Head-to-head comparison
Grok 4.3 vs. DeepSeek-V4-Flash
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 | Grok 4.3 | DeepSeek-V4-Flash |
|---|---|---|
| Provider | xAI | DeepSeek |
| Released | May 6, 2026 | Apr 24, 2026 |
| Availability | Active | Preview |
| Model type | Proprietary | Open Weights |
| Parameters | Not published | 284B, 13B active |
| Architecture | Not published | Mixture of Experts |
| Context window | 1,000,000 tokens | 1,000,000 tokens |
| Knowledge cutoff | Not published | Not published |
| Technical sources | Model | Model |
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 | Grok 4.3 | DeepSeek-V4-Flash |
|---|---|---|
| API input | $1.25 ≤200K / $2.5 >200K | $0.14 |
| API output | $2.5 ≤200K / $5 >200K | $0.28 |
| Cache read | $0.2 ≤200K / $0.4 >200K | $0. |
| Cache write (5 min.) | Not listed | Not listed |
| Cache write (1 hr.) | Not listed | Not listed |
| Price verified | 08/11/2026 Source | 07/30/2026 Source |
Grok 4.3DeepSeek-V4-Flash
API inputUSD per 1M tokens, base tier
Grok 4.3$1.25
DeepSeek-V4-FlashLower price$0.14
API outputUSD per 1M tokens, base tier
Grok 4.3$2.5
DeepSeek-V4-FlashLower price$0.28
Cache readUSD per 1M tokens, base tier
Grok 4.3$0.2
DeepSeek-V4-FlashLower price$0.003
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 |
|---|---|---|---|---|---|
| Grok 4.3 | xAI | Direct from developerUp to 200,000 context tokens | Lowest listed price: $1.25 | Lowest listed price: $2.5 | Source08/11/2026 |
| xAI | Direct from developerAbove 200,000 context tokens | $2.5 | $5 | Source08/11/2026 | |
| xAI | Via OpenRouterxai | Lowest listed price: $1.25 | Lowest listed price: $2.5 | Source09/07/2026 | |
| xAI | Via OpenRouterxai/priority | $2.5 | $5 | Source09/07/2026 | |
| xAI | Via OpenRouterxai/zdr | Lowest listed price: $1.25 | Lowest listed price: $2.5 | Source09/07/2026 | |
| xAI | Via OpenRouterxai/zdr/priority | $2.5 | $5 | Source09/07/2026 | |
| 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 |
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.
Grok 4.3
DeepSeek-V4-Flash
Coding: 100 / 99.7 (1 benchmark family)
Reasoning: 99.7 / 100 (1 benchmark family)
Mathematics: 99.8 / 99.9 (1 benchmark family)
Knowledge: 99.8 / 100 (1 benchmark family)
Finance: 100 / 99.9 (1 benchmark family)
Legal: 99.1 / 100 (1 benchmark family)
Cybersecurity: 70 / 100 (1 benchmark family)
Health: 99.6 / 100 (1 benchmark family)
32 matched rows from 2 benchmark families were considered. The radar shows 8 of 9 comparable categories.
Grok 4.3DeepSeek-V4-Flash
CyberBenchOverall. Higher is better. No documented setup difference
Grok 4.347.457 %
DeepSeek-V4-FlashWinner66.716 %
LMArena Text, Style ControlOverall. Higher is better. No documented setup difference
Grok 4.3No clear lead1,442.599
DeepSeek-V4-Flash1,435.816
CyberBenchPatch. Higher is better. No documented setup difference
Grok 4.364.407 %
DeepSeek-V4-FlashWinner72.414 %
LMArena Text, Style ControlOverall. Higher is better. Test setup not documented as identical
Grok 4.3Higher measured value1,442.599
DeepSeek-V4-Flash1,438.462
CyberBenchPoC. Higher is better. No documented setup difference
Grok 4.330.508 %
DeepSeek-V4-FlashWinner61.017 %
LMArena Text, Style ControlBusiness, management and finance. Higher is better. No documented setup difference
Grok 4.3No clear lead1,439.103
DeepSeek-V4-Flash1,437.854
LMArena Text, Style ControlBusiness, management and finance. Higher is better. Test setup not documented as identical
Grok 4.3Higher measured value1,439.103
DeepSeek-V4-Flash1,434.968
LMArena Text, Style ControlChinese. Higher is better. No documented setup difference
Grok 4.3No clear lead1,479.363
DeepSeek-V4-Flash1,472.677
LMArena Text, Style ControlChinese. Higher is better. Test setup not documented as identical
Grok 4.31,479.363
DeepSeek-V4-FlashHigher measured value1,479.62
LMArena Text, Style ControlCoding. Higher is better. No documented setup difference
Grok 4.3No clear lead1,487.832
DeepSeek-V4-Flash1,483.101
LMArena Text, Style ControlCoding. Higher is better. Test setup not documented as identical
Grok 4.3Higher measured value1,487.832
DeepSeek-V4-Flash1,479.449
LMArena Text, Style ControlCreative writing. Higher is better. No documented setup difference
Grok 4.3Winner1,426.247
DeepSeek-V4-Flash1,408.18
Key to the marks:better valuebetter, but not conclusivetie
| Benchmark and task | Grok 4.3 | DeepSeek-V4-Flash | Source |
|---|---|---|---|
CyberBenchOverallTest detailsNo documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better | 47.457 % | Winner66.716 % | Vals AISource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlOverallTest detailsNo documented difference in the test setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGrok 4.3: Snapshot: grok-4.3, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style controlGrok 4.3: Style-controlled Arena rating from 65,024 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 48,963 anonymous pairwise votes. | No clear lead1,442.599 95% confidence interval: ±3.771The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 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. | LMArenaSource detailsData as of: 09/01/2026 |
CyberBenchPatchTest detailsNo documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better | 64.407 % | Winner72.414 % | 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 betterGrok 4.3: Snapshot: grok-4.3, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style controlGrok 4.3: Style-controlled Arena rating from 65,024 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 48,705 anonymous pairwise votes. | Higher measured value1,442.599 95% confidence interval: ±3.771The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 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. | LMArenaSource detailsData as of: 09/01/2026 |
CyberBenchPoCTest detailsNo documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better | 30.508 % | Winner61.017 % | Vals AISource detailsData as of: 08/03/2026 |
