VerdictPal
Join

Models / Other

Granite 4.2 30B

Granite 4.2 · Released 2026-08-25

AA Intelligence Index 23.7. Listed on Artificial Analysis with API pricing $0.16/$0.65 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.

#140 of 166 on AA Index · current snapshot
24 AA Index · 9 benchmark rows · 1 sourcesPosition is benchmark-specific — not a cross-family or cross-source ranking.
Composite32
ContextUnlisted
Input / 1M$0.16
Output / 1M$0.65
Knowledge cutoffunpublished
Output speed77 t/s
TTFT (default API)0.24s
Statussolid

Family profile

Best published score in each covered benchmark family.

44/100 avg
Reasoning
64
Coding
37
Agentic
27
Long context
47

4 tested benchmark families

Benchmark placements

Where Granite 4.2 30B 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#51/ 185Artificial Analysis2026-09-01
τ³-Bench BankingAgentic#74/ 10614Artificial Analysis2026-09-01
AA time to first tokenPerformance#80/ 185Artificial Analysis2026-09-01
Humanity's Last ExamReasoning#151/ 18011Artificial Analysis2026-09-01
SciCodeCoding#151/ 18037Artificial Analysis2026-09-01
AA-LCRLong context#153/ 17947Artificial Analysis2026-09-01
Artificial Analysis Intelligence IndexReasoning#157/ 18424Artificial Analysis2026-09-01
Terminal-BenchAgentic#159/ 18427Artificial Analysis2026-09-01
GPQA DiamondReasoning#173/ 18564Artificial Analysis2026-09-01
Family context

The three highest-scoring models with pages in each capability family. Where Granite 4.2 30B shows up, it's highlighted.

ReasoningGranite 4.2 30B · 64
  1. 1
    Claude Mythos Preview
    95
  2. 2
    Gemini 3.7 Flash
    95
  3. 3
    Grok 4.6
    95
CodingGranite 4.2 30B · 37
  1. 1
    GPT 5.5
    96
  2. 2
    Claude Opus 4.8
    96
  3. 3
    Claude Opus 4.6
    96
AgenticGranite 4.2 30B · 27
  1. 1
    GPT 5.5
    100
  2. 2
    Claude Opus 4.8
    100
  3. 3
    Claude Fable 5
    100
Long contextGranite 4.2 30B · 47
  1. 1
    Muse Spark 1.2
    83
  2. 2
    Kimi K3
    83
  3. 3
    Gemini 3.5 Flash
    81
Newest receipts

Benchmark rows added to the public ledger for Granite 4.2 30B in the last 120 days. Older rows live in the full table below.

9 recent
BenchmarkFamilyScoreSourceDays ago
AA-LCRLong context46.67%Artificial Analysis2
AA output speedPerformance77 t/sArtificial Analysis2
AA time to first tokenPerformance0.24sArtificial Analysis2
Artificial Analysis Intelligence IndexReasoning23.7%Artificial Analysis2
GPQA DiamondReasoning64.4%Artificial Analysis2
Humanity's Last ExamReasoning11.2%Artificial Analysis2
SciCodeCoding36.6%Artificial Analysis2
τ³-Bench BankingAgentic14.43%Artificial Analysis2
Terminal-BenchAgentic26.59%Artificial Analysis2
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.

Reasoning64
Coding37
Agentic27
Long context47
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.

AnthropicOpenAIMistralAlibabaDeepSeekGoogleMoonshotMetaMiniMaxxAIZhipuXiaomiOtherMeituanCohereNVIDIA

Full benchmark ledger

Every catalog benchmark for Granite 4.2 30B. Scores link to the original source; gaps mean no public row exists yet.

9 sourced rows

9 of 37 catalog benchmarks have a sourced row for Granite 4.2 30B.

Reasoning

Coding

Agentic

Long context

Performance

Sources