Skip to main content

Head-to-head comparison

Grok 4.5 vs. Grok 4.3

Compare published benchmark results from matching versions and cohorts, API pricing, and technical specifications. Any documented test setup differences remain visible.

shared result series
199
distinct benchmarks
24
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.

Specifications for Grok 4.5 and Grok 4.3
AttributeGrok 4.5Grok 4.3
ProviderxAIxAI
ReleasedJul 16, 2026May 6, 2026
AvailabilityActiveActive
Model typeProprietaryProprietary
ParametersNot publishedNot published
ArchitectureNot publishedNot published
Context window500,000 tokens1,000,000 tokens
Knowledge cutoffFebruary 1, 2026Not published
Technical sourcesModelModel

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.

API pricing for Grok 4.5 and Grok 4.3
Price typeGrok 4.5Grok 4.3
API input$2 ≤200K / $4 >200K$1.25 ≤200K / $2.5 >200K
API output$6 ≤200K / $12 >200K$2.5 ≤200K / $5 >200K
Cache read$0.3 ≤200K / $0.6 >200K$0.2 ≤200K / $0.4 >200K
Cache write (5 min.)Not listedNot listed
Cache write (1 hr.)Not listedNot listed
Price verified08/11/2026 Source08/11/2026 Source
Grok 4.5Grok 4.3
API inputUSD per 1M tokens, base tier
Grok 4.5$2
Grok 4.3Lower price$1.25
API outputUSD per 1M tokens, base tier
Grok 4.5$6
Grok 4.3Lower price$2.5
Cache readUSD per 1M tokens, base tier
Grok 4.5$0.3
Grok 4.3Lower price$0.2

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.

Provider pricing for Grok 4.5 and Grok 4.3
ModelProviderPurchase route and tariffInput per 1M tokensOutput per 1M tokensSource
Grok 4.5xAIDirect from developerUp to 200,000 context tokensLowest listed price: $2Lowest listed price: $6Source08/11/2026
xAIDirect from developerAbove 200,000 context tokens$4$12Source08/11/2026
xAIVia OpenRouterxaiLowest listed price: $2Lowest listed price: $6Source09/06/2026
xAIVia OpenRouterxai/priority$4$12Source09/06/2026
xAIVia OpenRouterxai/zdrLowest listed price: $2Lowest listed price: $6Source09/06/2026
xAIVia OpenRouterxai/zdr/priority$4$12Source09/06/2026
Grok 4.3xAIDirect from developerUp to 200,000 context tokensLowest listed price: $1.25Lowest listed price: $2.5Source08/11/2026
xAIDirect from developerAbove 200,000 context tokens$2.5$5Source08/11/2026
xAIVia OpenRouterxaiLowest listed price: $1.25Lowest listed price: $2.5Source09/06/2026
xAIVia OpenRouterxai/priority$2.5$5Source09/06/2026
xAIVia OpenRouterxai/zdrLowest listed price: $1.25Lowest listed price: $2.5Source09/06/2026
xAIVia OpenRouterxai/zdr/priority$2.5$5Source09/06/2026

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.

255075100CodingReasoningMathematicsKnowledgeFinanceLegalAgentic tasksMultimodal
Grok 4.5
Grok 4.3
Coding: 100 / 64.1 (6 benchmark families)
Reasoning: 100 / 97.9 (2 benchmark families)
Mathematics: 100 / 96.1 (1 benchmark family)
Knowledge: 100 / 96.7 (2 benchmark families)
Finance: 99.7 / 80.7 (6 benchmark families)
Legal: 100 / 80.4 (4 benchmark families)
Agentic tasks: 100 / 57.7 (2 benchmark families)
Multimodal: 74.4 / 100 (1 benchmark family)

163 matched rows from 24 benchmark families were considered. The radar shows 8 of 12 comparable categories.

