VerdictPal
Join

Models / xAI

Grok 4.3 (Non-reasoning)

Grok 4.3 · Released 2026-04-30

AA Intelligence Index 24.8. 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.

#155 of 184 on AA Index · current snapshot
15 AA Index · 10 benchmark rows · 1 sourcesPosition is benchmark-specific — not a cross-family or cross-source ranking.
Composite31
ContextUnlisted
Input / 1M$1.3
Output / 1M$2.5
Knowledge cutoffunpublished
Output speed122 t/s
TTFT (default API)0.61s
Statussolid

Family profile

Best published score in each covered benchmark family.

43/100 avg
Reasoning
66
Coding
39
Agentic
34
Long context
32

4 tested benchmark families

Benchmark placements

Where Grok 4.3 (Non-reasoning) 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
AA output speedPerformance#32/ 190Artificial Analysis2026-09-10
AA time to first tokenPerformance#75/ 190Artificial Analysis2026-09-10
SciCodeCoding#80/ 9439Artificial Analysis2026-09-10
τ³-Bench BankingAgentic#101/ 1118Artificial Analysis2026-09-10
IFBenchReasoning#103/ 12748Artificial Analysis2026-09-10
Terminal-BenchAgentic#146/ 18934Artificial Analysis2026-09-10
Artificial Analysis Intelligence IndexReasoning#160/ 18815Artificial Analysis2026-09-10
Humanity's Last ExamReasoning#170/ 1857Artificial Analysis2026-09-10
AA-LCRLong context#171/ 18232Artificial Analysis2026-09-10
GPQA DiamondReasoning#177/ 19066Artificial Analysis2026-09-10
Family context

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

ReasoningGrok 4.3 (Non-reasoning) · 66
  1. 1
    GPT-6 Astra
    96
  2. 2
    Claude Mythos Preview
    95
  3. 3
    Gemini 3.7 Flash
    95
CodingGrok 4.3 (Non-reasoning) · 39
  1. 1
    GPT 5.5
    96
  2. 2
    Claude Opus 4.8
    96
  3. 3
    Claude Opus 4.6
    96
AgenticGrok 4.3 (Non-reasoning) · 34
  1. 1
    GPT 5.5
    100
  2. 2
    Claude Opus 4.8
    100
  3. 3
    Claude Fable 5
    100
Long contextGrok 4.3 (Non-reasoning) · 32
  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 (Non-reasoning) in the last 120 days. Older rows live in the full table below.

10 recent
BenchmarkFamilyScoreSourceDays ago
AA-LCRLong context32.33%Artificial Analysis4
AA output speedPerformance122 t/sArtificial Analysis4
AA time to first tokenPerformance0.61sArtificial Analysis4
Artificial Analysis Intelligence IndexReasoning14.5%Artificial Analysis4
GPQA DiamondReasoning65.8%Artificial Analysis4
Humanity's Last ExamReasoning6.8%Artificial Analysis4
IFBenchReasoning47.62%Artificial Analysis4
SciCodeCoding39.4%Artificial Analysis4
τ³-Bench BankingAgentic8.04%Artificial Analysis4
Terminal-BenchAgentic34.08%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.

Reasoning66
Coding39
Agentic34
Long context32
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 (Non-reasoning). Scores link to the original source; gaps mean no public row exists yet.

10 sourced rows

10 of 37 catalog benchmarks have a sourced row for Grok 4.3 (Non-reasoning).

Reasoning

Coding

Agentic

Long context

Performance

Sources