VerdictPal
Join

Models / xAI

Grok 4.3 (low)

Grok 4.3 · Released 2026-04-30

AA Intelligence Index 35.4. Listed on Artificial Analysis with API pricing $1.25/$2.5 per 1M tokens. Benchmark rows sync from the AA snapshot — see the ledger on this page.

Frontier model tracked on Artificial Analysis. Use the benchmark ledger below for sourced scores; we do not infer numbers beyond published rows.

#94 of 184 on AA Index · current snapshot
24 AA Index · 8 benchmark rows · 1 sourcesPosition is benchmark-specific — not a cross-family or cross-source ranking.
Composite51
Context128K
Input / 1M$1.3
Output / 1M$2.5
Knowledge cutoffopen
Output speed112 t/s
TTFT (default API)7.21s
Statussolid

Family profile

Best published score in each covered benchmark family.

62/100 avg
Reasoning
84
Agentic
27
Long context
74

3 tested benchmark families

Benchmark placements

Where Grok 4.3 (low) places on each public benchmark source that publishes a row. Rank counts every model with a latest row in the same test — not a universal quality score.

BenchmarkFamilyRankScoreSourceDate
IFBenchReasoning#7/ 12781Artificial Analysis2026-09-10
AA time to first tokenPerformance#23/ 190Artificial Analysis2026-09-10
AA output speedPerformance#37/ 190Artificial Analysis2026-09-10
AA-LCRLong context#91/ 18274Artificial Analysis2026-09-10
Artificial Analysis Intelligence IndexReasoning#95/ 18824Artificial Analysis2026-09-10
GPQA DiamondReasoning#109/ 19084Artificial Analysis2026-09-10
Humanity's Last ExamReasoning#133/ 18518Artificial Analysis2026-09-10
Terminal-BenchAgentic#166/ 18927Artificial Analysis2026-09-10
Family context

The three highest-scoring models with pages in each capability family. Where Grok 4.3 (low) shows up, it's highlighted.

ReasoningGrok 4.3 (low) · 84
  1. 1
    GPT-6 Astra
    96
  2. 2
    Claude Mythos Preview
    95
  3. 3
    Gemini 3.7 Flash
    95
AgenticGrok 4.3 (low) · 27
  1. 1
    GPT 5.5
    100
  2. 2
    Claude Opus 4.8
    100
  3. 3
    Claude Fable 5
    100
Long contextGrok 4.3 (low) · 74
  1. 1
    Kimi K3
    89
  2. 2
    Claude Fable 5.1
    85
  3. 3
    GPT-5.5 (high)
    84
Newest receipts

Benchmark rows added to the public ledger for Grok 4.3 (low) in the last 120 days. Older rows live in the full table below.

8 recent
BenchmarkFamilyScoreSourceDays ago
AA-LCRLong context74%Artificial Analysis4
AA output speedPerformance112 t/sArtificial Analysis4
AA time to first tokenPerformance7.21sArtificial Analysis4
Artificial Analysis Intelligence IndexReasoning24.3%Artificial Analysis4
GPQA DiamondReasoning84.3%Artificial Analysis4
Humanity's Last ExamReasoning18.4%Artificial Analysis4
IFBenchReasoning80.95%Artificial Analysis4
Terminal-BenchAgentic26.52%Artificial Analysis4
Family coverage

A high composite that hides a weak family is a trap. These bars surface the families where this model hasn't been publicly tested, and where it leads.

Reasoning84
Agentic27
Long context74
Price vs. performance
0255075100$0.10$0.30$1$3$10$30input USD / 1M tokens · log scale →← intelligence

Hover any dot for name, score, and input price. Keyboard: tab through the top twelve, or use the ranking below.

AnthropicOpenAIMistralAlibabaDeepSeekGoogleMoonshotMetaxAIMiniMaxZhipuXiaomiOtherMeituanCohereNVIDIA

Full benchmark ledger

Every catalog benchmark for Grok 4.3 (low). Scores link to the original source; gaps mean no public row exists yet.

8 sourced rows

8 of 37 catalog benchmarks have a sourced row for Grok 4.3 (low).

Reasoning

Agentic

Long context

Performance

Sources