UnifyBench

RankingKimi K3

Kimi K3

Compare models

Data updated 22 Oct 2026

81 published benchmark measures · 14 benchmark families contribute across 5 task areas. 4 capability estimates available in the full profile. See all results ↓ · Compare published benchmarks →

Model evidence summary

This profile combines published settings. It is not a runnable configuration or a leaderboard rank. Compare measured configurations →

Performance profile

Capabilities

Adjusted comparison score · 0–100
Kimi K3 capability radarComparison scores from 0 to 100. Unknown capabilities have no point; lines stop at gaps. Hollow points are preliminary. Exact values and support labels follow the chart.AgenticHard reasoningCodingHuman prefKnowledgeMultimodalLong context50100Kimi K3 · Agentic: 85.2 · SupportedKimi K3 · Hard reasoning: 54.3 · SupportedKimi K3 · Coding: 74.9 · PreliminaryKimi K3 · Multimodal: 76.4 · Supported

Filled points are supported; hollow points are preliminary. Lines stop at unknown capabilities. Exact values and sources follow below.

Agentic7 families · 1 with independent evidence · Supported85.2

7 core families; 48 direct opponents across 16 labs.

Estimated against the same complete panel: gpt-5.6-sol claude-opus-4-8 gemini-3.1-pro . Indirect comparisons assume performance can be summarized by one strength within this capability.

Refit without one family: 75.0–87.4; 0/13 scenarios unsupported. Without one publisher: 78.9–89.0; 0/15 unsupported. Smoothing check: 77.2–89.1; 0/3 unsupported. These are sensitivity checks, not confidence intervals.

Audit: family and publisher holdouts improved on neutral predictions within evaluated coverage; source sensitivity still requires inspection. Validation audit.

Matched family win shares below describe source evidence; they are not averaged to produce the adjusted score.

Hard reasoning3 families · 2 with independent evidence · Supported54.3

3 core families; 63 direct opponents across 9 labs.

Estimated against the same complete panel: gpt-5.6-sol claude-opus-4-8 gemini-3.1-pro . Indirect comparisons assume performance can be summarized by one strength within this capability.

Refit without one family: 41.5–72.2; 0/6 scenarios unsupported. Without one publisher: 42.9–58.1; 0/16 unsupported. Smoothing check: 52.7–55.4; 0/3 unsupported. These are sensitivity checks, not confidence intervals.

Audit: family and publisher holdouts improved on neutral predictions within evaluated coverage. Validation audit.

Matched family win shares below describe source evidence; they are not averaged to produce the adjusted score.

Coding1 families · 1 with independent evidence · Preliminary74.9

1 core families; 27 direct opponents across 9 labs. Needs broader benchmark and opponent support

Estimated against the same complete panel: gpt-5.6-sol claude-opus-4-8 gemini-3.1-pro . Indirect comparisons assume performance can be summarized by one strength within this capability.

Refit without one family: No supported estimate; 6/6 scenarios unsupported. Without one publisher: No supported estimate; 19/19 unsupported. Smoothing check: No supported estimate; 3/3 unsupported. These are sensitivity checks, not confidence intervals.

Audit: family and publisher holdouts improved on neutral predictions within evaluated coverage. Validation audit.

Matched family win shares below describe source evidence; they are not averaged to produce the adjusted score.

Human pref1 families · 1 with independent evidence · PreliminaryUnknown

1 core families; 76 direct opponents across 16 labs. No connected comparison to the complete reference panel

Estimated against the same complete panel: gpt-5.6-sol claude-opus-4-8 gemini-3.1-pro . Indirect comparisons assume performance can be summarized by one strength within this capability.

Refit without one family: No supported estimate; 1/1 scenarios unsupported. Without one publisher: No supported estimate; 1/1 unsupported. Smoothing check: No supported estimate; 3/3 unsupported. These are sensitivity checks, not confidence intervals.

Audit: cross-family and cross-publisher predictions could not be evaluated from the available comparison network. Validation audit.

Matched family win shares below describe source evidence; they are not averaged to produce the adjusted score.

  • Human preference (Arena): 94.7 observed win share
    lmarena.ai · Source 1
KnowledgeNo comparable evidenceUnknown

0 core families; 0 direct opponents across 0 labs. No admitted core comparisons

Estimated against the same complete panel: gpt-5.6-sol claude-opus-4-8 gemini-3.1-pro . Indirect comparisons assume performance can be summarized by one strength within this capability.

Refit without one family: No supported estimate; 4/4 scenarios unsupported. Without one publisher: No supported estimate; 5/5 unsupported. Smoothing check: No supported estimate; 3/3 unsupported. These are sensitivity checks, not confidence intervals.

