Model comparison

Llama 3.2 90B vs Phi-4

Phi-4 is the stronger model overall, scoring 31.2 to 27.5 on the Noometry Index.

Last verified October 10, 2026. 6 shared benchmarks.

Summary

They share 6 benchmarks with published results for both. Llama 3.2 90B scores higher in 2 categories and Phi-4 in 2 categories; 4 gaps are clear of the uncertainty.
The widest gap is in knowledge, where Phi-4 leads 32.6 to 21.7.
The biggest single-benchmark swing is MATH Level 5: 39.4% for Llama 3.2 90B and 64.9% for Phi-4.

Side by side

Llama 3.2 90B and Phi-4 specifications
	Llama 3.2 90B	Phi-4
Provider	Meta	Microsoft
Noometry Index	27.5	31.2
Released	2024-09-24	2024-12-11
Weights	Open	Open
Context window	—	128K
Max output	—	4K
Input $ / M tokens	—	$0.07
Output $ / M tokens	—	$0.14
Results tracked	9	37

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding Not comparable

Llama 3.2 90B: —, Phi-4: 34.4 (#239)

Coding benchmarks
Benchmark	Llama 3.2 90B	Phi-4
BigCodeBench Instruct	—	45.5%
LiveBench Coding	—	30.7%
LMArena Coding	—	1231
BigCodeBench Complete	—	55.4%

Agentic & Tool Use Llama 3.2 90B leads

Llama 3.2 90B: 30.0 (#80), Phi-4: 22.8 (#128)

Agentic & Tool Use benchmarks
Benchmark	Llama 3.2 90B	Phi-4
BALROG	27.3%	11.6%
Berkeley Function Calling Leaderboard	—	28.8%

Reasoning Llama 3.2 90B leads

Llama 3.2 90B: 21.7 (#217), Phi-4: 17.7 (#291)

Reasoning benchmarks
Benchmark	Llama 3.2 90B	Phi-4
Epoch Capabilities Index	125.5	130.42
Chess Puzzles	—	1%
EnigmaEval	0.4%	—
LiveBench Reasoning	—	47.8%
LMArena Hard Prompts	—	1220
LiveBench Data Analysis	—	45.2%
LiveBench	—	41.6%

Math Phi-4 leads

Llama 3.2 90B: 11.1 (#308), Phi-4: 20.8 (#285)

Math benchmarks
Benchmark	Llama 3.2 90B	Phi-4
OTIS Mock AIME 2024-2025	2.6%	13.8%
MATH Level 5	39.4%	64.9%
LiveBench Math	—	42%
LMArena Math	—	1246

Knowledge Phi-4 leads

Llama 3.2 90B: 21.7 (#274), Phi-4: 32.6 (#209)

Knowledge benchmarks
Benchmark	Llama 3.2 90B	Phi-4
GPQA Diamond	41%	56.1%
MMLU	80.3%	84.8%
Confabulations	—	29.4%
Vectara Hallucination Rate	—	3.7%
LMArena Expert	—	1203

Multimodal Not comparable

Llama 3.2 90B: 25.4 (#124), Phi-4: —

Multimodal benchmarks
Benchmark	Llama 3.2 90B	Phi-4
LMArena Vision	1000	—
GeoBench	52%	—

Multilingual Not comparable

Llama 3.2 90B: —, Phi-4: 37.2 (#237)

Multilingual benchmarks
Benchmark	Llama 3.2 90B	Phi-4
LMArena Non-English	—	1197
LMArena Chinese	—	1212
LMArena French	—	1224
LMArena German	—	1222
LMArena Japanese	—	1158
LMArena Korean	—	1151
LMArena Russian	—	1209
LMArena Spanish	—	1234

Instruction Following Not comparable

Llama 3.2 90B: —, Phi-4: 60.4 (#251)

Instruction Following benchmarks
Benchmark	Llama 3.2 90B	Phi-4
LiveBench Instruction Following	—	58.4%
LMArena Instruction Following	—	1201

Long Context Not comparable

Llama 3.2 90B: —, Phi-4: 36.9 (#226)

Long Context benchmarks
Benchmark	Llama 3.2 90B	Phi-4
LMArena Longer Query	—	1217

Writing & Preference Not comparable

Llama 3.2 90B: —, Phi-4: 40.5 (#244)

Writing & Preference benchmarks
Benchmark	Llama 3.2 90B	Phi-4
LMArena Text	—	1217
LMArena Creative Writing	—	1182
Short-Story Creative Writing	—	62.6%
LMArena Multi-Turn	—	1206
LiveBench Language	—	25.6%

Frequently asked questions

Is Llama 3.2 90B better than Phi-4?