Head-to-head comparison
Grok 4.6 vs. Kimi K3
Compare published benchmark results from matching versions and cohorts, API pricing, and technical specifications. Any documented test setup differences remain visible.
40
shared result series
22
distinct benchmarks
2026-08-16
latest retrieval
Change model selection
Specifications and cost
General specifications and standard API pricing
Undisclosed parameter counts and knowledge cutoffs stay marked as unavailable. The table shows direct standard token pricing, including documented context tiers. Batch, fast, priority, regional surcharges, tool calls, and cloud platform pricing are excluded.
| Attribute | Grok 4.6 | Kimi K3 |
|---|---|---|
| Provider | xAI | Moonshot AI |
| Released | Aug 12, 2026 | Jul 16, 2026 |
| Availability | Active | Active |
| Model type | Proprietary | Open Weights |
| Parameters | Not published | 2.8T, 104B active |
| Architecture | Not published | Mixture of Experts |
| Context window | 500,000 tokens | 1,048,576 tokens |
| Knowledge cutoff | February 1, 2026 | Not published |
| Technical sources | Model | Model |
| API pricing per 1M tokens | ||
| API input | $2 ≤200K / $4 >200K | $3 |
| API output | $6 ≤200K / $12 >200K | $15 |
| Cache read | $0.5 ≤200K / $1 >200K | $0.3 |
| Cache write (5 min.) | Not listed | Not listed |
| Cache write (1 hr.) | Not listed | Not listed |
| Price verified | 08/16/2026Source | 07/30/2026Source |
Grok 4.6Kimi K3
API inputUSD per 1M tokens, base tier
Grok 4.6$2Lower price
Kimi K3$3
API outputUSD per 1M tokens, base tier
Grok 4.6$6Lower price
Kimi K3$15
Cache readUSD per 1M tokens, base tier
Grok 4.6$0.5
Kimi K3$0.3Lower price
Performance
Shared benchmarks
Only published results with the same benchmark version, task, metric, and comparison cohort are paired. Different reasoning levels, agents, harnesses, or output limits appear directly in the table.
40 shared result series
Grok 4.6Kimi K3
Arena Text, Style ControlOverall. Higher is better. Test setup not documented as identical
Grok 4.61,464.323 arena points
Kimi K31,488.568 arena pointsHigher measured value
Code MigrationOverall. Higher is better. No documented setup difference
Grok 4.644.572 %Winner
Kimi K316.099 %
CorpFin v2Overall. Higher is better. No documented setup difference
Grok 4.666.161 %
Kimi K371.562 %Winner
EMBOverall. Higher is better. No documented setup difference
Grok 4.662.727 %
Kimi K366.399 %Winner
Finance Agent (v2)Overall. Higher is better. No documented setup difference
Grok 4.653.682 %
Kimi K354.36 %Winner
GPQA DiamondOverall. Higher is better. No documented setup difference
Grok 4.694.697 %Winner
Kimi K392.929 %
Harvey's Legal Agent BenchmarkOverall · Task fully resolved. Higher is better. No documented setup difference
Grok 4.615.833 %Winner
Kimi K310.833 %
Legal Research BenchOverall · All-pass. Higher is better. No documented setup difference
Grok 4.648.077 %Winner
Kimi K344.231 %
LegalBenchOverall. Higher is better. No documented setup difference
Grok 4.686.307 %Winner
Kimi K386.016 %
LiveCodeBench v6Overall. Higher is better. No documented setup difference
Grok 4.688.224 %Winner
Kimi K387.185 %
MedCodeOverall. Higher is better. No documented setup difference
Grok 4.644.712 %
Kimi K348.884 %Winner
MedScribeOverall. Higher is better. No documented setup difference
Grok 4.686.534 %
Kimi K387.958 %Winner
| Benchmark and task | Grok 4.6 | Kimi K3 | Comparability | Source |
|---|---|---|---|---|
| Arena Text, Style ControlOverall | 1,464.323 arena points 95% confidence interval: ±11.88The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,488.568 arena pointsHigher measured value 95% confidence interval: ±6.219The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | style-control-v1style-controlled Bradley-Terry ratingHigher is betterCohort: lmarena-text-style-control:2026-08-12:overallTest setup not documented as identicalNo direct winnerGrok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style control Kimi K3: Snapshot: kimi-k3-max, Reasoning: max, Harness: Arena text, style controlGrok 4.6: Style-controlled Arena rating from 2,448 anonymous pairwise votes.Kimi K3: Style-controlled Arena rating from 11,864 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Code MigrationOverall | 44.572 %Winner | 16.099 % | 1accuracyHigher is betterCohort: vals-code-migration:1:overallNo documented setup differenceWinner: Grok 4.6Grok 4.6: No further settings disclosed Kimi K3: No further settings disclosed | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-13Import ID: vals-code-migration-2026-08-16-107652dc6bfcRetrieved 2026-08-16 |
