VerdictPal
Join

Models / Other

Granite 4.2 8B

Granite 4.2 · Released 2026-08-25

AA Intelligence Index 19.6. Listed on Artificial Analysis with API pricing $0.06/$0.25 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.

#147 of 166 on AA Index · current snapshot
20 AA Index · 9 benchmark rows · 1 sourcesPosition is benchmark-specific — not a cross-family or cross-source ranking.
Composite28
ContextUnlisted
Input / 1M$0.06
Output / 1M$0.25
Knowledge cutoffunpublished
Output speed152 t/s
TTFT (default API)0.22s
Statussolid

Family profile

Best published score in each covered benchmark family.

39/100 avg
Reasoning
63
Coding
30
Agentic
18
Long context
43

4 tested benchmark families

Benchmark placements

Where Granite 4.2 8B 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#16/ 185Artificial Analysis2026-09-01
AA time to first tokenPerformance#81/ 185Artificial Analysis2026-09-01
τ³-Bench BankingAgentic#96/ 1068Artificial Analysis2026-09-01
AA-LCRLong context#156/ 17943Artificial Analysis2026-09-01
Humanity's Last ExamReasoning#156/ 18010Artificial Analysis2026-09-01
SciCodeCoding#163/ 18030Artificial Analysis2026-09-01
Artificial Analysis Intelligence IndexReasoning#165/ 18420Artificial Analysis2026-09-01
Terminal-BenchAgentic#167/ 18418Artificial Analysis2026-09-01
GPQA DiamondReasoning#174/ 18563Artificial Analysis2026-09-01
Family context

The three highest-scoring models with pages in each capability family. Where Granite 4.2 8B shows up, it's highlighted.

ReasoningGranite 4.2 8B · 63
  1. 1
    Claude Mythos Preview
    95
  2. 2
    Gemini 3.7 Flash
    95
  3. 3
    Grok 4.6
    95
CodingGranite 4.2 8B · 30
  1. 1
    GPT 5.5
    96
  2. 2
    Claude Opus 4.8
    96
  3. 3
    Claude Opus 4.6
    96
AgenticGranite 4.2 8B · 18
  1. 1
    GPT 5.5
    100
  2. 2
    Claude Opus 4.8
    100
  3. 3
    Claude Fable 5
    100
Long contextGranite 4.2 8B · 43
  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 8B in the last 120 days. Older rows live in the full table below.

9 recent
BenchmarkFamilyScoreSourceDays ago
AA-LCRLong context43.33%Artificial Analysis2
AA output speedPerformance152 t/sArtificial Analysis2
AA time to first tokenPerformance0.22sArtificial Analysis2
Artificial Analysis Intelligence IndexReasoning19.6%Artificial Analysis2
GPQA DiamondReasoning63.1%Artificial Analysis2
Humanity's Last ExamReasoning9.7%Artificial Analysis2
SciCodeCoding30.4%Artificial Analysis2
τ³-Bench BankingAgentic7.63%Artificial Analysis2
Terminal-BenchAgentic18.35%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.

Reasoning63
Coding30
Agentic18
Long context43
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 8B. 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 8B.

Reasoning

Coding

Agentic

Long context

Performance

Sources