Model comparison
Llama 3.2 90B vs Phi-3.5-mini
Llama 3.2 90B has enough public results to be ranked (#331); Phi-3.5-mini does not yet, so treat this comparison as directional.
Last verified . 0 shared benchmarks.
Meta
MicrosoftSide by side
| Llama 3.2 90B | Phi-3.5-mini | |
|---|---|---|
| Provider | Meta | Microsoft |
| Noometry Index | 27.5 | 36.9 |
| Released | 2024-09-24 | 2024-08-16 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 9 | 5 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Llama 3.2 90B: —, Phi-3.5-mini: 34.6 (#232)
| Benchmark | Llama 3.2 90B | Phi-3.5-mini |
|---|---|---|
| BigCodeBench Instruct | — | 32.8% |
| BigCodeBench Complete | — | 38.5% |
Agentic & Tool Use Not comparable
Llama 3.2 90B: 30.0 (#80), Phi-3.5-mini: —
| Benchmark | Llama 3.2 90B | Phi-3.5-mini |
|---|---|---|
| BALROG | 27.3% | — |
Reasoning Not comparable
Llama 3.2 90B: 21.7 (#217), Phi-3.5-mini: —
| Benchmark | Llama 3.2 90B | Phi-3.5-mini |
|---|---|---|
| EnigmaEval | 0.4% | — |
| Epoch Capabilities Index | 125.5 | — |
| PIQA | — | 81% |
Math Not comparable
Llama 3.2 90B: 11.1 (#308), Phi-3.5-mini: —
| Benchmark | Llama 3.2 90B | Phi-3.5-mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.6% | — |
| MATH Level 5 | 39.4% | — |
| GSM8K | — | 86.2% |
Knowledge Not comparable
Llama 3.2 90B: 21.7 (#274), Phi-3.5-mini: —
| Benchmark | Llama 3.2 90B | Phi-3.5-mini |
|---|---|---|
| GPQA Diamond | 41% | — |
| BoolQ | — | 78% |
| MMLU | 80.3% | — |
Multimodal Not comparable
Llama 3.2 90B: 25.4 (#124), Phi-3.5-mini: —
| Benchmark | Llama 3.2 90B | Phi-3.5-mini |
|---|---|---|
| LMArena Vision | 1000 | — |
| GeoBench | 52% | — |
Frequently asked questions
Is Llama 3.2 90B better than Phi-3.5-mini?
Llama 3.2 90B has enough public results to be ranked (#331); Phi-3.5-mini does not yet, so treat this comparison as directional.
How many benchmarks do Llama 3.2 90B and Phi-3.5-mini share?
0 benchmarks have published results for both models. Llama 3.2 90B has 9 scored results on Noometry and Phi-3.5-mini has 5.