Model profile
Grok 4.3
Evidence coverage
25 of 323 tracked benchmarks are published. 2 are verified and 23 provisional. 6 of 8 categories are measured.
- Published / tracked
- 25 / 323
- Verified
- 2
- Provisional
- 23
- Categories with evidence
- 6 / 8
Evidence by category
- Agentic7 benchmarksMixed evidence
- Coding3 benchmarksReported
- Reasoning2 benchmarksReported
- Knowledge8 benchmarksReported
- Math0 benchmarksNot measured
- Multilingual0 benchmarksNot measured
- Multimodal3 benchmarksReported
- Inst. Following2 benchmarksReported
Grok 4.3 ranks #31 out of 200 models on the public leaderboard with an overall score of 65.1/100. It also ranks #26 out of 99 on the verified leaderboard. While not a frontier model, it offers specific advantages depending on the use case.
Grok 4.3 is a proprietary model with a 1M token context window. It uses explicit chain-of-thought reasoning, which typically improves performance on math and complex reasoning tasks at the cost of higher latency and token usage.
This profile currently has 25 of 323 tracked benchmarks. BenchLM only exposes non-generated benchmark rows publicly, so missing categories stay blank until a sourced evaluation is available.
Its strongest category is Instruction Following (#6), while its weakest is Agentic (#119). This performance profile makes it a well-rounded choice across a range of tasks.
Peer position
Exact provisional scores and ranks for the closest listed peers. A score can appear before a model clears the evidence threshold for a rank, so equal scores can have different rank states.
Range 64.18–65.32
- Claude Sonnet 5AnthropicCompare#2965.32Claude Sonnet 5 is #29 with a score of 65.32.
- Qwen3.6 PlusAlibabaCompare#3065.2Qwen3.6 Plus is #30 with a score of 65.2.
- Grok 4.3Current modelxAI#3165.1Grok 4.3 is #31 with a score of 65.1.
- Claude Sonnet 4.6AnthropicCompare#3265.07Claude Sonnet 4.6 is #32 with a score of 65.07.
- Gemini 3.5 FlashGoogleCompare#3364.75Gemini 3.5 Flash is #33 with a score of 64.75.
- Claude Opus 4.5AnthropicCompare#3464.22Claude Opus 4.5 is #34 with a score of 64.22.
- Claude Opus 4.6 (Adaptive)AnthropicCompare#3564.18Claude Opus 4.6 (Adaptive) is #35 with a score of 64.18.
Category percentile
More
Relative position among models eligible for each sourced category. A higher percentile means a stronger position within that category's ranked cohort; 100 is highest.
- Inst. Following83%Eligible cohort rank #6 of 31Category score 91.2
- Knowledge16%Eligible cohort rank #44 of 52Category score 57.0
- Coding12%Eligible cohort rank #107 of 122Category score 39.4
- Agentic0%Eligible cohort rank #119 of 119Category score 6.3
Category evidence
Scores and ranks appear only where this model has published benchmark evidence. Categories without displayable source records remain not measured.
| Category | Score | Rank | Percentile | Weight | Benchmarks | Evidence |
|---|---|---|---|---|---|---|
| AgenticRank #119 of 119Percentile 0thWeight 22%7 benchmarksMixed sources | 6.3 | #119 of 119 | 0th | 22% | 7 benchmarks | Mixed sources |
| CodingRank #107 of 122Percentile 12thWeight 20%3 benchmarksReported | 39.4 | #107 of 122 | 12th | 20% | 3 benchmarks | Reported |
| ReasoningWeight 17%2 benchmarksReported | Score pending | Not ranked | Not available | 17% | 2 benchmarks | Reported |
| KnowledgeRank #44 of 52Percentile 16thWeight 12%8 benchmarksReported | 57.0 | #44 of 52 | 16th | 12% | 8 benchmarks | Reported |
| MathWeight 5%0 benchmarksNot measured | Not measured | Not ranked | Not available | 5% | 0 benchmarks | Not measured |
| MultilingualWeight 7%0 benchmarksNot measured | Not measured | Not ranked | Not available | 7% | 0 benchmarks | Not measured |
| MultimodalRank Not rankedWeight 12%3 benchmarksReported | 64.3 | Not ranked | Not available | 12% | 3 benchmarks | Reported |
| Inst. FollowingRank #6 of 31Percentile 83rdWeight 5%2 benchmarksReported | 91.2 | #6 of 31 | 83rd | 5% | 2 benchmarks | Reported |
Chatbot Arena performance
Scroll horizontally to inspect confidence intervals and vote counts.
