Benchmarks of INTELLECT 325
BenchmarkByScoreRank
Overall1
Knowledge4
Science2
Coding1
Writing12
Documents1
Legacy · saturated or no longer reported4
No benchmark matches
—per task?
self-host onlyprice
—output speed?
131Kcontext
Rankingin thinking mode?
Alternatives?
ModelScoreCostPer taskWhat changes
BetterNemotron 3 Nano 30B A3BthinkingOpen+3%—$0.017
OpenGPT OSS 120Bhigh+6%—$0.11Memory (4-bit): 64 GB → 70 GBBetterGPT-5 Minihigh+3%—$0.053
BetterQwen3 235B A22B Thinking 2507thinkingOpen+3%—$0.08Memory (4-bit): 64 GB → 141 GB+1BetterGPT-5.2xhigh+13%—$1.75 / $14ModelScoreCostPer taskWhat changes
Nothing here yet.
ModelScoreCostPer taskWhat changes
Nemotron 3 Nano 30B A3BthinkingOpen+3%—$0.017GPT-5 Minihigh+3%—$0.053Qwen3 235B A22B Thinking 2507thinkingOpen+3%—$0.08Memory (4-bit): 64 GB → 141 GB+1GPT OSS 120BhighOpen+6%—$0.11Memory (4-bit): 64 GB → 70 GBGPT-5.2xhigh+13%—$1.75 / $14ModelScoreCostPer taskWhat changes
GPT OSS 120BhighOpen+6%—$0.11Memory (4-bit): 64 GB → 70 GBNemotron 3 Nano 30B A3BthinkingOpen+3%—$0.017Qwen3 235B A22B Thinking 2507thinkingOpen+3%—$0.08Memory (4-bit): 64 GB → 141 GB+1
K EXAONEthinkingOpen+3%——Memory (4-bit): 64 GB → 142 GBGPT OSS 20BhighOpen+2%—$0.011Run it yourself
estimateFits on✗ 8 GB (phone, laptop)✗ 16 GB✗ 24 GB GPU✗ 48 GB GPU✓ 80 GB GPU · compressed
LicenceMITfree for commercial use
Benchmarks
all categoriesChat & Knowledge
Humanity's Last Exam13.1#157
AA Omniscience Index-50.9#216
CritPt (physics)0.3#151
AA Intelligence Index 4.3.2≈10.6#205
AA Omniscience · Accuracy19.6#161
AA-LCR (long context) 1.139.7#201
GPQA Diamond76.1#144
Coding
LiveCodeBench · AA archived77.7#22
Agents & Tool Use
τ²-bench · AA26.6#163
Writing & Language
IFBench (instructions)34#193
FAQ
How much does INTELLECT 3 cost?›
There is no per-unit API price: self-host only.
Is INTELLECT 3 free to use?›
There is no free API. The weights are open, so you can run it yourself.
How good is INTELLECT 3, and what is it best at?›
#156 of 336 in Chat & Knowledge, #128 of 239 in Coding, #161 of 242 in Agents & Tool Use, #118 of 197 in Writing & Language.
Is INTELLECT 3 better than Apriel v1.6 15B Thinker?›
On AIME 2025 · AA archived, INTELLECT 3 scores 88 vs 88 — about the same.
What is the context window of INTELLECT 3?›
131K tokens.
When was INTELLECT 3 released? Is there a newer version?›
Released 2025-11-27. It is the current version in its line.
Is INTELLECT 3 open source?›
Yes, the weights are open (MIT licence).
Can I run INTELLECT 3 locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Can INTELLECT 3 read images?›
No, it accepts text only.
What is INTELLECT 3?›
INTELLECT 3 is an open-weights language model from Prime Intellect, released Nov 2025.
What are the best alternatives to INTELLECT 3?›
Nemotron 3 Nano 30B A3B (better), GPT OSS 120B (open weights).