Audit: almost no publisher-held-out comparisons remained estimable. Cross-source validity is unresolved. Validation audit.

Matched family win shares below describe source evidence; they are not averaged to produce the adjusted score.

    Multimodal2 families · 0 with independent evidence · Supported76.4

    2 core families; 4 direct opponents across 2 labs.

    Estimated against the same complete panel: gpt-5.6-sol claude-opus-4-8 gemini-3.1-pro . Indirect comparisons assume performance can be summarized by one strength within this capability.

    Refit without one family: 75.4–77.8; 2/8 scenarios unsupported. Without one publisher: 75.1–79.1; 1/8 unsupported. Smoothing check: 70.8–79.1; 0/3 unsupported. These are sensitivity checks, not confidence intervals.

    Audit: limited publisher-held-out coverage. Cross-source validity is unresolved. Validation audit.

    Matched family win shares below describe source evidence; they are not averaged to produce the adjusted score.

    Long contextNo comparable evidenceUnknown

    0 core families; 0 direct opponents across 0 labs. No admitted core comparisons

    Estimated against the same complete panel: gpt-5.6-sol claude-opus-4-8 gemini-3.1-pro . Indirect comparisons assume performance can be summarized by one strength within this capability.

    Refit without one family: No supported estimate; 5/5 scenarios unsupported. Without one publisher: No supported estimate; 5/5 unsupported. Smoothing check: No supported estimate; 3/3 unsupported. These are sensitivity checks, not confidence intervals.

    Audit: family and publisher holdouts underperformed neutral predictions. Treat this as an exploratory estimate. Validation audit.

    Matched family win shares below describe source evidence; they are not averaged to produce the adjusted score.

      Scores estimate outcomes against a shared reference panel; they are not accuracy percentages. Sparse or disconnected evidence cannot qualify an overall profile. Open a capability to inspect its evidence.

      Reported effort · Max + unspecified

      Settings reported in this model's published benchmark results, including results outside the aggregate. Effort names are provider-specific. These are not API defaults or equal compute budgets.

      Mixed settings means multiple settings occur in the evidence. Best across efforts means the source selected its best reported result across settings; it does not mean Max. Unspecified settings stay unknown. This model-summary chart combines reported settings. The leaderboard keeps identified configurations separate and excludes unknown effort.

      Inspect each result and its source ↓ · Download effort evidence
      Score contributions and missing evidence

      14 contributing families across 5 capabilities. Fixed reference panels do not change when the catalog expands.

      Capability is fitted jointly across families. Capability estimates below describe different task areas; their weighted sum is not the Capability score.

      Results without reviewed compatibility or a reference match remain in the raw evidence below. Coverage counts only contributing results.

      Model information & shareable badge
      Lab
      Moonshot
      Catalog status
      api-listed
      Availability
      Documented provider API and open weights for self-hosting
      Family
      Kimi
      Released
      —
      Context
      1,000,000 tokens
      License
      —
      Model card
      https://huggingface.co/moonshotai/Kimi-K3
      Default Capability family coverage
      Documented-evidence family coverage/badge/kimi-k3.svg
      Benchmark scores & sources

      Original results, evaluation harnesses, and evidence behind this model.

      BenchmarkBucketScoreHarnessEvidenceSource-recorded date
      AA-Briefcase (Elo) · source release snapshot; version not specifiedSupporting evidence1548
      Reported settings & source

      Table headers: Kimi K3, GPT-5.6 Sol, Opus 4.8 and GLM-5.2 max; GPT-5.5 xhigh; Fable 5 max with fallbacks. Benchmark-specific footnotes override header settings; cited results are not new Moonshot evaluations. Benchmark-specific tools, harness and budget documented under Evaluation Details. Kimi temp1; single-step top_p.95,agentic top_p1; vision tools=Python,3runs except ZeroBench5runs.

      Cited result; see benchmark-specific Evaluation Details.

      Comparison limit: Kimi K3 Evaluation Details cites Artificial Analysis; retain as published context, not a new Moonshot comparison.

      moonshotai/Kimi-K3 · Performance table: AA-Briefcase (Elo) · reviewed 2026-10-18

      		Published configuration

      Effort: Max

      		lab self-report

      Kimi K3 Evaluation Details cites Artificial Analysis; retain as published context, not a new Moonshot comparison.

