Benchmarks of Motif 3 (Beta)10
BenchmarkByScoreRank
Overall1
Knowledge3
Science2
Agents1
Documents1
Legacy · saturated or no longer reported2
No benchmark matches
—per task?
API price not publicprice
—output speed?
262Kcontext
Ranking?
Alternatives?
ModelScoreCostPer taskWhat changes
BetterGranite 4.2 3BthinkingOpen+86%—$0.006Context: 262K → 128KOOpenMiniCPM5 1Bnon-thinking×54.5——Context: 262K → 131K
BetterGemma 4 E4BthinkingOpen+59%—$0.008Context: 262K → 128K
BetterMiMo v2.5thinkingOpen+54%—$0.019BetterGranite 4.2 8BthinkingOpen+54%—$0.024Context: 262K → 128KModelScoreCostPer taskWhat changes
Nothing here yet.
ModelScoreCostPer taskWhat changes
Granite 4.2 3BthinkingOpen+86%—$0.006Context: 262K → 128KGemma 4 E4BthinkingOpen+59%—$0.008Context: 262K → 128KMiMo v2.5thinkingOpen+54%—$0.019Granite 4.2 8BthinkingOpen+54%—$0.024Context: 262K → 128K
Claude Haiku 5.5low+9%—$0.024Remove sampling parameters+5ModelScoreCostPer taskWhat changes
OMiniCPM5 1Bnon-thinkingOpen×54.5——Context: 262K → 131KAG9v3 3BOpen×4.2——Context: 262K → 131KAG9v3 39A5BOpen×3.8——Context: 262K → 131K
Command A+thinkingOpen×3.5—$0.30 / $1.50Context: 262K → 128KlLFM2.5 2.6BthinkingOpen×3.1——Context: 262K → 131KModelScoreCostPer taskWhat changes
MMotif 2 12.7B Reasoning-46%——Context: 262K → 128KMMotif 3Open+73%—$0.50 / $2All Motif Technologies models →History
2 versionsBenchmarks
all categoriesChat & Knowledge
Humanity's Last Exam40.4#44
AA Omniscience Index-17.8#117
CritPt (physics)6#74
AA Intelligence Index 4.3.2≈32.3#51
AA-LCR (long context) 1.174.7#90
GPQA Diamond86.9#60
Coding
Terminal-Bench 2.170.8#35
Agents & Tool Use
GDPval-AA (work tasks) 2.130.2#66
FAQ
How much does Motif 3 (Beta) cost?›
There is no per-unit API price: API price not public.
Is Motif 3 (Beta) free to use?›
There is no free API.
How good is Motif 3 (Beta), and what is it best at?›
#44 of 334 in Chat & Knowledge, #35 of 156 in Coding, #66 of 175 in Agents & Tool Use. Strongest at: Reasoning, Science.
Is Motif 3 (Beta) better than Claude Sonnet 4.5?›
On AA Omniscience · Hallucination Rate, Motif 3 (Beta) scores 49.1 vs 49.1 — about the same.
What is the context window of Motif 3 (Beta)?›
262K tokens.
When was Motif 3 (Beta) released? Is there a newer version?›
Released 2026-07-14. It has been superseded by Motif 3.
Is Motif 3 (Beta) open source?›
No, Motif 3 (Beta) is a closed model available through an API. The closest open-weights option here is MiniCPM5 1B.
Can Motif 3 (Beta) read images?›
No, it accepts text only.
What is Motif 3 (Beta)?›
Motif 3 (Beta) is a closed language model from Motif Technologies, released Jul 2026.
What are the best alternatives to Motif 3 (Beta)?›
Granite 4.2 3B (better), MiniCPM5 1B (open weights).