Grok 4.5Grok 4.3
Code MigrationOverall. Higher is better. No documented setup difference
Grok 4.5Winner36.596 %
Grok 4.36.795 %
CorpFin v2Overall. Higher is better. No documented setup difference
Grok 4.567.405 %
Grok 4.3Winner68.532 %
EMBOverall. Higher is better. No documented setup difference
Grok 4.5Winner52.911 %
Grok 4.318.394 %
Finance Agent (v2)Overall. Higher is better. No documented setup difference
Grok 4.5Winner48.349 %
Grok 4.337.728 %
GPQA DiamondOverall. Higher is better. No documented setup difference
Grok 4.5Winner92.929 %
Grok 4.391.414 %
Harvey's Legal Agent BenchmarkOverall · Task fully resolved. Higher is better. No documented setup difference
Grok 4.5Winner12.917 %
Grok 4.30.417 %
Legal Research BenchOverall · All-pass. Higher is better. No documented setup difference
Grok 4.5Winner37.981 %
Grok 4.315.385 %
LegalBenchOverall. Higher is better. No documented setup difference
Grok 4.5Winner85.965 %
Grok 4.384.458 %
LiveCodeBench v6Overall. Higher is better. No documented setup difference
Grok 4.5Winner87.351 %
Grok 4.384.494 %
LMArena Text, Style ControlOverall. Higher is better. No documented setup difference
Grok 4.5Winner1,470.015
Grok 4.31,442.599
MedCodeOverall. Higher is better. No documented setup difference
Grok 4.5Winner43.291 %
Grok 4.338.068 %
MedScribeOverall. Higher is better. No documented setup difference
Grok 4.5Winner86.884 %
Grok 4.374.399 %

