BenchLeader

Phi-1.5

Phi-1.5 is a Microsoft proprietary model, released 11 Sept 2023. It is not yet ranked: no independent benchmark results so far, only pricing and metadata.

Blended price
–
Output speed
–
First answer
–
Context
–
Full answer
–
Cost per run
–
Released
11 Sept 2023

Versions

Microsoft has shipped 4 models under this name. Each is ranked on its own results; a newer version often has fewer results so far, which holds its index nearer the average until more arrive.

ModelReleasedIndexRank
Phi-412 Dec 202438.9#699
Phi 3medium23 Apr 202438.0#722
Phi-212 Dec 2023––
Phi-1.5this page11 Sept 2023––

Benchmark results

See all LLM benchmarks. One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.

Reasoning

Benchmarknot statedSourceTrend
HellaSwagnot in index47.6%#63Epoch AI Benchmarking Hub
WinoGrandenot in index73.4%#36Epoch AI Benchmarking Hub
ARC (AI2 Challenge)not in index44.4%#54Epoch AI Benchmarking Hub

Knowledge

Benchmarknot statedSourceTrend
MMLUnot in index37.6%#106Epoch AI Benchmarking Hub
OpenBookQAnot in index37.2%#35Epoch AI Benchmarking Hub

Composite

Benchmarknot statedSourceTrend
Epoch Capabilities Indexnot in index91.1#236Epoch AI Benchmarking Hub

More from Microsoft

New this month

See also

Questions people ask

Why does Phi-1.5 have no BenchLeader Index score?
The index needs at least five independent results across at least two categories; as of 25 Oct 2026 Phi-1.5 has 0 that count. Launch-post scores are never used, so it is ranked once independent publishers have measured it.
When was Phi-1.5 released?
Microsoft released Phi-1.5 on 11 Sept 2023.

Data as of 25 Oct 2026. Compare with another model.

Cite as: BenchLeader, “Phi-1.5: benchmarks, pricing, speed and rank”, data as of 25 Oct 2026, https://www.benchleader.com/models/phi-1-5.