Head-to-head comparison
DeepSeek-V4-Flash vs. Kimi K2.6
Compare published benchmark results from matching versions and cohorts, API pricing, and technical specifications. Any documented test setup differences remain visible.
- shared result series
- 61
- distinct benchmarks
- 2
- latest retrieval
- 2026-09-04
Change model selection
Specifications
General specifications
Release date, availability, context window, architecture, and published parameter counts at a glance. Undisclosed details remain marked as unavailable.
| Attribute | DeepSeek-V4-Flash | Kimi K2.6 |
|---|---|---|
| Provider | DeepSeek | Moonshot AI |
| Released | Apr 24, 2026 | Apr 20, 2026 |
| Availability | Preview | Active |
| Model type | Open Weights | Open Weights |
| Parameters | 284B, 13B active | 1T, 32B active |
| Architecture | Mixture of Experts | Mixture of Experts |
| Context window | 1,000,000 tokens | 262,144 tokens |
| Knowledge cutoff | Not published | Not published |
| Technical sources | Model | Model, Context |
Pricing
API pricing compared
The table compares official standard API rates per 1M tokens, including published cache pricing. Batch, fast, priority, regional surcharges, tool calls, and cloud platform pricing are excluded.
| Price type | DeepSeek-V4-Flash | Kimi K2.6 |
|---|---|---|
| API input | $0.14 | $0.95 |
| API output | $0.28 | $4 |
| Cache read | $0. | $0.16 |
| Cache write (5 min.) | Not listed | Not listed |
| Cache write (1 hr.) | Not listed | Not listed |
| Price verified | 07/30/2026 Source | 07/30/2026 Source |
DeepSeek-V4-FlashKimi K2.6
API inputUSD per 1M tokens, base tier
DeepSeek-V4-FlashLower price$0.14
Kimi K2.6$0.95
API outputUSD per 1M tokens, base tier
DeepSeek-V4-FlashLower price$0.28
Kimi K2.6$4
Cache readUSD per 1M tokens, base tier
DeepSeek-V4-FlashLower price$0.003
Kimi K2.6$0.16
Key to the marks:better valuebetter, but not conclusivetie
Pricing by provider
Direct developer pricing and provider endpoint tariffs routed through OpenRouter are listed separately. Prices are in USD per 1M tokens. Context-dependent direct tiers plus regional, Flex, Priority, and other OpenRouter tariffs remain individually identifiable.
| Model | Provider | Purchase route and tariff | Input per 1M tokens | Output per 1M tokens | Source |
|---|---|---|---|---|---|
| DeepSeek-V4-Flash | DeepSeek | Direct from developerStandard API | $0.14 | $0.28 | Source07/30/2026 |
| Alibaba | Via OpenRouteralibaba | $0.352 | $1.056 | Source09/07/2026 | |
| AtlasCloud | Via OpenRouteratlas-cloud/fp4 | $0.44 | $1.32 | Source09/07/2026 | |
| Baidu | Via OpenRouterbaidu/fp8 | $0.14 | $0.28 | Source09/07/2026 | |
| BaseTen | Via OpenRouterbaseten/fp8#1 | $0.13 | $0.26 | Source09/07/2026 | |
| BaseTen | Via OpenRouterbaseten/fp8#2 | $0.13 | $0.26 | Source09/07/2026 | |
| Cloudflare | Via OpenRoutercloudflare | $0.44 | $1.32 | Source09/07/2026 | |
| CoreWeave | Via OpenRoutercoreweave/fp8 | $0.13 | $0.28 | Source09/07/2026 | |
| DeepInfra | Via OpenRouterdeepinfra/fp8 | $0.06 | $0.18 | Source09/07/2026 | |
| DeepSeek | Via OpenRouterdeepseek | $0.22 | $0.66 | Source09/07/2026 | |
| DigitalOcean | Via OpenRouterdigitalocean | $0.08 | $0.252 | Source09/07/2026 | |
| Fireworks | Via OpenRouterfireworks | $0.22 | $0.66 | Source09/07/2026 | |
