VerdictPal
Join

Models / xAI

Grok 4.20 0309 v2 (Non-reasoning)

Grok 4.20 · Released 2026-04-07

AA Intelligence Index 21.8. 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.

#110 of 131 on AA Index · current snapshot
22 AA Index · 10 benchmark rows · 1 sourcesPosition is benchmark-specific — not a cross-family or cross-source ranking.
Composite38
ContextUnlisted
Input / 1M$2.0
Output / 1M$6.0
Knowledge cutoffunpublished
Output speed0 t/s
TTFT (default API)0.00s
Statussolid
ReasoningCodingAgenticLong context
Reasoning
78
Coding
33
Agentic
60
Long context
17

47average across 4 tested families

Benchmark placements

Where Grok 4.20 0309 v2 (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
τ³-Bench BankingAgentic#50/ 14360Artificial Analysis2026-07-28
Humanity's Last ExamReasoning#78/ 14424Artificial Analysis2026-07-28
IFBenchReasoning#94/ 12149Artificial Analysis2026-07-28
GPQA DiamondReasoning#116/ 14978Artificial Analysis2026-07-28
AA output speedPerformance#123/ 149Artificial Analysis2026-07-28
AA time to first tokenPerformance#123/ 149Artificial Analysis2026-07-28
Artificial Analysis Intelligence IndexReasoning#126/ 14722Artificial Analysis2026-07-28
SciCodeCoding#129/ 14433Artificial Analysis2026-07-28
Terminal-BenchAgentic#135/ 14817Artificial Analysis2026-07-28
AA-LCRLong context#137/ 14317Artificial Analysis2026-07-28
Family context

The three highest-scoring carded models in each capability family. Where Grok 4.20 0309 v2 (Non-reasoning) shows up, it's highlighted.

ReasoningGrok 4.20 0309 v2 (Non-reasoning) · 78
  1. 1
    Claude Mythos Preview
    95
  2. 2
    GPT-5.6 Sol
    94
  3. 3
    Kimi K3
    94
CodingGrok 4.20 0309 v2 (Non-reasoning) · 33
  1. 1
    GPT 5.5
    96
  2. 2
    Claude Opus 4.8
    96
  3. 3
    Claude Opus 4.6
    96
AgenticGrok 4.20 0309 v2 (Non-reasoning) · 60
  1. 1
    GPT 5.5
    100
  2. 2
    Claude Opus 4.8
    100
  3. 3
    Claude Fable 5
    100
Long contextGrok 4.20 0309 v2 (Non-reasoning) · 17
  1. 1
    GPT-5 (high)
    76
  2. 2
    GPT-5.2 Codex (xhigh)
    76
  3. 3
    Kimi K3
    75
Newest receipts

Benchmark rows added to the public ledger for Grok 4.20 0309 v2 (Non-reasoning) in the last 120 days. Older rows live in the full table below.

10 recent
BenchmarkFamilyScoreSourceDays ago
AA-LCRLong context17.33%Artificial Analysis4
AA output speedPerformance0 t/sArtificial Analysis4
AA time to first tokenPerformance0.00sArtificial Analysis4
Artificial Analysis Intelligence IndexReasoning21.8%Artificial Analysis4
GPQA DiamondReasoning77.6%Artificial Analysis4
Humanity's Last ExamReasoning24.2%Artificial Analysis4
IFBenchReasoning49.32%Artificial Analysis4
SciCodeCoding32.8%Artificial Analysis4
τ³-Bench BankingAgentic59.94%Artificial Analysis4
Terminal-BenchAgentic16.67%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.

Reasoning78
Coding33
Agentic60
Long context17
Price vs. performance
0255075100$0.10$0.30$1$3$10$30input USD / 1M tokens · log scale →← intelligence

Hover or tab any dot for name, score, and input price.

AnthropicOpenAIMistralAlibabaDeepSeekGoogleMoonshotxAIMiniMaxMetaZhipuXiaomiOtherMeituanCohereNVIDIA

Full benchmark ledger

Every catalog benchmark for Grok 4.20 0309 v2 (Non-reasoning). Scores link to the original source; gaps mean no public row exists yet.

10 sourced rows

10 of 32 catalog benchmarks have a sourced row for Grok 4.20 0309 v2 (Non-reasoning).

Reasoning

Coding

Agentic

Long context

Performance

Sources