      		Reviewed 2026-10-18
      AA-LCR · source release snapshot; version not specifiedLong context74.7%
      Reported settings & source

      Table headers: Kimi K3, GPT-5.6 Sol, Opus 4.8 and GLM-5.2 max; GPT-5.5 xhigh; Fable 5 max with fallbacks. Benchmark-specific footnotes override header settings; cited results are not new Moonshot evaluations. Benchmark-specific tools, harness and budget documented under Evaluation Details. Kimi temp1; single-step top_p.95,agentic top_p1; vision tools=Python,3runs except ZeroBench5runs.

      Cited result; see benchmark-specific Evaluation Details.

      Comparison limit: Kimi K3 Evaluation Details cites Artificial Analysis; retain as published context, not a new Moonshot comparison.

      moonshotai/Kimi-K3 · Performance table: AA-LCR · reviewed 2026-10-18

      		Published configuration

      Effort: Max

      		lab self-report

      Kimi K3 Evaluation Details cites Artificial Analysis; retain as published context, not a new Moonshot comparison.

      		Reviewed 2026-10-18
      Agents' Last ExamSupporting evidence27%Agents' Last Exam · Claude Code

      Effort: Not specified

      		official board

      Supporting evidence outside the reviewed capability core

      		2026-10-20
      Agents' Last ExamSupporting evidence28.3%Agents' Last Exam · Kimi Code

      Effort: Not specified

      		official board

      Supporting evidence outside the reviewed capability core

      		2026-10-20
      Agents' Last Exam · source release snapshot; version not specifiedSupporting evidence28.3%
      Reported settings & source

      Table headers: Kimi K3, GPT-5.6 Sol, Opus 4.8 and GLM-5.2 max; GPT-5.5 xhigh; Fable 5 max with fallbacks. Benchmark-specific footnotes override header settings; cited results are not new Moonshot evaluations. Benchmark-specific tools, harness and budget documented under Evaluation Details. Kimi temp1; single-step top_p.95,agentic top_p1; vision tools=Python,3runs except ZeroBench5runs.

      Cited result; see benchmark-specific Evaluation Details.

      Comparison limit: Kimi K3 Evaluation Details cites official Agents Last Exam leaderboard; retain as published context, not a new Moonshot comparison.

      moonshotai/Kimi-K3 · Performance table: Agents' Last Exam · reviewed 2026-10-18

      		Published configuration

      Effort: Max

      		lab self-report

      Kimi K3 Evaluation Details cites official Agents Last Exam leaderboard; retain as published context, not a new Moonshot comparison.

      		Reviewed 2026-10-18
      Agents' Last Exam · source release snapshot; version not specifiedSupporting evidence27.6%
      Reported settings & source

      DeepSeek updated 0813/0731 release evaluation table; tool/harness settings per model card.

      First-party reported result.

      deepseek-ai/DeepSeek-V4-Pro-0813 · Performance table: Agents' Last Exam · reviewed 2026-10-18

      		Published configuration

      Effort: Not specified

      		lab self-report

      Supporting evidence outside the reviewed capability core

      		Reviewed 2026-10-18
      Agents' Last Exam (ALE-CLI) · source release snapshot; version not specifiedSupporting evidence27.6%
      Reported settings & source

      GLM-5.3 release table; benchmark-specific harness and reasoning configurations in Evaluation Details.

      First-party reported result.

      zai-org/GLM-5.3 · Performance table: Agents' Last Exam (ALE-CLI) · reviewed 2026-10-18

      		Published configuration

      Effort: Not specified

      		lab self-report

      Supporting evidence outside the reviewed capability core

      		Reviewed 2026-10-18
      APEX-Agents · source release snapshot; version not specifiedAgentic41%
      Reported settings & source

      Table headers: Kimi K3, GPT-5.6 Sol, Opus 4.8 and GLM-5.2 max; GPT-5.5 xhigh; Fable 5 max with fallbacks. Benchmark-specific footnotes override header settings; cited results are not new Moonshot evaluations. Benchmark-specific tools, harness and budget documented under Evaluation Details. Kimi temp1; single-step top_p.95,agentic top_p1; vision tools=Python,3runs except ZeroBench5runs.

      Cited result; see benchmark-specific Evaluation Details.

      Comparison limit: Kimi K3 Evaluation Details cites Artificial Analysis / APEX-Agents leaderboard; retain as published context, not a new Moonshot comparison.

      moonshotai/Kimi-K3 · Performance table: APEX-Agents · reviewed 2026-10-18

      		Published configuration

      Effort: Max

      		lab self-report

      Kimi K3 Evaluation Details cites Artificial Analysis / APEX-Agents leaderboard; retain as published context, not a new Moonshot comparison.

