kimi-k2/kimi-k2. Source model name: Kimi K2. Provider reported by source: Kimi. Model snapshot: Kimi K2. Evaluator: Artificial Analysis. Dataset type: artificial-analysis-evaluation. Tool policy: Python functions, symbolic expressions, and numerical answers; official grading server. Attempts: 70 questions, five repeats per question, pass@1. Reasoning: non-reasoning. Reasoning effort: none. Score display: 0.0%. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-11-02-67d46be20a5b. Source payload hash: 67d46be20a5b412db6cfb60ad190441fcaa5513500b8fd47d033168d0e97b6b2. Parser version: artificial-analysis-rsc-models-v3. Imported at: 2026-11-02. Source cohort: artificial-analysis-critpt-v2:v2:standalone:non-reasoning:effort=unspecified:suffix=unspecified
- Comparison methodology
- Exact AA configuration: Kimi K2 (release kimi-k2, row kimi-k2, UUID 441734a9-8901-4850-9bae-b474c370291f, reasoning=false, effort=not specified, suffix=not specified). AA marks this model variant as non-reasoning and reports 0 reasoning tokens. The full CritPt v2 run covers 70 questions with five repeats. The official grading server reports pass@1.. Tool policy: Python functions, symbolic expressions, and numerical answers; official grading server. Attempts: 70 questions, five repeats per question, pass@1. Reasoning: non-reasoning. Reasoning effort: none
- Context
- This AA source field contains the original CritPt score. The earlier CritPt v2 attribution was incorrect; the value and former label remain as disputed historical evidence.. The source dataset marks this result as disputed. It remains visible as documented evidence, but is not reliable comparative proof.
IFBench: Overall (Show measurement, test conditions, and source)
- Source value
- 41.4965986394558
- Score
- 41.4965986394558
- Metric
- IFBench prompt-level loose accuracy (pass@1)
- Unit
- %
- Benchmark version
- AA test set: 294 questions
- Category
- general
- Task
- overall
- Task label
- Overall
- Direction
- Higher is better
- Source type
- independent-evaluator
- Evaluator
- Artificial Analysis
- Status
- superseded
- Retrieved at
- 2026-11-02
- Methodology
- Exact AA configuration: Kimi K2 (release kimi-k2, row kimi-k2, UUID 441734a9-8901-4850-9bae-b474c370291f, reasoning=false, effort=not specified, suffix=not specified). AA marks this model variant as non-reasoning and reports 0 reasoning tokens. Artificial Analysis runs 294 questions from the IFBench test set with five repeats per question. The official evaluator scores prompt-level accuracy in loose mode as pass@1.. Source model ID: artificial-analysis/441734a9-8901-4850-9bae-b474c370291f/kimi-k2/kimi-k2. Source model name: Kimi K2. Provider reported by source: Kimi. Model snapshot: Kimi K2. Evaluator: Artificial Analysis. Dataset type: artificial-analysis-evaluation. Tool policy: Single-turn answer evaluated with the official IFBench source code. Attempts: pass@1, 5 repeats per question. Reasoning: non-reasoning. Reasoning effort: none. Score display: 41.5%. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-11-02-67d46be20a5b. Source payload hash: 67d46be20a5b412db6cfb60ad190441fcaa5513500b8fd47d033168d0e97b6b2. Parser version: artificial-analysis-rsc-models-v3. Imported at: 2026-11-02. Source cohort: artificial-analysis-ifbench:AA test set: 294 questions:standalone:non-reasoning:effort=unspecified:suffix=unspecified
- Comparison methodology
- Exact AA configuration: Kimi K2 (release kimi-k2, row kimi-k2, UUID 441734a9-8901-4850-9bae-b474c370291f, reasoning=false, effort=not specified, suffix=not specified). AA marks this model variant as non-reasoning and reports 0 reasoning tokens. Artificial Analysis runs 294 questions from the IFBench test set with five repeats per question. The official evaluator scores prompt-level accuracy in loose mode as pass@1.. Tool policy: Single-turn answer evaluated with the official IFBench source code. Attempts: pass@1, 5 repeats per question. Reasoning: non-reasoning. Reasoning effort: none
- Context
- The often cited 58 refers to verifiable out-of-domain constraint types, not the number of questions in AA's test run.. This result is retained as historical evidence and is not interchangeable with current results.