| GMICloud | Via OpenRoutergmicloud/fp8 | $0.352 | $1.056 | Source09/07/2026 | |
| Inceptron | Via OpenRouterinceptron/fp4 | $0.13 | $0.28 | Source09/07/2026 | |
| Makora | Via OpenRoutermakora | $0.09 | $0.195 | Source09/07/2026 | |
| Mancer 2 | Via OpenRoutermancer/fp8 | $0.15 | $0.5 | Source09/07/2026 | |
| Morph | Via OpenRoutermorph/bf16 | $0.1234 | $0.3475 | Source09/07/2026 | |
| NextBit | Via OpenRouternextbit/fp8 | $0.4 | $1.2 | Source09/07/2026 | |
| Novita | Via OpenRouternovita/fp8 | $0.4092 | $1.2276 | Source09/07/2026 | |
| OpenInference | Via OpenRouteropen-inference/fp8 | $0.05 | $0.16 | Source09/07/2026 | |
| Parasail | Via OpenRouterparasail/fp8 | $0.14 | $0.28 | Source09/07/2026 | |
| Phala | Via OpenRouterphala | $0.44 | $1.32 | Source09/07/2026 | |
| Reka | Via OpenRouterreka/fp4 | $0.11 | $0.66 | Source09/07/2026 | |
| Relace | Via OpenRouterrelace/fp4 | Lowest listed price: $0.045 | Lowest listed price: $0.09 | Source09/07/2026 | |
| Sail Research | Via OpenRoutersail-research/fp4 | $0.065 | $0.18 | Source09/07/2026 | |
| SiliconFlow | Via OpenRoutersiliconflow/fp8 | $0.22 | $0.66 | Source09/07/2026 | |
| StreamLake | Via OpenRouterstreamlake/fp8 | $0.088 | $0.264 | Source09/07/2026 | |
| Together | Via OpenRoutertogether | $0.14 | $0.28 | Source09/07/2026 | |
| Venice | Via OpenRoutervenice | $0.175 | $0.35 | Source09/07/2026 | |
| Wafer | Via OpenRouterwafer/fast | $0.1 | $0.25 | Source09/07/2026 | |
| Kimi K2.6 | Moonshot AI | Direct from developerStandard API | $0.95 | $4 | Source07/30/2026 |
| AtlasCloud | Via OpenRouteratlas-cloud/int4 | $0.95 | $4 | Source09/07/2026 | |
| Baidu | Via OpenRouterbaidu/fp4 | $0.95 | $4 | Source09/07/2026 | |
| BaseTen | Via OpenRouterbaseten/fp4#1 | $0.95 | $4 | Source09/07/2026 | |
| BaseTen | Via OpenRouterbaseten/fp4#2 | $0.95 | $4 | Source09/07/2026 | |
| Chutes | Via OpenRouterchutes/int4 | $0.58 | $3.4 | Source09/07/2026 | |
| Cloudflare | Via OpenRoutercloudflare | $0.95 | $4 | Source09/07/2026 | |
| CoreWeave | Via OpenRoutercoreweave/fp4 | $0.65 | $3.41 | Source09/07/2026 | |
| Crusoe | Via OpenRoutercrusoe/bf16 | $0.7 | $3.5 | Source09/07/2026 | |
| Decart | Via OpenRouterdecart/fp4 | $0.5865 | Lowest listed price: $2.4696 | Source09/07/2026 | |
| DeepInfra | Via OpenRouterdeepinfra/fp4 | $0.75 | $3.5 | Source09/07/2026 | |
| DigitalOcean | Via OpenRouterdigitalocean | $0.95 | $4 | Source09/07/2026 | |
| Fireworks | Via OpenRouterfireworks | $0.95 | $4 | Source09/07/2026 | |
| GMICloud | Via OpenRoutergmicloud/fp8 | $0.855 | $3.6 | Source09/07/2026 | |
| Inceptron | Via OpenRouterinceptron/int4 | Lowest listed price: $0.56 | $3.39 | Source09/07/2026 | |
| Moonshot AI | Via OpenRoutermoonshotai/int4 | $0.95 | $4 | Source09/07/2026 | |
| Novita | Via OpenRouternovita | $0.8 | $3.4 | Source09/07/2026 | |
| Parasail | Via OpenRouterparasail/int4 | $0.75 | $3.5 | Source09/07/2026 | |
| Phala | Via OpenRouterphala | $1.09 | $4.6 | Source09/07/2026 | |
| SiliconFlow | Via OpenRoutersiliconflow/fp8 | $0.77 | $3.4 | Source09/07/2026 | |
| StreamLake | Via OpenRouterstreamlake/fp8 | $0.5985 | $2.52 | Source09/07/2026 | |
| Venice | Via OpenRoutervenice/int4 | $0.75 | $3.5 | Source09/07/2026 |
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.