| CorpFin v2Overall | 66.161 % | 71.562 %Winner | 2accuracyHigher is betterCohort: vals-corp-fin-v2:2:overallNo documented setup differenceWinner: Kimi K3Grok 4.6: No further settings disclosed Kimi K3: No further settings disclosed | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-12Import ID: vals-corp_fin_v2-2026-08-16-45bbf84f57abRetrieved 2026-08-16 |
| EMBOverall | 62.727 % | 66.399 %Winner | 1accuracyHigher is betterCohort: vals-emb:1:overallNo documented setup differenceWinner: Kimi K3Grok 4.6: No further settings disclosed Kimi K3: No further settings disclosed | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-13Import ID: vals-emb-2026-08-16-68d5d1d47a97Retrieved 2026-08-16 |
| Finance Agent (v2)Overall | 53.682 % | 54.36 %Winner | 2accuracyHigher is betterCohort: vals-finance-agent-v2:2:overallNo documented setup differenceWinner: Kimi K3Grok 4.6: No further settings disclosed Kimi K3: No further settings disclosed | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-14Import ID: vals-fabv2-2026-08-16-8853da43085dRetrieved 2026-08-16 |
| GPQA DiamondOverall | 94.697 %Winner | 92.929 % | 1accuracyHigher is betterCohort: vals-gpqa:1:overallNo documented setup differenceWinner: Grok 4.6Grok 4.6: No further settings disclosed Kimi K3: No further settings disclosed | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-12Import ID: vals-gpqa-2026-08-16-7f8363eaa2dbRetrieved 2026-08-16 |
| Harvey's Legal Agent BenchmarkOverall · Task fully resolved | 15.833 %Winner | 10.833 % | 1task resolution rateHigher is betterCohort: vals-legal-agent-benchmark:1:overallNo documented setup differenceWinner: Grok 4.6Grok 4.6: No further settings disclosed Kimi K3: No further settings disclosed | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-14Import ID: vals-hlab-2026-08-16-bae90566df2fRetrieved 2026-08-16 |
| Legal Research BenchOverall · All-pass | 48.077 %Winner | 44.231 % | 1all-pass rateHigher is betterCohort: vals-legal-research:1:overallNo documented setup differenceWinner: Grok 4.6Grok 4.6: No further settings disclosed Kimi K3: No further settings disclosed | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-14Import ID: vals-legal_research-2026-08-16-af296c00ecaaRetrieved 2026-08-16 |
| LegalBenchOverall | 86.307 %Winner | 86.016 % | 1accuracyHigher is betterCohort: vals-legal-bench:1:overallNo documented setup differenceWinner: Grok 4.6Grok 4.6: No further settings disclosed Kimi K3: No further settings disclosed | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-12Import ID: vals-legal_bench-2026-08-16-d5b3b1b2b5c8Retrieved 2026-08-16 |
| LiveCodeBench v6Overall | 88.224 %Winner | 87.185 % | 1accuracyHigher is betterCohort: vals-lcb:1:overallNo documented setup differenceWinner: Grok 4.6Grok 4.6: No further settings disclosed Kimi K3: No further settings disclosed | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-13Import ID: vals-lcb-2026-08-16-17b9c147080dRetrieved 2026-08-16 |
| MedCodeOverall | 44.712 % | 48.884 %Winner | 1accuracyHigher is betterCohort: vals-medcode:1:overallNo documented setup differenceWinner: Kimi K3Grok 4.6: No further settings disclosed Kimi K3: No further settings disclosed | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-12Import ID: vals-medcode-2026-08-16-524f7f474eacRetrieved 2026-08-16 |
| MedScribeOverall | 86.534 % | 87.958 %Winner | 1accuracyHigher is betterCohort: vals-medscribe:1:overallNo documented setup differenceWinner: Kimi K3Grok 4.6: No further settings disclosed Kimi K3: No further settings disclosed | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-12Import ID: vals-medscribe-2026-08-16-c385354a7e62Retrieved 2026-08-16 |
| MMLU-ProOverall | 89.4 %Winner | 87.973 % | 1accuracyHigher is betterCohort: vals-mmlu-pro:1:overallNo documented setup differenceWinner: Grok 4.6Grok 4.6: No further settings disclosed Kimi K3: No further settings disclosed | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-12Import ID: vals-mmlu_pro-2026-08-16-e14d5bb3a34cRetrieved 2026-08-16 |
| MortgageTaxOverall | 64.189 % | 66.336 %Winner | 1accuracyHigher is betterCohort: vals-mortgage-tax:1:overallNo documented setup differenceWinner: Kimi K3Grok 4.6: No further settings disclosed Kimi K3: No further settings disclosed | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-12Import ID: vals-mortgage_tax-2026-08-16-e78c985dbb1cRetrieved 2026-08-16 |