Key to the marks:better valuebetter, but not conclusivetie

Benchmark scores for Grok 4.5 and Grok 4.3
Benchmark and taskGrok 4.5Grok 4.3Source
Code MigrationOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better
Winner36.596 %
6.795 %
Vals AI
Source details
Data as of: 09/03/2026
CorpFin v2Overall
Test details
No documented difference in the test setupVersion: 2Metric: accuracyScoring: Higher is better
67.405 %
Winner68.532 %
Vals AI
Source details
Data as of: 08/12/2026
EMBOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better
Winner52.911 %
18.394 %
Vals AI
Source details
Data as of: 09/03/2026
Finance Agent (v2)Overall
Test details
No documented difference in the test setupVersion: 2Metric: accuracyScoring: Higher is better
Winner48.349 %
37.728 %
Vals AI
Source details
Data as of: 09/03/2026
GPQA DiamondOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better
Winner92.929 %
91.414 %
Vals AI
Source details
Data as of: 09/01/2026
Harvey's Legal Agent BenchmarkOverall · Task fully resolved
Test details
No documented difference in the test setupVersion: 1Metric: task resolution rateScoring: Higher is better
Winner12.917 %
0.417 %
Vals AI
Source details
Data as of: 09/03/2026
Legal Research BenchOverall · All-pass
Test details
No documented difference in the test setupVersion: 1Metric: all-pass rateScoring: Higher is better
Winner37.981 %
15.385 %
Vals AI
Source details
Data as of: 09/03/2026
LegalBenchOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better
Winner85.965 %
84.458 %
Vals AI
Source details
Data as of: 09/01/2026
LiveCodeBench v6Overall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better
Winner87.351 %
84.494 %
Vals AI
Source details
Data as of: 09/01/2026
LMArena Text, Style ControlOverall
Test details
No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGrok 4.5: Snapshot: grok-4.5, Harness: Arena text, style control
Grok 4.3: Snapshot: grok-4.3, Harness: Arena text, style controlGrok 4.5: Style-controlled Arena rating from 25,873 anonymous pairwise votes.Grok 4.3: Style-controlled Arena rating from 65,024 anonymous pairwise votes.
Winner1,470.015
95% confidence interval: ±4.921The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,442.599
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.		LMArena
Source details
Data as of: 09/01/2026
MedCodeOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better
Winner43.291 %
38.068 %
Vals AI
Source details
Data as of: 09/03/2026
MedScribeOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better
Winner86.884 %
74.399 %
Vals AI
Source details
Data as of: 09/03/2026
MMLU-ProOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better
Winner89.216 %
85.838 %
Vals AI
Source details
Data as of: 09/01/2026
MMMU-ProOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better
61.792 %
Winner83.064 %
Vals AI
Source details
Data as of: 09/01/2026
MortgageTaxOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better
Winner61.804 %
48.252 %
Vals AI
Source details
Data as of: 09/01/2026
ProgramBenchOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better
Tie0 %
Tie0 %
Vals AI
Source details
Data as of: 09/01/2026
SAGEOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better
Winner34.967 %
19.736 %
Vals AI
Source details
Data as of: 09/03/2026
SkillsBenchOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Harness: OpenHands
Winner66.034 %
40.638 %
Vals AI
Source details
Data as of: 09/01/2026
SWE-bench VerifiedOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better
Winner86.6 %
71.4 %
Vals AI
Source details
Data as of: 09/01/2026
TaxEval v2Overall
Test details
No documented difference in the test setupVersion: 2Metric: accuracyScoring: Higher is better
Winner71.668 %
70.81 %
Vals AI
Source details
Data as of: 09/01/2026
Terminal-Bench 2.1Overall
Test details
No documented difference in the test setupVersion: 2.1Metric: accuracyScoring: Higher is better
Winner67.79 %
41.948 %
Vals AI
Source details
Data as of: 09/03/2026
Vals IndexOverall
Test details
No documented difference in the test setupVersion: 2Metric: weighted index scoreScoring: Higher is better
Winner51.528 %
24.294 %
Vals AI
Source details
Data as of: 09/03/2026
Vals Multimodal IndexOverall
Test details
No documented difference in the test setupVersion: 1.2Metric: weighted index scoreScoring: Higher is better
Winner63.42 %
43.293 %
Vals AI
Source details
Data as of: 08/11/2026
Vibe Code Bench v1.1Overall
Test details
No documented difference in the test setupVersion: 1.1Metric: accuracyScoring: Higher is betterSettings: Harness: OpenHands
Winner69.002 %
19.403 %
Vals AI
Source details
Data as of: 09/03/2026
Code MigrationCLI
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Reasoning: high, Temperature: 0.7, Top P: 0.95
Winner25.461 %
9.06 %
Vals AI
Source details
Data as of: 08/09/2026
CorpFin v2Exact Pages
Test details
Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterGrok 4.5: Reasoning: high, Temperature: 0.7, Top P: 0.95
Grok 4.3: Temperature: 0.7, Top P: 0.95
66.317 %
Higher measured value66.783 %
Vals AI
Source details
Data as of: 08/06/2026
EMBComps
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Reasoning: high, Temperature: 0.7, Top P: 0.95
Winner39.489 %