Capability profile from matched benchmarks
Each axis averages directly matched benchmark families. A value of 100 means the stronger value within this pair, not a universal quality score.
DeepSeek-V4-Flash
Kimi K2.6
Coding: 97.9 / 100 (1 benchmark family)
Reasoning: 98 / 100 (1 benchmark family)
Mathematics: 96.4 / 100 (1 benchmark family)
Knowledge: 98.2 / 100 (1 benchmark family)
Finance: 98.8 / 100 (1 benchmark family)
Legal: 99.2 / 100 (1 benchmark family)
Cybersecurity: 89.6 / 99.5 (1 benchmark family)
Health: 99.3 / 100 (1 benchmark family)
32 matched rows from 2 benchmark families were considered. The radar shows 8 of 9 comparable categories.
DeepSeek-V4-FlashKimi K2.6
CyberBenchOverall. Higher is better. No documented setup difference
DeepSeek-V4-Flash66.716 %
Kimi K2.6Winner74.351 %
LMArena Text, Style ControlOverall. Higher is better. No documented setup difference
DeepSeek-V4-Flash1,435.816
Kimi K2.6Winner1,460.613
CyberBenchPatch. Higher is better. No documented setup difference
DeepSeek-V4-FlashWinner72.414 %
Kimi K2.671.429 %
LMArena Text, Style ControlOverall. Higher is better. Test setup not documented as identical
DeepSeek-V4-Flash1,438.462
Kimi K2.6Higher measured value1,460.613
CyberBenchPoC. Higher is better. No documented setup difference
DeepSeek-V4-Flash61.017 %
Kimi K2.6Winner77.273 %
LMArena Text, Style ControlBusiness, management and finance. Higher is better. No documented setup difference
DeepSeek-V4-Flash1,437.854
Kimi K2.6Winner1,455.777
LMArena Text, Style ControlBusiness, management and finance. Higher is better. Test setup not documented as identical
DeepSeek-V4-Flash1,434.968
Kimi K2.6Higher measured value1,455.777
LMArena Text, Style ControlChinese. Higher is better. No documented setup difference
DeepSeek-V4-Flash1,472.677
Kimi K2.6Winner1,526.043
LMArena Text, Style ControlChinese. Higher is better. Test setup not documented as identical
DeepSeek-V4-Flash1,479.62
Kimi K2.6Higher measured value1,526.043
LMArena Text, Style ControlCoding. Higher is better. No documented setup difference
DeepSeek-V4-Flash1,483.101
Kimi K2.6Winner1,514.216
LMArena Text, Style ControlCoding. Higher is better. Test setup not documented as identical
DeepSeek-V4-Flash1,479.449
Kimi K2.6Higher measured value1,514.216
LMArena Text, Style ControlCreative writing. Higher is better. No documented setup difference
DeepSeek-V4-Flash1,408.18
Kimi K2.6Winner1,430.943
Key to the marks:better valuebetter, but not conclusivetie
| Benchmark and task | DeepSeek-V4-Flash | Kimi K2.6 | Source |
|---|---|---|---|
CyberBenchOverallTest detailsNo documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better | 66.716 % | Winner74.351 % | Vals AISource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlOverallTest detailsNo documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style control Kimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 48,963 anonymous pairwise votes.Kimi K2.6: Style-controlled Arena rating from 37,573 anonymous pairwise votes. | 1,435.816 95% confidence interval: ±4.15The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Winner1,460.613 95% confidence interval: ±4.534The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
CyberBenchPatchTest detailsNo documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better | Winner72.414 % | 71.429 % | Vals AISource detailsData as of: 08/03/2026 |
LMArena Text, Style ControlOverallTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style control Kimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 48,705 anonymous pairwise votes.Kimi K2.6: Style-controlled Arena rating from 37,573 anonymous pairwise votes. | 1,438.462 95% confidence interval: ±4.21The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,460.613 95% confidence interval: ±4.534The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
CyberBenchPoCTest detailsNo documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better | 61.017 % | Winner77.273 % | Vals AISource detailsData as of: 08/03/2026 |
LMArena Text, Style ControlBusiness, management and financeTest detailsNo documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style control Kimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 9,911 anonymous pairwise votes.Kimi K2.6: Style-controlled Arena rating from 7,489 anonymous pairwise votes. | 1,437.854 95% confidence interval: ±7.128The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Winner1,455.777 95% confidence interval: ±7.725The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlBusiness, management and financeTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style control Kimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 10,060 anonymous pairwise votes.Kimi K2.6: Style-controlled Arena rating from 7,489 anonymous pairwise votes. | 1,434.968 95% confidence interval: ±7.142The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,455.777 95% confidence interval: ±7.725The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlChineseTest detailsNo documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style control Kimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 2,530 anonymous pairwise votes.Kimi K2.6: Style-controlled Arena rating from 1,900 anonymous pairwise votes. | 1,472.677 95% confidence interval: ±12.483The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Winner1,526.043 95% confidence interval: ±14.272The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlChineseTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style control Kimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 2,509 anonymous pairwise votes.Kimi K2.6: Style-controlled Arena rating from 1,900 anonymous pairwise votes. | 1,479.62 95% confidence interval: ±12.459The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,526.043 95% confidence interval: ±14.272The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlCodingTest detailsNo documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style control Kimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 14,346 anonymous pairwise votes.Kimi K2.6: Style-controlled Arena rating from 