IFBench: Overall (Show measurement, test conditions, and source)
- Source value
- 41.4965986394558
- Score
- 41.4965986394558
- Metric
- IFBench prompt-level loose accuracy (pass@1)
- Unit
- %
- Benchmark version
- AA test set: 294 questions
- Category
- general
- Task
- overall
- Task label
- Overall
- Direction
- Higher is better
- Source type
- independent-evaluator
- Evaluator
- Artificial Analysis
- Status
- active
- Retrieved at
- 2026-11-07
- Methodology
- Exact AA configuration: Kimi K2 (release kimi-k2, row kimi-k2, UUID 441734a9-8901-4850-9bae-b474c370291f, reasoning=false, effort=not specified, suffix=not specified). This source capture does not provide an average reasoning-token count. Artificial Analysis runs 294 questions from the IFBench test set with five repeats per question. The official evaluator scores prompt-level accuracy in loose mode as pass@1.. Source model ID: artificial-analysis/441734a9-8901-4850-9bae-b474c370291f/kimi-k2/kimi-k2. Source model name: Kimi K2. Provider reported by source: Kimi. Model snapshot: Kimi K2. Evaluator: Artificial Analysis. Dataset type: artificial-analysis-evaluation. Tool policy: Single-turn answer evaluated with the official IFBench source code. Attempts: pass@1, 5 repeats per question. Reasoning: non-reasoning. Reasoning effort: none. Score display: 41.5%. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-11-07-b96e3ffc8c5b. Source payload hash: b96e3ffc8c5b052aa56f96d05e89d02b8cc234a75085820fca0ca2a39e498274. Parser version: artificial-analysis-rsc-models-v4. Imported at: 2026-11-07. Source cohort: artificial-analysis-ifbench:AA test set: 294 questions:standalone:non-reasoning:effort=unspecified:suffix=unspecified
- Comparison methodology
- Exact AA configuration: Kimi K2 (release kimi-k2, row kimi-k2, UUID 441734a9-8901-4850-9bae-b474c370291f, reasoning=false, effort=not specified, suffix=not specified). This source capture does not provide an average reasoning-token count. Artificial Analysis runs 294 questions from the IFBench test set with five repeats per question. The official evaluator scores prompt-level accuracy in loose mode as pass@1.. Tool policy: Single-turn answer evaluated with the official IFBench source code. Attempts: pass@1, 5 repeats per question. Reasoning: non-reasoning. Reasoning effort: none
- Context
- The often cited 58 refers to verifiable out-of-domain constraint types, not the number of questions in AA's test run.
MMLU (Show measurement, test conditions, and source)
- Source value
- 89.5
- Score
- 89.5
- Metric
- score as published
- Unit
- %
- Direction
- No direction published
- Source type
- vendor-reported
- Evaluator
- Kimi K2: Open Agentic Intelligence technical report (arXiv:2507.20534)
- Status
- active
- Retrieved at
- 2026-10-19
- Methodology
- Vendor-reported result. Exact Kimi-K2-Instruct result in the Moonshot technical report. The captured result does not state model-row N, a confidence interval, or any additional evaluation settings.
MMLU-Redux (Show measurement, test conditions, and source)
- Source value
- 92.7
- Score
- 92.7
- Metric
- EM
- Unit
- %
- Direction
- No direction published
- Source type
- vendor-reported
- Evaluator
- Kimi K2: Open Agentic Intelligence technical report (arXiv:2507.20534)
- Status
- active
- Retrieved at
- 2026-10-19
- Methodology
- Vendor-reported result. Exact Kimi-K2-Instruct result in the Moonshot technical report. The captured result does not state model-row N, a confidence interval, or any additional evaluation settings.
IFEval (Show measurement, test conditions, and source)
- Source value
- 89.8
- Score
- 89.8
- Metric
- Prompt Strict
- Unit
- %
- Direction
- No direction published
- Source type
- vendor-reported
- Evaluator
- Kimi K2: Open Agentic Intelligence technical report (arXiv:2507.20534)
- Status
- active
- Retrieved at
- 2026-10-19
- Methodology
- Vendor-reported result. Exact Kimi-K2-Instruct result in the Moonshot technical report. The captured result does not state model-row N, a confidence interval, or any additional evaluation settings.
Multi-Challenge (Show measurement, test conditions, and source)
- Source value
- 54.1
- Score
- 54.1
- Metric
- Acc.
