VerdictPal
Join

Models / Other

Motif 3

Motif · Released 2026-08-12

Motif Technologies' 314B MoE (13.2B active). Artificial Analysis Intelligence Index 47.4. AA lists API pricing as $0 / $0 per 1M tokens (open weights).

Open Motif checkpoint for long-context coding and Korean-capable general work. Prefer sourced ledger rows over the technical-report table.

#33 of 166 on AA Index · current snapshot
47 AA Index · 9 benchmark rows · 1 sourcesPosition is benchmark-specific — not a cross-family or cross-source ranking.
Composite55
Context262K
Input / 1MFree
Output / 1MFree
Knowledge cutoffunpublished
Statussolid

Family profile

Best published score in each covered benchmark family.

68/100 avg
Reasoning
83
Coding
41
Agentic
75
Long context
72

4 tested benchmark families

Editor's note
Recorded from the 2026-08-15 AA snapshot (index 47.4) plus the Hugging Face card and arXiv 2608.09119. Supersedes the Motif 3 Beta stub. Editorial depth still needs a desk pass.
Benchmark placements

Where Motif 3 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#26/ 10635Artificial Analysis2026-09-01
Terminal-BenchAgentic#35/ 18475Artificial Analysis2026-09-01
Artificial Analysis Intelligence IndexReasoning#40/ 18447Artificial Analysis2026-09-01
Humanity's Last ExamReasoning#47/ 18037Artificial Analysis2026-09-01
AA-LCRLong context#71/ 17972Artificial Analysis2026-09-01
GPQA DiamondReasoning#117/ 18583Artificial Analysis2026-09-01
SciCodeCoding#122/ 18041Artificial Analysis2026-09-01
AA output speedPerformance#173/ 185Artificial Analysis2026-09-01
AA time to first tokenPerformance#173/ 185Artificial Analysis2026-09-01
Family context

The three highest-scoring models with pages in each capability family. Where Motif 3 shows up, it's highlighted.

ReasoningMotif 3 · 83
  1. 1
    Claude Mythos Preview
    95
  2. 2
    Gemini 3.7 Flash
    95
  3. 3
    Grok 4.6
    95
CodingMotif 3 · 41
  1. 1
    GPT 5.5
    96
  2. 2
    Claude Opus 4.8
    96
  3. 3
    Claude Opus 4.6
    96
AgenticMotif 3 · 75
  1. 1
    GPT 5.5
    100
  2. 2
    Claude Opus 4.8
    100
  3. 3
    Claude Fable 5
    100
Long contextMotif 3 · 72
  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 Motif 3 in the last 120 days. Older rows live in the full table below.

9 recent
BenchmarkFamilyScoreSourceDays ago
AA-LCRLong context72.33%Artificial Analysis2
AA output speedPerformance0 t/sArtificial Analysis2
AA time to first tokenPerformance0.00sArtificial Analysis2
Artificial Analysis Intelligence IndexReasoning47.4%Artificial Analysis2
GPQA DiamondReasoning83.4%Artificial Analysis2
Humanity's Last ExamReasoning37%Artificial Analysis2
SciCodeCoding40.6%Artificial Analysis2
τ³-Bench BankingAgentic35.26%Artificial Analysis2
Terminal-BenchAgentic74.91%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.

Reasoning83
Coding41
Agentic75
Long context72
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 Motif 3. 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 Motif 3.

Reasoning

Coding

Agentic

Long context

Performance

Changelog
  1. Motif 3 GA on Artificial Analysis (index 47.4). Open-weight MoE, 314B / 13.2B active.
Sources