LMArena Text, Style ControlBusiness, management and financeTest detailsNo documented difference in the test setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGrok 4.3: Snapshot: grok-4.3, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style controlGrok 4.3: Style-controlled Arena rating from 13,131 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 9,911 anonymous pairwise votes. | No clear lead1,439.103 95% confidence interval: ±6.526The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 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. | 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 betterGrok 4.3: Snapshot: grok-4.3, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style controlGrok 4.3: Style-controlled Arena rating from 13,131 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 10,060 anonymous pairwise votes. | Higher measured value1,439.103 95% confidence interval: ±6.526The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 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. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlChineseTest detailsNo documented difference in the test setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGrok 4.3: Snapshot: grok-4.3, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style controlGrok 4.3: Style-controlled Arena rating from 3,641 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 2,530 anonymous pairwise votes. | No clear lead1,479.363 95% confidence interval: ±10.781The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 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. | 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 betterGrok 4.3: Snapshot: grok-4.3, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style controlGrok 4.3: Style-controlled Arena rating from 3,641 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 2,509 anonymous pairwise votes. | 1,479.363 95% confidence interval: ±10.781The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,479.62 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. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlCodingTest detailsNo documented difference in the test setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGrok 4.3: Snapshot: grok-4.3, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style controlGrok 4.3: Style-controlled Arena rating from 18,240 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 14,346 anonymous pairwise votes. | No clear lead1,487.832 95% confidence interval: ±5.841The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 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. | 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 betterGrok 4.3: Snapshot: grok-4.3, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style controlGrok 4.3: Style-controlled Arena rating from 18,240 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 14,310 anonymous pairwise votes. | Higher measured value1,487.832 95% confidence interval: ±5.841The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 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. | 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 betterGrok 4.3: Snapshot: grok-4.3, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style controlGrok 4.3: Style-controlled Arena rating from 11,624 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 7,972 anonymous pairwise votes. | Winner1,426.247 95% confidence interval: ±6.835The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 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. | 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 betterGrok 4.3: Snapshot: grok-4.3, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style controlGrok 4.3: Style-controlled Arena rating from 11,624 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 8,029 anonymous pairwise votes. | Higher measured value1,426.247 95% confidence interval: ±6.835The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 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. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlEnglishTest detailsNo documented difference in the test setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGrok 4.3: Snapshot: grok-4.3, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style controlGrok 4.3: Style-controlled Arena rating from 29,995 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 21,931 anonymous pairwise votes. | No clear lead1,451.255 95% confidence interval: ±4.882The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 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. | 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 betterGrok 4.3: Snapshot: grok-4.3, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style controlGrok 4.3: Style-controlled Arena rating from 29,995 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 21,747 anonymous pairwise votes. | Higher measured value1,451.255 95% confidence interval: ±4.882The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 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. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlEntertainment, sports and mediaTest detailsNo documented difference in the test setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGrok 4.3: Snapshot: grok-4.3, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style controlGrok 4.3: Style-controlled Arena rating from 15,321 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 10,423 anonymous pairwise votes. | No clear lead1,417.664 95% confidence interval: ±6.208The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 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. | 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 betterGrok 4.3: Snapshot: grok-4.3, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style controlGrok 4.3: Style-controlled Arena rating from 15,321 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 10,655 anonymous pairwise votes. | Higher measured value1,417.664 95% confidence interval: ±6.208The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 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. | 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 betterGrok 4.3: Snapshot: grok-4.3, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style controlGrok 4.3: Style-controlled Arena rating from 49,803 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 36,983 anonymous pairwise votes. | Winner1,441.685 95% confidence interval: ±4.957The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 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. | 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 betterGrok 4.3: Snapshot: grok-4.3, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style controlGrok 4.3: Style-controlled Arena rating from 49,803 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 37,039 anonymous pairwise votes. | Higher measured value1,441.685 95% confidence interval: ±4.957The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 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. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlExpert promptsTest detailsNo documented difference in the test setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGrok 4.3: Snapshot: grok-4.3, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style controlGrok 4.3: Style-controlled Arena rating from 6,726 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 4,904 anonymous pairwise votes. | 1,451.881 95% confidence interval: ±8.316The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | No clear lead1,458.425 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. | 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 betterGrok 4.3: Snapshot: grok-4.3, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style controlGrok 4.3: Style-controlled Arena rating from 6,726 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 4,907 anonymous pairwise votes. | 1,451.881 95% confidence interval: ±8.316The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,467.744 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. | 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 betterGrok 4.3: Snapshot: grok-4.3, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style controlGrok 4.3: Style-controlled Arena rating from 2,414 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 1,909 anonymous pairwise votes. | No clear lead1,462.38 95% confidence interval: ±14.479The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 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. | 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 betterGrok 4.3: Snapshot: grok-4.3, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style controlGrok 4.3: Style-controlled Arena rating from 2,414 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 1,872 anonymous pairwise votes. | Higher measured value1,462.38 95% confidence interval: ±14.479The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 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. | 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 betterGrok 4.3: Snapshot: grok-4.3, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style controlGrok 4.3: Style-controlled Arena rating from 964 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 834 anonymous pairwise votes. | No clear lead1,439.549 95% confidence interval: ±20.113The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 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. | 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 betterGrok 4.3: Snapshot: grok-4.3, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style controlGrok 4.3: Style-controlled Arena rating from 964 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 881 anonymous pairwise votes. | Higher measured value1,439.549 95% confidence interval: ±20.113The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 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. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlHard promptsTest detailsNo documented difference in the test setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGrok 4.3: Snapshot: grok-4.3, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style controlGrok 4.3: Style-controlled Arena rating from 43,360 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 32,576 anonymous pairwise votes. | 1,456.843 95% confidence interval: ±4.493The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | No clear lead1,459.19 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. | 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 betterGrok 4.3: Snapshot: grok-4.3, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style controlGrok 4.3: Style-controlled Arena rating from 43,360 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 32,479 anonymous pairwise votes. | 1,456.843 95% confidence interval: ±4.493The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,458.492 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. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlHard prompts, EnglishTest detailsNo documented difference in the test setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGrok 4.3: Snapshot: grok-4.3, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style controlGrok 4.3: Style-controlled Arena rating from 20,550 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 15,327 anonymous pairwise votes. | 1,461.646 95% confidence interval: ±5.658The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | No clear lead1,464.306 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. | 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 betterGrok 4.3: Snapshot: grok-4.3, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style controlGrok 4.3: Style-controlled Arena rating from 20,550 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 15,135 anonymous pairwise votes. | 1,461.646 95% confidence interval: ±5.658The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,465.194 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. | 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 betterGrok 4.3: Snapshot: grok-4.3, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style controlGrok 4.3: Style-controlled Arena rating from 22,697 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 16,772 anonymous pairwise votes. | 1,415.157 95% confidence interval: ±5.466The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Winner1,428.139 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. | 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 betterGrok 4.3: Snapshot: grok-4.3, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style controlGrok 4.3: Style-controlled Arena rating from 22,697 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 16,813 anonymous pairwise votes. | 1,415.157 95% confidence interval: ±5.466The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,433.908 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. | 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 betterGrok 4.3: Snapshot: grok-4.3, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style controlGrok 4.3: Style-controlled Arena rating from 758 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 633 anonymous pairwise votes. | No clear lead1,430.46 95% confidence interval: ±23.787The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 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. | 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 betterGrok 4.3: Snapshot: grok-4.3, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style controlGrok 4.3: Style-controlled Arena rating from 758 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 600 anonymous pairwise votes. | Higher measured value1,430.46 95% confidence interval: ±23.787The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 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. | 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 betterGrok 4.3: Snapshot: grok-4.3, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style controlGrok 4.3: Style-controlled Arena rating from 1,033 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 867 anonymous pairwise votes. | No clear lead1,403.868 95% confidence interval: ±20.122The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 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. | 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 betterGrok 4.3: Snapshot: grok-4.3, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style controlGrok 4.3: Style-controlled Arena rating from 1,033 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 909 anonymous pairwise votes. | Higher measured value1,403.868 95% confidence interval: ±20.122The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 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. | 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 betterGrok 4.3: Snapshot: grok-4.3, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style controlGrok 4.3: Style-controlled Arena rating from 5,269 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 3,892 anonymous pairwise votes. | 1,436.198 95% confidence interval: ±9.218The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | No clear lead1,449.174 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. | 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 betterGrok 4.3: Snapshot: grok-4.3, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style controlGrok 4.3: Style-controlled Arena rating from 5,269 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 3,872 anonymous pairwise votes. | 1,436.198 95% confidence interval: ±9.218The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,459.091 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. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlLife, physical and social scienceTest detailsNo documented difference in the test setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGrok 4.3: Snapshot: grok-4.3, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style controlGrok 4.3: Style-controlled Arena rating from 10,711 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 7,776 anonymous pairwise votes. | No clear lead1,459.558 95% confidence interval: ±6.907The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 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. | 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 betterGrok 4.3: Snapshot: grok-4.3, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style controlGrok 4.3: Style-controlled Arena rating from 10,711 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 7,968 anonymous pairwise votes. | 1,459.558 95% confidence interval: ±6.907The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,460.882 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. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlLonger queriesTest detailsNo documented difference in the test setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGrok 4.3: Snapshot: grok-4.3, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style controlGrok 4.3: Style-controlled Arena rating from 29,763 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 21,561 anonymous pairwise votes. | 1,444.978 95% confidence interval: ±5.193The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | No clear lead1,448.456 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. | 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 betterGrok 4.3: Snapshot: grok-4.3, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style controlGrok 4.3: Style-controlled Arena rating from 29,763 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 21,664 anonymous pairwise votes. | 1,444.978 95% confidence interval: ±5.193The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,449.036 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. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlMathTest detailsNo documented difference in the test setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGrok 4.3: Snapshot: grok-4.3, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style controlGrok 4.3: Style-controlled Arena rating from 3,085 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 2,516 anonymous pairwise votes. | 1,420.441 95% confidence interval: ±11.372The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | No clear lead1,425.091 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. | 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 betterGrok 4.3: Snapshot: grok-4.3, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style controlGrok 4.3: Style-controlled Arena rating from 3,085 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 2,459 anonymous pairwise votes. | 1,420.441 95% confidence interval: ±11.372The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,441.301 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. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlMathematical professionsTest detailsNo documented difference in the test setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGrok 4.3: Snapshot: grok-4.3, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style controlGrok 4.3: Style-controlled Arena rating from 3,463 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 2,746 anonymous pairwise votes. | No clear lead1,435.264 95% confidence interval: ±10.919The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 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. | 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 betterGrok 4.3: Snapshot: grok-4.3, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style controlGrok 4.3: Style-controlled Arena rating from 3,463 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 2,607 anonymous pairwise votes. | 1,435.264 95% confidence interval: ±10.919The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,443.348 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. | 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 betterGrok 4.3: Snapshot: grok-4.3, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style controlGrok 4.3: Style-controlled Arena rating from 4,838 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 3,429 anonymous pairwise votes. | 1,453.942 95% confidence interval: ±9.624The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | No clear lead1,459.604 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. | 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 betterGrok 4.3: Snapshot: grok-4.3, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style controlGrok 4.3: Style-controlled Arena rating from 4,838 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 3,495 anonymous pairwise votes. | 1,453.942 95% confidence interval: ±9.624The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | Higher measured value1,462.945 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. | 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 betterGrok 4.3: Snapshot: grok-4.3, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style controlGrok 4.3: Style-controlled Arena rating from 11,780 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 8,820 anonymous pairwise votes. | 1,445.801 95% confidence interval: ±6.771The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | No clear lead1,452.356 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. | 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 betterGrok 4.3: Snapshot: grok-4.3, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style controlGrok 4.3: Style-controlled Arena rating from 11,780 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 8,674 anonymous pairwise votes. | Higher measured value1,445.801 95% confidence interval: ±6.771The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 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. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlNon-EnglishTest detailsNo documented difference in the test setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGrok 4.3: Snapshot: grok-4.3, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style controlGrok 4.3: Style-controlled Arena rating from 35,028 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 27,030 anonymous pairwise votes. | No clear lead1,429.644 95% confidence interval: ±4.672The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 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. | 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 betterGrok 4.3: Snapshot: grok-4.3, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style controlGrok 4.3: Style-controlled Arena rating from 35,028 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 26,956 anonymous pairwise votes. | Higher measured value1,429.644 95% confidence interval: ±4.672The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 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. | 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 betterGrok 4.3: Snapshot: grok-4.3, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style controlGrok 4.3: Style-controlled Arena rating from 1,119 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 1,005 anonymous pairwise votes. | No clear lead1,445.93 95% confidence interval: ±18.315The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 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. | 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 betterGrok 4.3: Snapshot: grok-4.3, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style controlGrok 4.3: Style-controlled Arena rating from 1,119 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 1,014 anonymous pairwise votes. | Higher measured value1,445.93 95% confidence interval: ±18.315The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 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. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlRussianTest detailsNo documented difference in the test setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGrok 4.3: Snapshot: grok-4.3, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style controlGrok 4.3: Style-controlled Arena rating from 6,575 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 5,250 anonymous pairwise votes. | No clear lead1,442.007 95% confidence interval: ±8.161The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 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. | 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 betterGrok 4.3: Snapshot: grok-4.3, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style controlGrok 4.3: Style-controlled Arena rating from 6,575 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 5,207 anonymous pairwise votes. | Higher measured value1,442.007 95% confidence interval: ±8.161The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 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. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlSoftware and IT servicesTest detailsNo documented difference in the test setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGrok 4.3: Snapshot: grok-4.3, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style controlGrok 4.3: Style-controlled Arena rating from 26,092 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 20,105 anonymous pairwise votes. | No clear lead1,479.252 95% confidence interval: ±5.165The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 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. | 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 betterGrok 4.3: Snapshot: grok-4.3, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style controlGrok 4.3: Style-controlled Arena rating from 26,092 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 20,031 anonymous pairwise votes. | Higher measured value1,479.252 95% confidence interval: ±5.165The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 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. | 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 betterGrok 4.3: Snapshot: grok-4.3, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style controlGrok 4.3: Style-controlled Arena rating from 1,920 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 1,548 anonymous pairwise votes. | No clear lead1,441.657 95% confidence interval: ±15.181The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 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. | 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 betterGrok 4.3: Snapshot: grok-4.3, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style controlGrok 4.3: Style-controlled Arena rating from 1,920 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 1,443 anonymous pairwise votes. | Higher measured value1,441.657 95% confidence interval: ±15.181The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 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. | LMArenaSource detailsData as of: 09/01/2026 |
LMArena Text, Style ControlWriting, literature and languageTest detailsNo documented difference in the test setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGrok 4.3: Snapshot: grok-4.3, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style controlGrok 4.3: Style-controlled Arena rating from 16,563 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 11,742 anonymous pairwise votes. | No clear lead1,425.635 95% confidence interval: ±6The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 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. | 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 betterGrok 4.3: Snapshot: grok-4.3, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style controlGrok 4.3: Style-controlled Arena rating from 16,563 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 11,861 anonymous pairwise votes. | Higher measured value1,425.635 95% confidence interval: ±6The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 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. | 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 Grok 4.3 and DeepSeek-V4-Flash with other leading models using the same data and benchmark logic.