- Unit
- %
- Direction
- No direction published
- Source type
- vendor-reported
- Evaluator
- Kimi K2: Open Agentic Intelligence technical report (arXiv:2507.20534)
- Status
- active
- Retrieved at
- 2026-10-19
- Methodology
- Vendor-reported result. Exact Kimi-K2-Instruct result in the Moonshot technical report. The captured result does not state model-row N, a confidence interval, or any additional evaluation settings.
SimpleQA (Show measurement, test conditions, and source)
- Source value
- 31
- Score
- 31
- Metric
- Correct
- Unit
- %
- Direction
- No direction published
- Source type
- vendor-reported
- Evaluator
- Kimi K2: Open Agentic Intelligence technical report (arXiv:2507.20534)
- Status
- active
- Retrieved at
- 2026-10-19
- Methodology
- Vendor-reported result. Exact Kimi-K2-Instruct result in the Moonshot technical report. The captured result does not state model-row N, a confidence interval, or any additional evaluation settings.
AIME 2024 (Show measurement, test conditions, and source)
- Source value
- 69.6
- Score
- 69.6
- Metric
- score as published
- Unit
- %
- Direction
- No direction published
- Source type
- vendor-reported
- Evaluator
- Kimi K2: Open Agentic Intelligence technical report (arXiv:2507.20534)
- Status
- active
- Retrieved at
- 2026-10-19
- Methodology
- Vendor-reported result. Exact Kimi-K2-Instruct result in the Moonshot technical report. The captured result does not state model-row N, a confidence interval, or any additional evaluation settings.
GPQA-Diamond (Show measurement, test conditions, and source)
- Source value
- 75.1
- Score
- 75.1
- Metric
- score as published
- Unit
- %
- Direction
- No direction published
- Source type
- vendor-reported
- Evaluator
- Kimi K2: Open Agentic Intelligence technical report (arXiv:2507.20534)
- Status
- active
- Retrieved at
- 2026-10-19
- Methodology
- Vendor-reported result. Exact Kimi-K2-Instruct result in the Moonshot technical report. The captured result does not state model-row N, a confidence interval, or any additional evaluation settings.
LiveBench (Show measurement, test conditions, and source)
- Source value
- 76.4
- Score
- 76.4
- Metric
- Pass@1
- Unit
- %
- Benchmark version
- 2024-11-25 snapshot
- Direction
- No direction published
- Source type
- vendor-reported
- Evaluator
- Kimi K2: Open Agentic Intelligence technical report (arXiv:2507.20534)
- Status
- active
- Retrieved at
- 2026-10-19
- Methodology
- Vendor-reported result. Exact Kimi-K2-Instruct result in the Moonshot technical report. The report labels this as the 2024-11-25 snapshot. The captured result does not state model-row N, a confidence interval, or any additional evaluation settings.
SWE-lancer (Show measurement, test conditions, and source)
- Source value
- 39.1
- Score
- 39.1
- Metric
- score as published
- Unit
- %
- Direction
- No direction published
- Source type
- vendor-reported
- Evaluator
- Kimi K2: Open Agentic Intelligence technical report (arXiv:2507.20534)
- Status
- active
- Retrieved at
- 2026-10-19
- Methodology
- Vendor-reported result. Exact Kimi-K2-Instruct result in the Moonshot technical report. The captured result does not state model-row N, a confidence interval, or any additional evaluation settings.
Page 1 of 4
Popularity compared
How often the model is searched for, used and mentioned, compared with every model of its category.
Popularity index
The 100 most popular models of this category, 0 to 100, higher is more popular
20 of 101 models
As of November 2026 · Source: gradually.ai popularity index
Over time
Weekly values from October 18, 2026 to November 7, 2026
Kimi K2Hermes 4 405B 35Kimi K2 0711 35StarCoder2 15B 35Amazon Nova Micro 35
Method changes in the timeline, a jump at these points is no market event:
- 1November 1, 2026: Value only with search or usage data, 30-day attention
What is gaining popularity right now, across models, vendors, harnesses and AI subscriptions, is collected in All AI trends.
Similar models
More models of the same kind as Kimi K2, chosen by model line, developer, size, price and release date.
