Ctrl K
Back to models

Motif Technologies

Motif 3

  • Released
  • Open weights
  • MIT
Compare
Intelligence Index

Reasoning setting

33.6
Estimated · Artificial Analysis v4.3.2
Context window
262.14K tok

Performance profile

ReasoningRank #44 of 107
83.4%
GPQA Diamond
CodingRank #57 of 94
42.2%
SciCode

Capabilities

Context window

Modalities

Measured setting

Reasoning trade-offs

Source (opens in a new tab)
Intelligence Index v4.3.2
ReasoningEstimated
Intelligence Index
33.6

Pricing & access

No API offering listed in our tracked sources.

Run locally

Original download
629.7 GB
App memory
Unverified
Documented software
vLLM · Motif forkSetup guide (opens in a new tab)
Find GGUF downloads (opens in a new tab)Original weights (opens in a new tab)

Benchmarks

Full leaderboardSource (opens in a new tab)

Humanity’s Last Exam

Frontier reasoning

Motif 3 · Reasoning#33 of 126

  1. 1Claude Opus 5.5Max61.4%
  2. 2Claude Fable 5.1Max59.1%
  3. 3Gemini 4 ArgonHigh57.1%
  5. 30Agnes 3.0 FlashReasoning38.5%
  6. 31Qwen3.8-Flash-NextReasoning38.0%
  7. 32Agnes 2.5 Pro BetaReasoning37.5%
  8. 33Motif 3Reasoning37.0%
  9. 34Qwen3.7 PlusReasoning35.6%
  10. 35MiMo-V2.6-FlashReasoning35.1%
  11. 36Mistral Large 4Reasoning35.0%

Peers use their best measured result on this benchmark.