      		Reviewed 2026-10-18
      ARC-AGI-2Hard reasoning60.4%ARC Prize verified

      Effort: Not specified

      contributes to capability      		official board2026-07-16
      Artificial Analysis Cyber IndexSupporting evidence41.2676448723918 Artificial Analysis Stirrup · Cyber Index v1.0 · max

      Effort: Max

      Cyber Index source settings

      Artificial Analysis Stirrup, v1.0. Display only. This composite measures defensive source-code tasks. Successful capability scores depend on safety refusals, and refusal rates are reported separately. It does not enter weighted Overall.

      Official Cyber Index board
      		official board

      Supporting evidence outside the reviewed capability core

      		2026-10-21
      Artificial Analysis Intelligence IndexSupporting evidence60 AA Intelligence Index

      Effort: Not specified

      		official board

      Composite index or publisher-specific internal evaluation lacks a stable general-capability comparison unit. Composite index excluded to avoid double counting its ingredients.

      		2026-08-12
      AutomationBench · source release snapshot; version not specifiedAgentic30.8%
      Reported settings & source

      Table headers: Kimi K3, GPT-5.6 Sol, Opus 4.8 and GLM-5.2 max; GPT-5.5 xhigh; Fable 5 max with fallbacks. Benchmark-specific footnotes override header settings; cited results are not new Moonshot evaluations. Benchmark-specific tools, harness and budget documented under Evaluation Details. Kimi temp1; single-step top_p.95,agentic top_p1; vision tools=Python,3runs except ZeroBench5runs.

      First-party reported result.

      moonshotai/Kimi-K3 · Performance table: AutomationBench · reviewed 2026-10-18

      		Published configuration

      Effort: Max

      contributes to capability      		lab self-reportReviewed 2026-10-18
      AutomationBench (Public) · source release snapshot; version not specifiedAgentic30.8%
      Reported settings & source

      DeepSeek updated 0813/0731 release evaluation table; tool/harness settings per model card.

      First-party reported result.

      deepseek-ai/DeepSeek-V4-Pro-0813 · Performance table: AutomationBench (Public) · reviewed 2026-10-18

      		Published configuration

      Effort: Not specified

      contributes to capability      		lab self-reportReviewed 2026-10-18
      AutomationBench (v1.0.6) · v1.0.6Agentic46.7%
      Reported settings & source

      GLM-5.3 release table; benchmark-specific harness and reasoning configurations in Evaluation Details.

      First-party reported result.

      zai-org/GLM-5.3 · Performance table: AutomationBench (v1.0.6) · reviewed 2026-10-18

      		Published configuration

      Effort: Not specified

      contributes to capability      		lab self-reportReviewed 2026-10-18
      AutomationBench-AASupporting evidence58.272977800152034%Artificial Analysis AutomationBench-AA

      Effort: Not specified

      		official board

      Supporting evidence outside the reviewed capability core

      		2026-10-20
      AutoResearchExamSupporting evidence0.435 AutoResearchExam Terminus 2

      Effort: Not specified

      		official board

      Supporting evidence outside the reviewed capability core

      		2026-09-09
      BabyVision w/ python · source release snapshot; version not specifiedSupporting evidence85.7%
      Reported settings & source

      Table headers: Kimi K3, GPT-5.6 Sol, Opus 4.8 and GLM-5.2 max; GPT-5.5 xhigh; Fable 5 max with fallbacks. Benchmark-specific footnotes override header settings; cited results are not new Moonshot evaluations. Benchmark-specific tools, harness and budget documented under Evaluation Details. Kimi temp1; single-step top_p.95,agentic top_p1; vision tools=Python,3runs except ZeroBench5runs.

      First-party reported result.

      moonshotai/Kimi-K3 · Performance table: BabyVision w/ python · reviewed 2026-10-18

      		Published configuration

      Effort: Max

      		lab self-report

      Supporting evidence outside the reviewed capability core

      		Reviewed 2026-10-18
      BrowseCompAgentic91.2%BrowseComp reported

      Effort: Not specified

      		lab self-report

      Legacy self-report lacks a reviewed comparison configuration

      		2026-07-16
      BrowseComp · source release snapshot; version not specifiedAgentic91.2%
      Reported settings & source

      Table headers: Kimi K3, GPT-5.6 Sol, Opus 4.8 and GLM-5.2 max; GPT-5.5 xhigh; Fable 5 max with fallbacks. Benchmark-specific footnotes override header settings; cited results are not new Moonshot evaluations. Benchmark-specific tools, harness and budget documented under Evaluation Details. Kimi temp1; single-step top_p.95,agentic top_p1; vision tools=Python,3runs except ZeroBench5runs.

