Phi 4 Reasoning Plus phi-4-reasoning-plus

microsoft · microsoft

unranked — no quality signals yet

params
14.7B
arch
dense
license
mit open weights

# architecture

attn shared GQA 40q/10kv feed-forward (dense) every parameter, every token out ×40 layers 14.7B — no routing
layers
40
d_model
5120
heads
40q / 10kv
head dim
128
vocab
100352
family
phi3

signal path of one layer, generated from the registry's structured fields — dimension lines quote the model's real numbers; an MoE trace forks at the router, a dense trace runs straight through. Geometry fields come from the repo's config.json.

# why ranked

Overall: provisional — score 42.8 ● low — a single signal; treat with caution

provisional: too few independent signals for a numbered position — the score is shown, but this model sorts after every ranked model.

signalweightinput (0–100)
aa_intelligence 0.70
bench_composite 0.30 42.8

benchmark panel evidence:

complete panelscore (0–100)
aime-2025-v142.8

missing signals are dropped and the remaining weights renormalized — never imputed.

full methodology

# trend

OGM score · last 31 days
OGM score over 31 days

# benchmarks

benchmarkscoresourcedate
AIME 2024 0.8 / 1 LLM Stats
AIME 2025 0.8 / 1 LLM Stats
Arena-hard 0.8 / 1 LLM Stats
Flenqa 1.0 / 1 LLM Stats

# where to run

providerquantctx$/M in$/M out$/M cacheprice srctpsuptime
Azure 32k $0.12$0.50 via modelsdev

sorted by blended price ((3·input + output) / 4 per 1M) · ✓ = the provider's own catalog confirms the offer · "via …" prices are what the aggregator routing the offer charges, not the provider's own list price

source aliases
llmstats
phi-4-reasoning-plus