Skip to main content

Model profile

Kimi 3

Moonshot AICurrentReleased Jul 14, 2026
Data verified
Overall Score
Coming soon
Arena Elo
Not listed
Categories Ranked
0of 8
Price (1M tokens)
Not listedAPI pricing
Speed
Not listed
Context
Not listed

Evidence coverage

0 of 296 tracked benchmarks are published. 0 are verified and 0 provisional. 0 of 8 categories are measured.

Updated July 14, 2026Methodology
Published / tracked
0 / 296
Verified
0
Provisional
0
Categories measured
0 / 8

Evidence by category

  • Agentic0 benchmarks
    Not measured
  • Coding0 benchmarks
    Not measured
  • Reasoning0 benchmarks
    Not measured
  • Knowledge0 benchmarks
    Not measured
  • Math0 benchmarks
    Not measured
  • Multilingual0 benchmarks
    Not measured
  • Multimodal0 benchmarks
    Not measured
  • Inst. Following0 benchmarks
    Not measured
PendingPending
Confidence:
Low
base

BenchLM is tracking Kimi 3, but sourced benchmark results are not published on the site yet. This page currently shows the model metadata we can verify now, and score-level benchmark coverage will appear once public evaluations land.

Kimi 3's weight availability, context window, and reasoning mode have not been published in a source we can verify yet.

This profile does not yet have sourced benchmarks on BenchLM, so the benchmark sections below are intentionally marked as coming soon.

Peer position

Exact provisional scores and ranks for the closest listed peers.

  1. Kimi 3Current model
    Moonshot AI
    Unranked0.0
    Kimi 3 is Unranked with a score of 0.0.
  2. Agents-A1-F16-GGUF
    InternScience
    Unranked0.0
    Agents-A1-F16-GGUF is Unranked with a score of 0.0.
    Compare
  3. Agents-A1-FP8
    InternScience
    Unranked0.0
    Agents-A1-FP8 is Unranked with a score of 0.0.
    Compare
  4. Agents-A1-Q4_K_M-GGUF
    InternScience
    Unranked0.0
    Agents-A1-Q4_K_M-GGUF is Unranked with a score of 0.0.
    Compare
  5. Agents-A1-Q8_0-GGUF
    InternScience
    Unranked0.0
    Agents-A1-Q8_0-GGUF is Unranked with a score of 0.0.
    Compare
  6. Claude Haiku 4.5 Thinking
    Anthropic
    Unranked0.0
    Claude Haiku 4.5 Thinking is Unranked with a score of 0.0.
    Compare
  7. Claude Sonnet 4.5 Thinking
    Anthropic
    Unranked0.0
    Claude Sonnet 4.5 Thinking is Unranked with a score of 0.0.
    Compare

Benchmark data coming soon

BenchLM has created this model profile, but no sourced benchmark rows are published here yet. Category charts, rankings, and score tables will appear after public evaluations are available and attached to source records.

Category evidence

Scores and ranks appear only where this model has published benchmark evidence. Categories without displayable source records remain not measured.

Category scores, ranks, weighting, benchmark coverage, and evidence status
CategoryScore
AgenticWeight 22%0 benchmarksNot measuredNot measured
CodingWeight 20%0 benchmarksNot measuredNot measured
ReasoningWeight 17%0 benchmarksNot measuredNot measured
KnowledgeWeight 12%0 benchmarksNot measuredNot measured
MathWeight 5%0 benchmarksNot measuredNot measured
MultilingualWeight 7%0 benchmarksNot measuredNot measured
MultimodalWeight 12%0 benchmarksNot measuredNot measured
Inst. FollowingWeight 5%0 benchmarksNot measuredNot measured

Frequently Asked Questions

How does Kimi 3 perform overall in AI benchmarks?

BenchLM is tracking Kimi 3, but sourced benchmark coverage is still coming soon. We currently list its creator, model type, and context window while we wait for public benchmark results.

Does Kimi 3 have full benchmark coverage on BenchLM?

Not yet. Kimi 3 currently has 0 published benchmark scores out of the 296 benchmarks BenchLM tracks. BenchLM only exposes non-generated public benchmark rows, so missing categories stay blank until a sourced evaluation is available.

What is the context window size of Kimi 3?

Kimi 3 has a context window of null, which determines how much text it can process in a single interaction.

Last updated: July 14, 2026 · Runtime metrics stay blank until BenchLM has a sourced snapshot.

Don't miss the next GPT moment

Which models moved up, what is new, and what it costs. One email each week.

Free. One email per week.