Data as of October 17, 2026 · How the score is built
Released Jul 11, 2025128K context
Kimi K2
Decision readingKimi K2 scores 33.5 out of 100 and ranks #168 of 224. This profile shows 13 source-displayable benchmark rows; its strongest eligible category is Instruction Following at #96. API pricing is $0.6 input and $2.5 output per million tokens.
Released Jul 11, 2025 — see all recent releases
Decision snapshot
Each value carries a field reference instead of floating alone. Markers compare this model with the current ranked and priced catalog; they are not absolute quality thresholds.
Capability
33.5/100
field median 49.6#168 of 224 ranked models
Public
#168of 224
Verified —
Price
$0.60input / $2.50 output
input median $0.75blended $1.55
Speed
54tok/s
field median 92 tok/sFirst token 1.49 s
Context
128Ktokens
field median 256,000Reported for this model; direct source link not stored
Strongest published evidence
Instruction Following ranks #96. A well-rounded choice across a range of tasks.
Validate before choosing
13 published rows leave some tracked benchmark slots empty. Knowledge is its lowest eligible category at #129.
Source-linked · 13 displayable benchmark rows
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 |
|---|---|---|---|---|---|---|
| AgenticWeight 22%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| CodingRank Not rankedWeight 20%3 benchmarksVerified | 40.8 | 3 benchmarks | Verified | |||
| ReasoningWeight 17%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| MultimodalWeight 12%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| KnowledgeRank #129 of 184Percentile 30thWeight 12%6 benchmarksVerified | 36.1 | 6 benchmarks | Verified | |||
| MultilingualWeight 7%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| Inst. FollowingRank #96 of 148Percentile 35thWeight 5%1 benchmarkVerified | 48.4 | 1 benchmark | Verified | |||
| MathRank #12 of 12Percentile 0thWeight 5%3 benchmarksVerified | 0.0 | 3 benchmarks | Verified |
13 of 681 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.
- AgenticNot measured
- Coding3/3 verified
- ReasoningNot measured
- MultimodalNot measured
- Knowledge6/6 verified
- MultilingualNot measured
- Inst. Following1/1 verified
- Math3/3 verified
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 K2 category percentile values
- AgenticNot eligible
- CodingNot eligible
- ReasoningNot eligible
- MultimodalNot eligible
- Knowledge30th percentile
- MultilingualNot eligible
- Instruction following35th percentile
- Math0th percentile
The dashed outline is median of 6 nearest peers.
Eligible category ranks
- AgenticNot ranked
- CodingNot ranked
- ReasoningNot ranked
- MultimodalNot ranked
- Knowledge#129/184
- MultilingualNot ranked
- Inst. Following#96/148
- Math#12/12
Benchmark ledger
Coding opens by default. The marker compares each value with the best source-verified result in the catalog; provisional leaders do not set the reference. Expand the remaining categories for every published row.