16.558 %
Vals AI
Source details
Data as of: 08/06/2026
Finance Agent (v2)Adjustments
Test details
No documented difference in the test setupVersion: 2Metric: accuracyScoring: Higher is betterSettings: Reasoning: high, Temperature: 0.7, Top P: 0.95
Winner38.568 %
31.863 %
Vals AI
Source details
Data as of: 08/06/2026
GPQA DiamondFew-Shot CoT
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGrok 4.5: Reasoning: high, Temperature: 0.7, Top P: 0.95
Grok 4.3: Temperature: 0.7, Top P: 0.95
No direct winner92.929 %
No direct winner92.929 %
Vals AI
Source details
Data as of: 08/09/2026
Harvey's Legal Agent BenchmarkAntitrust Competition · Criteria passed
Test details
No documented difference in the test setupVersion: 1Metric: criteria pass rateScoring: Higher is betterSettings: Reasoning: high, Temperature: 0.7, Top P: 0.95
Winner87.319 %
61.594 %
Vals AI
Source details
Data as of: 08/07/2026
Legal Research BenchAdministrative / Regulatory · All-pass
Test details
No documented difference in the test setupVersion: 1Metric: all-pass rateScoring: Higher is betterSettings: Reasoning: high, Temperature: 0.7, Top P: 0.95
Winner51.515 %
25.758 %
Vals AI
Source details
Data as of: 08/06/2026
LegalBenchConclusion Tasks
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGrok 4.5: Reasoning: high, Temperature: 0.7, Top P: 0.95
Grok 4.3: Temperature: 0.7, Top P: 0.95
89.507 %
Higher measured value89.912 %
Vals AI
Source details
Data as of: 08/09/2026
LiveCodeBench v6Easy
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGrok 4.5: Reasoning: high, Temperature: 0.7, Top P: 0.95
Grok 4.3: Temperature: 0.7, Top P: 0.95
Higher measured value99.068 %
98.447 %
Vals AI
Source details
Data as of: 08/09/2026
LMArena Text, Style ControlBusiness, management and finance
Test details
No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGrok 4.5: Snapshot: grok-4.5, Harness: Arena text, style control
Grok 4.3: Snapshot: grok-4.3, Harness: Arena text, style controlGrok 4.5: Style-controlled Arena rating from 5,122 anonymous pairwise votes.Grok 4.3: Style-controlled Arena rating from 13,131 anonymous pairwise votes.
Winner1,465.734
95% confidence interval: ±8.936The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,439.103
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.		LMArena
Source details
Data as of: 09/01/2026
MMLU-ProBiology
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGrok 4.5: Reasoning: high, Temperature: 0.7, Top P: 0.95
Grok 4.3: Temperature: 0.7, Top P: 0.95
Higher measured value94.282 %
93.305 %
Vals AI
Source details
Data as of: 08/09/2026
MortgageTaxNumerical Extraction
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGrok 4.5: Reasoning: high, Temperature: 0.7, Top P: 0.95
Grok 4.3: Temperature: 0.7, Top P: 0.95, Output limit: 256,000 tokens
Higher measured value62.798 %
37.52 %
Vals AI
Source details
Data as of: 08/09/2026
ProgramBenchAlmost Resolved
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Reasoning: high, Temperature: 0.7, Top P: 0.95
Winner4.5 %
0 %
Vals AI
Source details
Data as of: 08/09/2026
SAGEAutomata
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGrok 4.5: Reasoning: high, Temperature: 1, Top P: 0.95, Output limit: 30,000 tokens
Grok 4.3: Temperature: 1, Top P: 0.95, Output limit: 30,000 tokens
32.54 %
Higher measured value35.318 %
Vals AI
Source details
Data as of: 08/09/2026
SkillsBenchNo Skills
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Reasoning: high, Harness: OpenHands, Temperature: 0.7, Top P: 0.95
Winner48.808 %
19.305 %
Vals AI
Source details
Data as of: 08/07/2026
SWE-bench Verified<15 min fix
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Reasoning: high, Temperature: 0.7, Top P: 0.95
Winner93.814 %
83.505 %
Vals AI
Source details
Data as of: 08/08/2026
TaxEval v2Correctness
Test details
Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterGrok 4.5: Reasoning: high, Temperature: 0.7, Top P: 0.95
Grok 4.3: Temperature: 0.7, Top P: 0.95
Higher measured value62.551 %
60.589 %
Vals AI
Source details
Data as of: 08/09/2026
Terminal-Bench 2.1Easy
Test details
No documented difference in the test setupVersion: 2.1Metric: accuracyScoring: Higher is betterSettings: Reasoning: high, Temperature: 0.7, Top P: 0.95
Winner91.667 %
75 %
Vals AI
Source details
Data as of: 08/06/2026
Vals IndexCorpFin v2
Test details
No documented difference in the test setupVersion: 1.2Metric: benchmark scoreScoring: Higher is betterSettings: Reasoning: high, Temperature: 0.7, Top P: 0.95
68.415 %
Winner70.047 %
Vals AI
Source details
Data as of: 08/09/2026
Vals Multimodal IndexCorpFin v2
Test details
No documented difference in the test setupVersion: 1.2Metric: benchmark scoreScoring: Higher is betterSettings: Reasoning: high, Temperature: 0.7, Top P: 0.95
68.415 %
Winner70.047 %
Vals AI
Source details
Data as of: 08/09/2026
Code MigrationCOBOL
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Reasoning: high, Temperature: 0.7, Top P: 0.95
Winner70 %
0 %
Vals AI
Source details
Data as of: 08/09/2026
CorpFin v2Max Fitting Context
Test details
Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterGrok 4.5: Reasoning: high, Temperature: 0.7, Top P: 0.95
Grok 4.3: Temperature: 0.7, Top P: 0.95