- Kimi K2 0711Moonshot AI · same developer
- Kimi K2 0905Moonshot AI · same developer
- Kimi K2.5Moonshot AI · same developer
- Kimi K2 ThinkingMoonshot AI · same developer
- Kimi K2.6Moonshot AI · same developer
- Kimi K2 Thinking TurboMoonshot AI · same developer
- Kimi K2.7 CodeMoonshot AI · same developer
- Kimi K2.7 Code HighspeedMoonshot AI · same developer
All specifications
Architecture
Input and output
Watermarking and provenance
AI watermarking refers to invisible signals embedded in the output. Visible marks and provenance metadata are listed separately. Unknown means there is insufficient evidence for that particular field.
- AI watermarking
- Unknown
- no source
- Watermarking technique
- Not known
- no source
Licence and access
Frequently asked questions about Kimi K2
How large is the context window of Kimi K2?
131,072 tokens. That is how much text Kimi K2 reads at once, about 200 A4 pages.
Page count as a rule of thumb from Artificial Analysis
GLM-5.1200K
DeepSeek-V3 0324164K
Kimi K2Rank 94 of 103131K
GLM-4.5131K
GPT OSS 120B131K
DeepSeek-V3.2128K
DeepSeek-R1128K
How fast is Kimi K2?
37 tokens per second. That is slower than a typical model at 87.
Measured by Artificial Analysis on Nov 6, 2026. AA 3.0.0, including time to first token, averaged across available workloads and five days.
Kimi K339
Kimi K2Rank 94 of 10137
MiMo V2.6 Flash35
GLM-4.733
Kimi K3.1 Pro33
DeepSeek-V3.233
MiMo-V2.5-Pro33
Can I run Kimi K2 locally?
Yes, the weights are open. With 1T parameters it needs a lot of memory, more a server than a laptop.
Stated by Moonshot AI
- Open weights
- yes
- License
- Modified MIT
- Parameters
- 1T
- active per token
- 32B
Sources and data date
Show all 19 sources
Benchmark sources at a glance
Which independent evaluators tested this model. This is coverage, not a quality ranking.
| Evaluator | Test series | Composite indices | Recorded active measurements |
|---|---|---|---|
| Artificial Analysis | 1 | 0 | 1 |
| SWE-bench | 0 | 0 | 2 |
| Scale AI Evals | 0 | 0 | 1 |
Without vendor claims and historical or disputed results; those stay labelled in the single values. 3 measurements are not yet assigned to a test series.
| Type | Evidence and data date |
|---|---|
| Speed | Median across serving providers, Non-reasoning. AA 3.0.0, including time to first token, averaged across available workloads and five days. Retrieved November 6, 2026. |
| Input | Documented modalities. |
| Output | Documented modalities. |
| Research status | Research date October 15, 2026. 8 source URLs checked. This documents the inspected sources, not an exhaustive inventory of every publication. |
| Not published | metric-units-and-task-dates Note Moonshot supplies task/setup notes for SWE-bench and averaging setup, but most raw table values have no explicit unit and the report does not provide dates for each benchmark run. |
| Not found in the inspected sources | Kimi-K2-Instruct technical-report row settings and uncertainty Note The inspected report excerpts do not state per-row scored N, confidence intervals, or full inference settings for the accepted results; this is limited to the examined report evidence. |
| Additional source | Artificial Analysis (retrieved November 2, 2026) |
| Additional source | Artificial Analysis (retrieved November 2, 2026; November 7, 2026) |
| Additional source | Kimi K2: Open Agentic Intelligence technical report (arXiv:2507.20534) (retrieved October 19, 2026) |
| Additional source | Aider LLM Leaderboards (Polyglot) (retrieved October 28, 2026) |
| Additional source | SWE-bench official leaderboard (retrieved October 28, 2026) |
| Additional source | Scale SWE-Bench Pro public leaderboard (retrieved October 28, 2026) |
| Additional source | Model metadata (retrieved October 28, 2026)123 |
| Additional source | Kimi API model list · Editorial description reviewed October 2, 2026 |
| Additional source | OpenRouter: Popularity index (derived), CC BY 4.0 |
| Additional source | Vercel AI Gateway: Popularity index (derived), CC BY 4.0 |
| Additional source | Ollama: cumulative downloads for the popularity index |
| Additional source | Replicate: cumulative runs for the popularity index |
| Additional source | Google Trending Now: limited feed selection for Germany and the US |
| Additional source | Creative Commons Attribution 4.0 |