| ProofBenchOverall | 51 % | 87 %Winner | 1.1accuracyHigher is betterCohort: vals-proof-bench:1.1:overallNo documented setup differenceWinner: Kimi K3Grok 4.6: No further settings disclosed Kimi K3: No further settings disclosed | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-14Import ID: vals-proof_bench-2026-08-16-14232db24de1Retrieved 2026-08-16 |
| Public Benefits Bench v1.1Overall | 66.847 % | 68.268 %Winner | 1.1accuracyHigher is betterCohort: vals-snap:1.1:overallNo documented setup differenceWinner: Kimi K3Grok 4.6: No further settings disclosed Kimi K3: No further settings disclosed | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-12Import ID: vals-public-benefits-bench-2026-08-16-7ce68123c502Retrieved 2026-08-16 |
| SAGEOverall | 28.9 % | 54.26 %Winner | 1accuracyHigher is betterCohort: vals-sage:1:overallNo documented setup differenceWinner: Kimi K3Grok 4.6: No further settings disclosed Kimi K3: No further settings disclosed | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-12Import ID: vals-sage-2026-08-16-a416dd25affbRetrieved 2026-08-16 |
| SWE-bench VerifiedOverall | 95.6 %Winner | 93.4 % | 1accuracyHigher is betterCohort: vals-swebench:1:overallNo documented setup differenceWinner: Grok 4.6Grok 4.6: No further settings disclosed Kimi K3: No further settings disclosed | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-12Import ID: vals-swebench-2026-08-16-c133071b8167Retrieved 2026-08-16 |
| TaxEval v2Overall | 71.096 % | 75.716 %Winner | 2accuracyHigher is betterCohort: vals-tax-eval-v2:2:overallNo documented setup differenceWinner: Kimi K3Grok 4.6: No further settings disclosed Kimi K3: No further settings disclosed | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-12Import ID: vals-tax_eval_v2-2026-08-16-5bbd495dac53Retrieved 2026-08-16 |
| Terminal-Bench 2.1Overall | 78.277 % | 80.899 %Winner | 2.1accuracyHigher is betterCohort: vals-terminal-bench-2-1:2.1:overallNo documented setup differenceWinner: Kimi K3Grok 4.6: No further settings disclosed Kimi K3: No further settings disclosed | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-13Import ID: vals-terminal-bench-2-1-2026-08-16-b3f38c18bea4Retrieved 2026-08-16 |
| Vals IndexOverall | 59.167 %Winner | 57.813 % | 2weighted index scoreHigher is betterCohort: vals-vals-index:2:overallNo documented setup differenceWinner: Grok 4.6Grok 4.6: No further settings disclosed Kimi K3: No further settings disclosed | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-14Import ID: vals-vals_index-2026-08-16-ab641d89d6edRetrieved 2026-08-16 |
| Vibe Code Bench v1.1Overall | 76.239 % | 84.963 %Winner | 1.1accuracyHigher is betterCohort: vals-vibe-code-bench:1.1:overallNo documented setup differenceWinner: Kimi K3Grok 4.6: Harness: OpenHands Kimi K3: Harness: OpenHands | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-13Import ID: vals-vibe-code-2026-08-16-a73c9770bcc4Retrieved 2026-08-16 |
| Arena Text, Style ControlBusiness, management and finance | 1,455.102 arena points 95% confidence interval: ±27.332The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,494.784 arena pointsHigher measured value 95% confidence interval: ±12.523The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | style-control-v1style-controlled Bradley-Terry ratingHigher is betterCohort: lmarena-text-style-control:2026-08-12:industry_business_and_management_and_financial_operationsTest setup not documented as identicalNo direct winnerGrok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style control Kimi K3: Snapshot: kimi-k3-max, Reasoning: max, Harness: Arena text, style controlGrok 4.6: Style-controlled Arena rating from 442 anonymous pairwise votes.Kimi K3: Style-controlled Arena rating from 2,416 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlChinese | 1,535.167 arena pointsHigher measured value 95% confidence interval: ±39.462The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,524.123 arena points 95% confidence interval: ±21.434The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | style-control-v1style-controlled Bradley-Terry ratingHigher is betterCohort: lmarena-text-style-control:2026-08-12:chineseTest setup not documented as identicalNo direct winnerGrok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style control Kimi K3: Snapshot: kimi-k3-max, Reasoning: max, Harness: Arena text, style controlGrok 4.6: Style-controlled Arena rating from 215 anonymous pairwise votes.Kimi K3: Style-controlled Arena rating from 800 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlCoding | 1,511.77 arena points 95% confidence interval: ±26.72The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,542.923 arena pointsHigher measured value 95% confidence interval: ±10.951The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | style-control-v1style-controlled Bradley-Terry ratingHigher is betterCohort: lmarena-text-style-control:2026-08-12:codingTest setup not documented as identicalNo direct winnerGrok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style control Kimi K3: Snapshot: kimi-k3-max, Reasoning: max, Harness: Arena text, style controlGrok 4.6: Style-controlled Arena rating from 485 anonymous pairwise votes.Kimi K3: Style-controlled Arena rating from 3,162 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlCreative writing | 1,472.894 arena pointsHigher measured value 95% confidence interval: ±31.578The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,456.079 arena points 95% confidence interval: ±13.261The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | style-control-v1style-controlled Bradley-Terry ratingHigher is betterCohort: lmarena-text-style-control:2026-08-12:creative_writingTest setup not documented as identicalNo direct winnerGrok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style control Kimi K3: Snapshot: kimi-k3-max, Reasoning: max, Harness: Arena text, style controlGrok 4.6: Style-controlled Arena rating from 379 anonymous pairwise votes.Kimi K3: Style-controlled Arena rating from 2,177 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlEnglish | 1,459.266 arena points 95% confidence interval: ±18.461The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,497.219 arena pointsHigher measured value 95% confidence interval: ±9.002The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | style-control-v1style-controlled Bradley-Terry ratingHigher is betterCohort: lmarena-text-style-control:2026-08-12:englishTest setup not documented as identicalNo direct winnerGrok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style control Kimi K3: Snapshot: kimi-k3-max, Reasoning: max, Harness: Arena text, style controlGrok 4.6: Style-controlled Arena rating from 998 anonymous pairwise votes.Kimi K3: Style-controlled Arena rating from 4,521 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlEntertainment, sports and media | 1,455.476 arena pointsHigher measured value 95% confidence interval: ±28.81The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,449.776 arena points 95% confidence interval: ±11.817The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | style-control-v1style-controlled Bradley-Terry ratingHigher is betterCohort: lmarena-text-style-control:2026-08-12:industry_entertainment_and_sports_and_mediaTest setup not documented as identicalNo direct winnerGrok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style control Kimi K3: Snapshot: kimi-k3-max, Reasoning: max, Harness: Arena text, style controlGrok 4.6: Style-controlled Arena rating from 448 anonymous pairwise votes.Kimi K3: Style-controlled Arena rating from 2,745 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlExcluding ties | 1,469.633 arena points 95% confidence interval: ±16.492The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,501.266 arena pointsHigher measured value 95% confidence interval: ±8.181The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | style-control-v1style-controlled Bradley-Terry ratingHigher is betterCohort: lmarena-text-style-control:2026-08-12:exclude_tiesTest setup not documented as identicalNo direct winnerGrok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style control Kimi K3: Snapshot: kimi-k3-max, Reasoning: max, Harness: Arena text, style controlGrok 4.6: Style-controlled Arena rating from 1,782 anonymous pairwise votes.Kimi K3: Style-controlled Arena rating from 8,787 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlExpert prompts | 1,479.969 arena points 95% confidence interval: ±34.191The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,514.705 arena pointsHigher measured value 95% confidence interval: ±17.9The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | style-control-v1style-controlled Bradley-Terry ratingHigher is betterCohort: lmarena-text-style-control:2026-08-12:expertTest setup not documented as identicalNo