Coding3 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| SWE Multilingual | Score47.3% | Versus best verified row Best verified: Claude Opus 5.5 · 93.9% | Gap46.6 behind | Weight5% ref. weight | Provider exact |
| SWE-bench VerifiedSoftware Engineering Benchmark Verified | Score65.8% | Versus best verified row Best verified: Claude Opus 5 · 96% | Gap30.2 behind | WeightDisplay only | Provider exact |
| LiveCodeBench v6 | Score53.7% | Versus best verified row Best verified: Sakana Fugu-Ultra · 93.2% | Gap39.5 behind | WeightDisplay only | Provider exact |
Knowledge6 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| HLEHumanity's Last Exam | Score4.7% | Versus best verified row Best verified: Claude Fable 5.1 · 65% | Gap60.3 behind | Weight44% ref. weight | Provider exact |
| MMLU-ProMassive Multitask Language Understanding Professional | Score81.1% | Versus best verified row Best verified: Qwen3.7 Max · 89.6% | Gap8.5 behind | Weight6% ref. weight | Provider exact |
| GPQAGraduate-Level Google-Proof Q&A | Score75.1% | Versus best verified row Best verified: GPT-6 Astra · 96% | Gap20.9 behind | Weight3% ref. weight | Provider exact |
| SuperGPQASuperGPQA: Scaling LLM Evaluation Across 285 Graduate Disciplines | Score57.2% | Versus best verified row Best verified: Qwen 3.6 Max (preview) · 73.9% | Gap16.7 behind | Weight2% ref. weight | Provider exact |
| MMLUMassive Multitask Language Understanding | Score89.5% | Versus best verified row Best verified: o1 · 91.8% | Gap2.3 behind | WeightDisplay only | Provider exact |
| SimpleQAMeasuring Short-Form Factuality in Large Language Models | Score31% | Versus best verified row Best verified: GPT-4.5 · 62.5% | Gap31.5 behind | WeightDisplay only | Provider exact |
Inst. Following1 row
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| IFEvalInstruction-Following Eval | Score89.8% | Versus best verified row Best verified: LFM2.5-24B-A2B · 96.8% | Gap7 behind | WeightDisplay only | Provider exact |
Math3 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| AIME 2024American Invitational Mathematics Examination 2024 | Score69.6% | Versus best verified row Best verified: GPT-OSS 120B · 95.8% | Gap26.2 behind | WeightDisplay only | Provider exact |
| AIME 2025American Invitational Mathematics Examination 2025 | Score49.5% | Versus best verified row Best verified: GPT-5.2 · 100% | Gap50.5 behind | WeightDisplay only | Provider exact |
| MATH-500MATH-500 Problem Set | Score97.4% | Versus best verified row Best verified: Ternary Bonsai 2 27B · 98.8% | Gap1.4 behind | WeightDisplay only | Provider exact |
Bars run 0–100; the dark tick marks the best source-verified value
All 13 rowsWhat 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 K2 · 33.5 score · $1.55 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
- 128K
- Maximum output
- Not sourced yet
- Knowledge cutoff
- Not sourced yet
- Input modalities
- Not sourced yet
- Output modalities
- Not sourced yet
- Parameters
- Not disclosed by the provider
- Availability
- Not sourced yet
- Cloud regions
- Not tracked yet
- Lifecycle
- Established
- API capabilities
- Tool calling, structured outputs, and batch support are not tracked yet
- Prompt caching
- Not documented in the pricing record
- Self-host
- Weights are not published
- 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 K2 ranks #168 of 224 on the public leaderboard with a score of 33.48/100. It does not yet have enough sourced coverage for a verified position.
Kimi K2 is a proprietary model with a 128K context window. No explicit reasoning mode is documented in this profile.
13 of 681 tracked benchmark slots currently have displayable evidence. Missing categories stay blank.
Its strongest eligible category is Instruction Following at #96, while its lowest eligible position is Knowledge at #129. a well-rounded choice across a range of tasks.
Last updated October 17, 2026. Runtime fields remain blank until a sourced snapshot exists.
Questions
How does Kimi K2 perform overall in AI benchmarks?
Kimi K2 ranks #168 out of 224 models on the public BenchAlign leaderboard, with a score of 33.48/100. Its evidence status is Estimated, and this profile shows 13 source-displayable benchmark rows. The label describes evidence depth, not a provider quality claim; inspect category rows before choosing a workload.
Is Kimi K2 good for knowledge and understanding?
Kimi K2 ranks #129 out of 184 eligible models for knowledge and understanding, with a public category score of 36.1/100. 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 K2 good for coding and programming?
Kimi K2 has source-displayable benchmark coverage for coding and programming, 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 K2 good for mathematics?
Kimi K2 ranks #12 out of 12 eligible models for mathematics, with a public category score of 0/100. 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 K2 good for instruction following?
Kimi K2 ranks #96 out of 148 eligible models for instruction following, with a public category score of 48.4/100. 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.
Does Kimi K2 have full benchmark coverage on BenchLM?
No. Kimi K2 currently has 24 source-displayable rows across 681 tracked benchmark slots. 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 K2?
Kimi K2 has a reported context window of 128K 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.