| View | Elo | Confidence interval | Votes |
|---|---|---|---|
| Text Overall | 1443 | ±4.3 | 45,525 |
| Coding | 1487 | ±6.8 | 12,913 |
| Math | 1418 | ±13.1 | 2,259 |
| Instruction Following | 1413 | ±6.4 | 15,451 |
| Creative Writing | 1428 | ±8.1 | 7,682 |
| Multi-turn | 1451 | ±7.8 | 8,348 |
| Hard Prompts | 1458 | ±5.2 | 30,172 |
| Hard Prompts (English) | 1461 | ±6.5 | 15,126 |
| Longer Query | 1445 | ±6.1 | 20,198 |
Benchmark Details
Rows below have a displayable published verification record. Each source link and provenance note remains in the page HTML while its category is closed. Source-unverified manual rows and generated rows stay hidden.
Agentic7 benchmarks
τ²-Bench Tool-Agent-User Evaluation
GDPval-AA normalized
Artificial Analysis Agentic Index
Gert Labs Composite Game Benchmark
Coding3 benchmarks
Scientific Code Benchmark
Artificial Analysis Coding Index
Artificial Analysis SciCode
Reasoning2 benchmarks
Artificial Analysis Long Context Reasoning
Critical Physics Tasks
Knowledge8 benchmarks
Humanity's Last Exam
Graduate-Level Google-Proof Q&A
Artificial Analysis Omniscience Accuracy
Artificial Analysis Omniscience Hallucination Rate
Artificial Analysis GPQA Diamond
Artificial Analysis Humanity's Last Exam
Artificial Analysis Omniscience Index
Multimodal3 benchmarks
Massive Multi-discipline Multimodal Understanding Pro
Design Arena Website Elo
Artificial Analysis MMMU-Pro
Inst. Following2 benchmarks
Instruction Following Benchmark
Artificial Analysis IFBench
Frequently Asked Questions
How does Grok 4.3 perform overall in AI benchmarks?
Grok 4.3 has 25 published benchmark scores on BenchLM, but it does not yet have enough non-generated coverage to receive a global overall rank.
Is Grok 4.3 good for knowledge and understanding?
Grok 4.3 ranks #44 out of 52 models in knowledge and understanding benchmarks with an average score of 57. There are stronger options in this category.
Is Grok 4.3 good for coding and programming?
Grok 4.3 ranks #107 out of 122 models in coding and programming benchmarks with an average score of 39.4. There are stronger options in this category.
Is Grok 4.3 good for reasoning and logic?
Grok 4.3 has visible benchmark coverage in reasoning and logic, but BenchLM does not currently assign it a global category rank there.
Is Grok 4.3 good for agentic tool use and computer tasks?
Grok 4.3 ranks #119 out of 119 models in agentic tool use and computer tasks benchmarks with an average score of 6.3. There are stronger options in this category.
Is Grok 4.3 good for multimodal and grounded tasks?
Grok 4.3 has visible benchmark coverage in multimodal and grounded tasks, but BenchLM does not currently assign it a global category rank there.
Is Grok 4.3 good for instruction following?
Grok 4.3 ranks #6 out of 31 models in instruction following benchmarks with an average score of 91.2. It is among the top performers in this category.
Does Grok 4.3 have full benchmark coverage on BenchLM?
Not yet. Grok 4.3 currently has 25 published benchmark scores out of the 323 benchmarks BenchLM tracks. BenchLM only exposes non-generated public benchmark rows, so missing categories stay blank until a sourced evaluation is available.
What is the context window size of Grok 4.3?
Grok 4.3 has a published context window of 1M, which determines how much text it can process in a single interaction.
Related Resources
Choose with this week’s evidence
Join 2,000+ readers for ranking moves, new releases, pricing changes, and the evidence behind them.
Free. One email per week.