10,419 anonymous pairwise votes. | 1,483.101 95% confidence interval: ±6.376The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Winner1,514.216 95% confidence interval: ±7.05The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlCodingTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style control Kimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 14,310 anonymous pairwise votes.Kimi K2.6: Style-controlled Arena rating from 10,419 anonymous pairwise votes. | 1,479.449 95% confidence interval: ±6.409The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,514.216 95% confidence interval: ±7.05The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlCreative writingTest detailsNo documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style control Kimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 7,972 anonymous pairwise votes.Kimi K2.6: Style-controlled Arena rating from 5,846 anonymous pairwise votes. | 1,408.18 95% confidence interval: ±7.747The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Winner1,430.943 95% confidence interval: ±8.493The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlCreative writingTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style control Kimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 8,029 anonymous pairwise votes.Kimi K2.6: Style-controlled Arena rating from 5,846 anonymous pairwise votes. | 1,408.903 95% confidence interval: ±7.781The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,430.943 95% confidence interval: ±8.493The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlEnglishTest detailsNo documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style control Kimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 21,931 anonymous pairwise votes.Kimi K2.6: Style-controlled Arena rating from 17,189 anonymous pairwise votes. | 1,445.287 95% confidence interval: ±5.383The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Winner1,467.466 95% confidence interval: ±5.735The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlEnglishTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style control Kimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 21,747 anonymous pairwise votes.Kimi K2.6: Style-controlled Arena rating from 17,189 anonymous pairwise votes. | 1,449.894 95% confidence interval: ±5.421The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,467.466 95% confidence interval: ±5.735The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlEntertainment, sports and mediaTest detailsNo documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style control Kimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 10,423 anonymous pairwise votes.Kimi K2.6: Style-controlled Arena rating from 7,644 anonymous pairwise votes. | 1,405.349 95% confidence interval: ±7.122The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Winner1,427.512 95% confidence interval: ±7.76The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlEntertainment, sports and mediaTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style control Kimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 10,655 anonymous pairwise votes.Kimi K2.6: Style-controlled Arena rating from 7,644 anonymous pairwise votes. | 1,406.152 95% confidence interval: ±7.06The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,427.512 95% confidence interval: ±7.76The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlExcluding tiesTest detailsNo documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style control Kimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 36,983 anonymous pairwise votes.Kimi K2.6: Style-controlled Arena rating from 27,810 anonymous pairwise votes. | 1,431.271 95% confidence interval: ±5.416The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Winner1,464.238 95% confidence interval: ±5.929The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlExcluding tiesTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style control Kimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 37,039 anonymous pairwise votes.Kimi K2.6: Style-controlled Arena rating from 27,810 anonymous pairwise votes. | 1,435.7 95% confidence interval: ±5.462The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,464.238 95% confidence interval: ±5.929The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlExpert promptsTest detailsNo documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style control Kimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 4,904 anonymous pairwise votes.Kimi K2.6: Style-controlled Arena rating from 3,516 anonymous pairwise votes. | 1,458.425 95% confidence interval: ±9.147The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Winner1,501.44 95% confidence interval: ±10.353The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlExpert promptsTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style control Kimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 4,907 anonymous pairwise votes.Kimi K2.6: Style-controlled Arena rating from 3,516 anonymous pairwise votes. | 1,467.744 95% confidence interval: ±9.211The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,501.44 95% confidence interval: ±10.353The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlFrenchTest detailsNo documented difference in the test setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style control Kimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 1,909 anonymous pairwise votes.Kimi K2.6: Style-controlled Arena rating from 1,500 anonymous pairwise votes. | 1,444.246 95% confidence interval: ±15.542The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | No clear lead1,473.951 95% confidence interval: ±17.102The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlFrenchTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style control Kimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 1,872 anonymous pairwise votes.Kimi K2.6: Style-controlled Arena rating from 1,500 anonymous pairwise votes. | 1,457.512 95% confidence interval: ±15.76The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,473.951 