direct winnerGrok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style control Kimi K3: Snapshot: kimi-k3-max, Reasoning: max, Harness: Arena text, style controlGrok 4.6: Style-controlled Arena rating from 272 anonymous pairwise votes.Kimi K3: Style-controlled Arena rating from 1,099 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlHard prompts | 1,488.551 arena points 95% confidence interval: ±15.88The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,516.393 arena pointsHigher measured value 95% confidence interval: ±7.386The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | style-control-v1style-controlled Bradley-Terry ratingHigher is betterCohort: lmarena-text-style-control:2026-08-12:hard_promptsTest setup not documented as identicalNo direct winnerGrok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style control Kimi K3: Snapshot: kimi-k3-max, Reasoning: max, Harness: Arena text, style controlGrok 4.6: Style-controlled Arena rating from 1,397 anonymous pairwise votes.Kimi K3: Style-controlled Arena rating from 7,750 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlHard prompts, English | 1,472.181 arena points 95% confidence interval: ±25.031The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,517.989 arena pointsHigher measured value 95% confidence interval: ±11.15The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | style-control-v1style-controlled Bradley-Terry ratingHigher is betterCohort: lmarena-text-style-control:2026-08-12:hard_prompts_englishTest setup not documented as identicalNo direct winnerGrok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style control Kimi K3: Snapshot: kimi-k3-max, Reasoning: max, Harness: Arena text, style controlGrok 4.6: Style-controlled Arena rating from 543 anonymous pairwise votes.Kimi K3: Style-controlled Arena rating from 2,935 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlInstruction following | 1,460.755 arena points 95% confidence interval: ±21.635The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,484.181 arena pointsHigher measured value 95% confidence interval: ±9.761The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | style-control-v1style-controlled Bradley-Terry ratingHigher is betterCohort: lmarena-text-style-control:2026-08-12:instruction_followingTest setup not documented as identicalNo direct winnerGrok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style control Kimi K3: Snapshot: kimi-k3-max, Reasoning: max, Harness: Arena text, style controlGrok 4.6: Style-controlled Arena rating from 732 anonymous pairwise votes.Kimi K3: Style-controlled Arena rating from 3,963 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlLife, physical and social science | 1,497.908 arena points 95% confidence interval: ±31.96The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,526.942 arena pointsHigher measured value 95% confidence interval: ±13.994The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | style-control-v1style-controlled Bradley-Terry ratingHigher is betterCohort: lmarena-text-style-control:2026-08-12:industry_life_and_physical_and_social_scienceTest setup not documented as identicalNo direct winnerGrok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style control Kimi K3: Snapshot: kimi-k3-max, Reasoning: max, Harness: Arena text, style controlGrok 4.6: Style-controlled Arena rating from 335 anonymous pairwise votes.Kimi K3: Style-controlled Arena rating from 1,858 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlLonger queries | 1,485.451 arena points 95% confidence interval: ±18.11The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,500.801 arena pointsHigher measured value 95% confidence interval: ±8.957The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | style-control-v1style-controlled Bradley-Terry ratingHigher is betterCohort: lmarena-text-style-control:2026-08-12:longer_queryTest setup not documented as identicalNo direct winnerGrok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style control Kimi K3: Snapshot: kimi-k3-max, Reasoning: max, Harness: Arena text, style controlGrok 4.6: Style-controlled Arena rating from 1,103 anonymous pairwise votes.Kimi K3: Style-controlled Arena rating from 5,260 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlMulti-turn | 1,444.26 arena points 95% confidence interval: ±31.774The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,502.452 arena pointsHigher measured value 95% confidence