67.483 %
Higher measured value68.765 %
Vals AI
Source details
Data as of: 08/06/2026
EMBDataroom
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Reasoning: high, Temperature: 0.7, Top P: 0.95
Winner64.953 %
29.176 %
Vals AI
Source details
Data as of: 08/06/2026
Finance Agent (v2)All-Pass
Test details
No documented difference in the test setupVersion: 2Metric: accuracyScoring: Higher is betterSettings: Reasoning: high, Temperature: 0.7, Top P: 0.95
Winner36.743 %
26.373 %
Vals AI
Source details
Data as of: 08/06/2026
GPQA DiamondZero-Shot CoT
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGrok 4.5: Reasoning: high, Temperature: 0.7, Top P: 0.95
Grok 4.3: Temperature: 0.7, Top P: 0.95
Higher measured value92.929 %
89.899 %
Vals AI
Source details
Data as of: 08/09/2026
Harvey's Legal Agent BenchmarkAntitrust Competition · Task fully resolved
Test details
No documented difference in the test setupVersion: 1Metric: task resolution rateScoring: Higher is betterSettings: Reasoning: high, Temperature: 0.7, Top P: 0.95
Tie0 %
Tie0 %
Vals AI
Source details
Data as of: 08/07/2026
Legal Research BenchAdministrative / Regulatory · Weighted partial credit
Test details
No documented difference in the test setupVersion: 1Metric: weighted partial-credit scoreScoring: Higher is betterSettings: Reasoning: high, Temperature: 0.7, Top P: 0.95
Winner88.75 %
73.866 %
Vals AI
Source details
Data as of: 08/06/2026
LegalBenchInterpretation Tasks
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGrok 4.5: Reasoning: high, Temperature: 0.7, Top P: 0.95
Grok 4.3: Temperature: 0.7, Top P: 0.95
Higher measured value83.22 %
81.805 %
Vals AI
Source details
Data as of: 08/09/2026
LiveCodeBench v6Hard
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGrok 4.5: Reasoning: high, Temperature: 0.7, Top P: 0.95
Grok 4.3: Temperature: 0.7, Top P: 0.95
Higher measured value73.429 %
66 %
Vals AI
Source details
Data as of: 08/09/2026
LMArena Text, Style ControlChinese
Test details
No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGrok 4.5: Snapshot: grok-4.5, Harness: Arena text, style control
Grok 4.3: Snapshot: grok-4.3, Harness: Arena text, style controlGrok 4.5: Style-controlled Arena rating from 1,737 anonymous pairwise votes.Grok 4.3: Style-controlled Arena rating from 3,641 anonymous pairwise votes.
Winner1,512.8
95% confidence interval: ±15.002The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
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.		LMArena
Source details
Data as of: 09/01/2026
MMLU-ProBusiness
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGrok 4.5: Reasoning: high, Temperature: 0.7, Top P: 0.95
Grok 4.3: Temperature: 0.7, Top P: 0.95
Higher measured value93.283 %
92.902 %
Vals AI
Source details
Data as of: 08/09/2026
MortgageTaxSemantic Extraction
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGrok 4.5: Reasoning: high, Temperature: 0.7, Top P: 0.95
Grok 4.3: Temperature: 0.7, Top P: 0.95, Output limit: 256,000 tokens
Higher measured value60.811 %
58.983 %
Vals AI
Source details
Data as of: 08/09/2026
ProgramBenchFully Resolved
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Reasoning: high, Temperature: 0.7, Top P: 0.95
Tie0 %
Tie0 %
Vals AI
Source details
Data as of: 08/09/2026
SAGECalculus
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGrok 4.5: Reasoning: high, Temperature: 1, Top P: 0.95, Output limit: 30,000 tokens
Grok 4.3: Temperature: 1, Top P: 0.95, Output limit: 30,000 tokens
Higher measured value59.568 %
48.148 %
Vals AI
Source details
Data as of: 08/09/2026
SkillsBenchWith Skills
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Reasoning: high, Harness: OpenHands, Temperature: 0.7, Top P: 0.95
Winner66.034 %
40.638 %
Vals AI
Source details
Data as of: 08/07/2026
SWE-bench Verified>4 hours
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Reasoning: high, Temperature: 0.7, Top P: 0.95
Winner66.667 %
33.333 %
Vals AI
Source details
Data as of: 08/08/2026
TaxEval v2Stepwise Reasoning
Test details
Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterGrok 4.5: Reasoning: high, Temperature: 0.7, Top P: 0.95
Grok 4.3: Temperature: 0.7, Top P: 0.95
80.785 %
Higher measured value81.03 %
Vals AI
Source details
Data as of: 08/09/2026
Terminal-Bench 2.1Hard
Test details
No documented difference in the test setupVersion: 2.1Metric: accuracyScoring: Higher is betterSettings: Reasoning: high, Temperature: 0.7, Top P: 0.95
Winner56.667 %
14.444 %
Vals AI
Source details
Data as of: 08/06/2026
Vals IndexFinance Agent v2
Test details
No documented difference in the test setupVersion: 1.2Metric: benchmark scoreScoring: Higher is betterSettings: Reasoning: high, Temperature: 0.7, Top P: 0.95
Winner48.751 %
37.766 %
Vals AI
Source details
Data as of: 08/09/2026
Vals Multimodal IndexFinance Agent v2
Test details
No documented difference in the test setupVersion: 1.2Metric: benchmark scoreScoring: Higher is betterSettings: Reasoning: high, Temperature: 0.7, Top P: 0.95
Winner48.751 %
37.766 %
Vals AI
Source details
Data as of: 08/09/2026

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 4.5 and Grok 4.3 with other leading models using the same data and benchmark logic.

View the complete LLM comparison