95% confidence interval: ±17.102The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlGermanTest detailsNo documented difference in the test setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style control Kimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 834 anonymous pairwise votes.Kimi K2.6: Style-controlled Arena rating from 734 anonymous pairwise votes. | 1,423.985 95% confidence interval: ±21.432The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | No clear lead1,458.134 95% confidence interval: ±21.649The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlGermanTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style control Kimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 881 anonymous pairwise votes.Kimi K2.6: Style-controlled Arena rating from 734 anonymous pairwise votes. | 1,434.001 95% confidence interval: ±20.992The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,458.134 95% confidence interval: ±21.649The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlHard promptsTest detailsNo documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style control Kimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 32,576 anonymous pairwise votes.Kimi K2.6: Style-controlled Arena rating from 24,328 anonymous pairwise votes. | 1,459.19 95% confidence interval: ±4.879The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Winner1,484.733 95% confidence interval: ±5.291The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlHard promptsTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style control Kimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 32,479 anonymous pairwise votes.Kimi K2.6: Style-controlled Arena rating from 24,328 anonymous pairwise votes. | 1,458.492 95% confidence interval: ±4.934The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,484.733 95% confidence interval: ±5.291The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlHard prompts, EnglishTest detailsNo documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style control Kimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 15,327 anonymous pairwise votes.Kimi K2.6: Style-controlled Arena rating from 11,753 anonymous pairwise votes. | 1,464.306 95% confidence interval: ±6.191The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Winner1,486.948 95% confidence interval: ±6.669The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlHard prompts, EnglishTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style control Kimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 15,135 anonymous pairwise votes.Kimi K2.6: Style-controlled Arena rating from 11,753 anonymous pairwise votes. | 1,465.194 95% confidence interval: ±6.261The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,486.948 95% confidence interval: ±6.669The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlInstruction followingTest detailsNo documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style control Kimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 16,772 anonymous pairwise votes.Kimi K2.6: Style-controlled Arena rating from 12,232 anonymous pairwise votes. | 1,428.139 95% confidence interval: ±5.955The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Winner1,453.473 95% confidence interval: ±6.475The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlInstruction followingTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style control Kimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 16,813 anonymous pairwise votes.Kimi K2.6: Style-controlled Arena rating from 12,232 anonymous pairwise votes. | 1,433.908 95% confidence interval: ±6.024The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,453.473 95% confidence interval: ±6.475The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlJapaneseTest detailsNo documented difference in the test setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style control Kimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 633 anonymous pairwise votes.Kimi K2.6: Style-controlled Arena rating from 468 anonymous pairwise votes. | 1,397.389 95% confidence interval: ±25.351The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | No clear lead1,443.926 95% confidence interval: ±29.086The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlJapaneseTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style control Kimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 600 anonymous pairwise votes.Kimi K2.6: Style-controlled Arena rating from 468 anonymous pairwise votes. | 1,422.217 95% confidence interval: ±25.99The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,443.926 95% confidence interval: ±29.086The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlKoreanTest detailsNo documented difference in the test setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style control Kimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 867 anonymous pairwise votes.Kimi K2.6: Style-controlled Arena rating from 712 anonymous pairwise votes. | 1,394.225 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. | No clear lead1,421.63 95% confidence interval: ±23.119The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlKoreanTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style control Kimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 909 anonymous pairwise votes.Kimi K2.6: Style-controlled Arena rating from 712 anonymous pairwise votes. | 1,374.943 95% confidence interval: ±21.551The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,421.63 95% confidence interval: ±23.119The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlLegal and governmentTest detailsNo documented difference in the test setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style control Kimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 3,892 anonymous pairwise votes.Kimi K2.6: Style-controlled Arena rating from 2,841 anonymous pairwise votes. | 1,449.174 95% confidence interval: ±10.185The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | No clear lead1,460.627 95% confidence interval: ±11.45The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlLegal and governmentTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style control Kimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 3,872 anonymous pairwise votes.Kimi K2.6: Style-controlled Arena rating from 2,841 anonymous pairwise votes. | 1,459.091 95% confidence interval: ±10.242The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,460.627 95% confidence interval: ±11.45The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlLife, physical and social scienceTest detailsNo documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style control Kimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 7,776 anonymous pairwise votes.Kimi K2.6: Style-controlled Arena rating from 6,229 anonymous pairwise votes. | 1,458.608 95% confidence interval: ±7.61The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Winner1,476.941 95% confidence interval: ±8.13The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlLife, physical and social scienceTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style control Kimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 7,968 anonymous pairwise votes.Kimi K2.6: Style-controlled Arena rating from 6,229 anonymous pairwise votes. | 1,460.882 95% confidence interval: ±7.588The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,476.941 95% confidence interval: ±8.13The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlLonger queriesTest detailsNo documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style control Kimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 21,561 anonymous pairwise votes.Kimi K2.6: Style-controlled Arena rating from 15,575 anonymous pairwise votes. | 1,448.456 95% confidence interval: ±5.733The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Winner1,475.676 95% confidence interval: ±6.237The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlLonger queriesTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style control Kimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 21,664 anonymous pairwise votes.Kimi K2.6: Style-controlled Arena rating from 15,575 anonymous pairwise votes. | 1,449.036 95% confidence interval: ±5.731The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,475.676 95% confidence interval: ±6.237The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlMathTest detailsNo documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style control Kimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 2,516 anonymous pairwise votes.Kimi K2.6: Style-controlled Arena rating from 1,936 anonymous pairwise votes. | 1,425.091 95% confidence interval: ±12.209The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Winner1,478.292 95% confidence interval: ±13.492The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlMathTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style control Kimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 2,459 anonymous pairwise votes.Kimi K2.6: Style-controlled Arena rating from 1,936 anonymous pairwise votes. | 1,441.301 95% confidence interval: ±12.311The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,478.292 95% confidence interval: ±13.492The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlMathematical professionsTest detailsNo documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style control Kimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 2,746 anonymous pairwise votes.Kimi K2.6: Style-controlled Arena rating from 2,051 anonymous pairwise votes. | 1,431.608 95% confidence interval: ±11.935The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Winner1,484.174 95% confidence interval: ±13.331The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlMathematical professionsTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style control Kimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 2,607 anonymous pairwise votes.Kimi K2.6: Style-controlled Arena rating from 2,051 anonymous pairwise votes. | 1,443.348 95% confidence interval: ±12.313The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,484.174 95% confidence interval: ±13.331The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlMedicine and healthcareTest detailsNo documented difference in the test setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style control Kimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 3,429 anonymous pairwise votes.Kimi K2.6: Style-controlled Arena rating from 2,701 anonymous pairwise votes. | 1,459.604 95% confidence interval: ±10.945The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | No clear lead1,469.999 95% confidence interval: ±11.959The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlMedicine and healthcareTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style control Kimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 3,495 anonymous pairwise votes.Kimi K2.6: Style-controlled Arena rating from 2,701 anonymous pairwise votes. | 1,462.945 95% confidence interval: ±10.866The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,469.999 95% confidence interval: ±11.959The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlMulti-turnTest detailsNo documented difference in the test setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style control Kimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 8,820 anonymous pairwise votes.Kimi K2.6: Style-controlled Arena rating from 6,558 anonymous pairwise votes. | 1,452.356 95% confidence interval: ±7.462The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | No clear lead1,459.745 95% confidence interval: ±8.178The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlMulti-turnTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style control Kimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 8,674 anonymous pairwise votes.Kimi K2.6: Style-controlled Arena rating from 6,558 anonymous pairwise votes. | 1,445.683 95% confidence interval: ±7.508The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,459.745 95% confidence interval: ±8.178The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlNon-EnglishTest