VerdictPal
Join

Models / xAI

Grok 4.20 0309 (Reasoning)

Grok 4.20 · Released 2026-03-10

AA Intelligence Index 36.5. Listed on Artificial Analysis with API pricing $2/$6 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.

#84 of 184 on AA Index · current snapshot
25 AA Index · 8 benchmark rows · 1 sourcesPosition is benchmark-specific — not a cross-family or cross-source ranking.
Composite56
Context128K
Input / 1M$2.0
Output / 1M$6.0
Knowledge cutoffopen
Statussolid

Family profile

Best published score in each covered benchmark family.

66/100 avg
Reasoning
89
Agentic
41
Long context
68

3 tested benchmark families

Benchmark placements

Where Grok 4.20 0309 (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
IFBenchReasoning#2/ 12783Artificial Analysis2026-09-10
GPQA DiamondReasoning#64/ 19089Artificial Analysis2026-09-10
Humanity's Last ExamReasoning#70/ 18532Artificial Analysis2026-09-10
Artificial Analysis Intelligence IndexReasoning#85/ 18825Artificial Analysis2026-09-10
Terminal-BenchAgentic#117/ 18941Artificial Analysis2026-09-10
AA-LCRLong context#131/ 18268Artificial Analysis2026-09-10
AA output speedPerformance#146/ 190Artificial Analysis2026-09-10
AA time to first tokenPerformance#146/ 190Artificial Analysis2026-09-10
Family context

The three highest-scoring models with pages in each capability family. Where Grok 4.20 0309 (Reasoning) shows up, it's highlighted.

ReasoningGrok 4.20 0309 (Reasoning) · 89
  1. 1
    GPT-6 Astra
    96
  2. 2
    Claude Mythos Preview
    95
  3. 3
    Gemini 3.7 Flash
    95
AgenticGrok 4.20 0309 (Reasoning) · 41
  1. 1
    GPT 5.5
    100
  2. 2
    Claude Opus 4.8
    100
  3. 3
    Claude Fable 5
    100
Long contextGrok 4.20 0309 (Reasoning) · 68
  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 4.20 0309 (Reasoning) in the last 120 days. Older rows live in the full table below.

8 recent
BenchmarkFamilyScoreSourceDays ago
AA-LCRLong context67.67%Artificial Analysis4
AA output speedPerformance0 t/sArtificial Analysis4
AA time to first tokenPerformance0.00sArtificial Analysis4
Artificial Analysis Intelligence IndexReasoning25.2%Artificial Analysis4
GPQA DiamondReasoning88.5%Artificial Analysis4
Humanity's Last ExamReasoning32.4%Artificial Analysis4
IFBenchReasoning82.93%Artificial Analysis4
Terminal-BenchAgentic40.91%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.

Reasoning89
Agentic41
Long context68
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 4.20 0309 (Reasoning). Scores link to the original source; gaps mean no public row exists yet.

8 sourced rows

9 of 37 catalog benchmarks have a sourced row for Grok 4.20 0309 (Reasoning).

Reasoning

Agentic

Long context

Performance

Sources