      First-party reported result.

      moonshotai/Kimi-K3 · Performance table: BrowseComp · reviewed 2026-10-18

      		Published configuration

      Effort: Max

      		lab self-report

      No matched opponent in this evaluation unit

      		Reviewed 2026-10-18
      Bug Hunt BenchSupporting evidence20%Bug Hunt Bench · default

      Effort: Not specified

      		official board

      Supporting evidence outside the reviewed capability core

      		2026-07-26
      CharXiv (RQ) · source release snapshot; version not specifiedMultimodal84.8%
      Reported settings & source

      Table headers: Kimi K3, GPT-5.6 Sol, Opus 4.8 and GLM-5.2 max; GPT-5.5 xhigh; Fable 5 max with fallbacks. Benchmark-specific footnotes override header settings; cited results are not new Moonshot evaluations. Benchmark-specific tools, harness and budget documented under Evaluation Details. without tools Kimi temp1; single-step top_p.95,agentic top_p1; vision tools=Python,3runs except ZeroBench5runs.

      First-party reported result.

      moonshotai/Kimi-K3 · Performance table: CharXiv (RQ) · reviewed 2026-10-18

      		Published configuration

      Effort: Max

      contributes to capability      		lab self-reportReviewed 2026-10-18
      CharXiv (RQ) · source release snapshot; version not specifiedMultimodal91.3%
      Reported settings & source

      Table headers: Kimi K3, GPT-5.6 Sol, Opus 4.8 and GLM-5.2 max; GPT-5.5 xhigh; Fable 5 max with fallbacks. Benchmark-specific footnotes override header settings; cited results are not new Moonshot evaluations. Benchmark-specific tools, harness and budget documented under Evaluation Details. with tools Kimi temp1; single-step top_p.95,agentic top_p1; vision tools=Python,3runs except ZeroBench5runs.

      First-party reported result.

      moonshotai/Kimi-K3 · Performance table: CharXiv (RQ) · reviewed 2026-10-18

      		Published configuration

      Effort: Max

      contributes to capability      		lab self-reportReviewed 2026-10-18
      CorpFin v2 · source release snapshot; version not specifiedSupporting evidence71.6%
      Reported settings & source

      Table headers: Kimi K3, GPT-5.6 Sol, Opus 4.8 and GLM-5.2 max; GPT-5.5 xhigh; Fable 5 max with fallbacks. Benchmark-specific footnotes override header settings; cited results are not new Moonshot evaluations. Benchmark-specific tools, harness and budget documented under Evaluation Details. Kimi temp1; single-step top_p.95,agentic top_p1; vision tools=Python,3runs except ZeroBench5runs.

      Cited result; see benchmark-specific Evaluation Details.

      Comparison limit: Kimi K3 Evaluation Details cites Vals AI; retain as published context, not a new Moonshot comparison.

      moonshotai/Kimi-K3 · Performance table: CorpFin v2 · reviewed 2026-10-18

      		Published configuration

      Effort: Max

      		lab self-report

      Kimi K3 Evaluation Details cites Vals AI; retain as published context, not a new Moonshot comparison.

      		Reviewed 2026-10-18
      CritPt · source release snapshot; version not specifiedSupporting evidence23.4%
      Reported settings & source

      Table headers: Kimi K3, GPT-5.6 Sol, Opus 4.8 and GLM-5.2 max; GPT-5.5 xhigh; Fable 5 max with fallbacks. Benchmark-specific footnotes override header settings; cited results are not new Moonshot evaluations. Benchmark-specific tools, harness and budget documented under Evaluation Details. Kimi temp1; single-step top_p.95,agentic top_p1; vision tools=Python,3runs except ZeroBench5runs.

      Cited result; see benchmark-specific Evaluation Details.

      Comparison limit: Kimi K3 Evaluation Details cites Artificial Analysis; retain as published context, not a new Moonshot comparison.

      moonshotai/Kimi-K3 · Performance table: CritPt · reviewed 2026-10-18

      		Published configuration

      Effort: Max

      		lab self-report

      Kimi K3 Evaluation Details cites Artificial Analysis; retain as published context, not a new Moonshot comparison.

      		Reviewed 2026-10-18
      Cybergym · source release snapshot; version not specifiedSupporting evidence80%
      Reported settings & source

      DeepSeek updated 0813/0731 release evaluation table; tool/harness settings per model card.

      First-party reported result.

      deepseek-ai/DeepSeek-V4-Pro-0813 · Performance table: Cybergym · reviewed 2026-10-18

      		Published configuration

      Effort: Not specified

      		lab self-report

      Narrow specialist biological, medical or security evaluation; preserved as raw evidence outside general capability scoring.

      		Reviewed 2026-10-18