detailsNo documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style control Kimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 27,030 anonymous pairwise votes.Kimi K2.6: Style-controlled Arena rating from 20,384 anonymous pairwise votes. | 1,423.067 95% confidence interval: ±5.056The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Winner1,449.236 95% confidence interval: ±5.442The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlNon-EnglishTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style control Kimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 26,956 anonymous pairwise votes.Kimi K2.6: Style-controlled Arena rating from 20,384 anonymous pairwise votes. | 1,422.651 95% confidence interval: ±5.123The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,449.236 95% confidence interval: ±5.442The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlPolishTest detailsNo documented difference in the test setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style control Kimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 1,005 anonymous pairwise votes.Kimi K2.6: Style-controlled Arena rating from 741 anonymous pairwise votes. | 1,439.462 95% confidence interval: ±18.965The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | No clear lead1,445.318 95% confidence interval: ±21.349The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlPolishTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style control Kimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 1,014 anonymous pairwise votes.Kimi K2.6: Style-controlled Arena rating from 741 anonymous pairwise votes. | 1,430.358 95% confidence interval: ±18.866The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,445.318 95% confidence interval: ±21.349The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlRussianTest detailsNo documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style control Kimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 5,250 anonymous pairwise votes.Kimi K2.6: Style-controlled Arena rating from 3,817 anonymous pairwise votes. | 1,433.186 95% confidence interval: ±8.845The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Winner1,453.006 95% confidence interval: ±9.898The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlRussianTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style control Kimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 5,207 anonymous pairwise votes.Kimi K2.6: Style-controlled Arena rating from 3,817 anonymous pairwise votes. | 1,437.38 95% confidence interval: ±8.983The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,453.006 95% confidence interval: ±9.898The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlSoftware and IT servicesTest detailsNo documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style control Kimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 20,105 anonymous pairwise votes.Kimi K2.6: Style-controlled Arena rating from 15,076 anonymous pairwise votes. | 1,471.075 95% confidence interval: ±5.634The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Winner1,503.051 95% confidence interval: ±6.107The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlSoftware and IT servicesTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style control Kimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 20,031 anonymous pairwise votes.Kimi K2.6: Style-controlled Arena rating from 15,076 anonymous pairwise votes. | 1,473.269 95% confidence interval: ±5.664The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,503.051 95% confidence interval: ±6.107The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlSpanishTest detailsNo documented difference in the test setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style control Kimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 1,548 anonymous pairwise votes.Kimi K2.6: Style-controlled Arena rating from 1,322 anonymous pairwise votes. | 1,433.026 95% confidence interval: ±16.368The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | No clear lead1,457.814 95% confidence interval: ±17.141The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlSpanishTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style control Kimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 1,443 anonymous pairwise votes.Kimi K2.6: Style-controlled Arena rating from 1,322 anonymous pairwise votes. | 1,431.772 95% confidence interval: ±16.888The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,457.814 95% confidence interval: ±17.141The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlWriting, literature and languageTest detailsNo documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style control Kimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 11,742 anonymous pairwise votes.Kimi K2.6: Style-controlled Arena rating from 8,865 anonymous pairwise votes. | 1,417.982 95% confidence interval: ±6.712The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Winner1,438.306 95% confidence interval: ±7.246The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlWriting, literature and languageTest detailsTest setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style control Kimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style controlDeepSeek-V4-Flash: Style-controlled Arena rating from 11,861 anonymous pairwise votes.Kimi K2.6: Style-controlled Arena rating from 8,865 anonymous pairwise votes. | 1,421.395 95% confidence interval: ±6.717The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,438.306 95% confidence interval: ±7.246The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | LMArenaSource detailsData as of: 09/01/2026 |
Key to the marks:better valuebetter, but not conclusivetie | |||
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.
The standard price table uses direct developer rates. The provider comparison labels OpenRouter endpoints, regions, and special tariffs separately.
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 DeepSeek-V4-Flash and Kimi K2.6 with other leading models using the same data and benchmark logic.