interval: ±14.124The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | style-control-v1style-controlled Bradley-Terry ratingHigher is betterCohort: lmarena-text-style-control:2026-08-12:multi_turnTest setup not documented as identicalNo direct winnerGrok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style control Kimi K3: Snapshot: kimi-k3-max, Reasoning: max, Harness: Arena text, style controlGrok 4.6: Style-controlled Arena rating from 352 anonymous pairwise votes.Kimi K3: Style-controlled Arena rating from 1,890 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlNon-English | 1,461.99 arena points 95% confidence interval: ±15.246The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,473.735 arena pointsHigher measured value 95% confidence interval: ±7.512The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | style-control-v1style-controlled Bradley-Terry ratingHigher is betterCohort: lmarena-text-style-control:2026-08-12:non_englishTest setup not documented as identicalNo direct winnerGrok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style control Kimi K3: Snapshot: kimi-k3-max, Reasoning: max, Harness: Arena text, style controlGrok 4.6: Style-controlled Arena rating from 1,450 anonymous pairwise votes.Kimi K3: Style-controlled Arena rating from 7,338 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlRussian | 1,446.737 arena points 95% confidence interval: ±34.404The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,490.991 arena pointsHigher measured value 95% confidence interval: ±16.903The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | style-control-v1style-controlled Bradley-Terry ratingHigher is betterCohort: lmarena-text-style-control:2026-08-12:russianTest setup not documented as identicalNo direct winnerGrok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style control Kimi K3: Snapshot: kimi-k3-max, Reasoning: max, Harness: Arena text, style controlGrok 4.6: Style-controlled Arena rating from 275 anonymous pairwise votes.Kimi K3: Style-controlled Arena rating from 1,268 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlSoftware and IT services | 1,511.885 arena points 95% confidence interval: ±20.78The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,527.685 arena pointsHigher measured value 95% confidence interval: ±9.01The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | style-control-v1style-controlled Bradley-Terry ratingHigher is betterCohort: lmarena-text-style-control:2026-08-12:industry_software_and_it_servicesTest setup not documented as identicalNo direct winnerGrok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style control Kimi K3: Snapshot: kimi-k3-max, Reasoning: max, Harness: Arena text, style controlGrok 4.6: Style-controlled Arena rating from 805 anonymous pairwise votes.Kimi K3: Style-controlled Arena rating from 4,716 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Arena Text, Style ControlWriting, literature and language | 1,455.393 arena points 95% confidence interval: ±25.717The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,469.348 arena pointsHigher measured value 95% confidence interval: ±11.093The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | style-control-v1style-controlled Bradley-Terry ratingHigher is betterCohort: lmarena-text-style-control:2026-08-12:industry_writing_and_literature_and_languageTest setup not documented as identicalNo direct winnerGrok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style control Kimi K3: Snapshot: kimi-k3-max, Reasoning: max, Harness: Arena text, style controlGrok 4.6: Style-controlled Arena rating from 543 anonymous pairwise votes.Kimi K3: Style-controlled Arena rating from 3,046 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
How to read this comparison
Winning one benchmark is not an overall verdict
Your workload, budget, and required context length matter most. A coding benchmark says little about visual understanding or agent performance.
Prices use official API rates per 1M tokens. Web subscriptions and cloud platform surcharges can differ.
Every result links to its measurement source and retrieval date. Labels distinguish vendor reports, official benchmark leaderboards, and independent evaluations. Disputed or archived results are excluded.
More matchups
Related LLM comparisons
Compare Grok 4.6 and Kimi K3 with other leading models using the same data and benchmark logic.
View the complete LLM comparison