Model comparison

Llama 3.2 90B vs o3

o3 is the stronger model overall, scoring 47.5 to 27.5 on the Noometry Index.

Last verified October 11, 2026. 7 shared benchmarks.

Summary

They share 7 benchmarks with published results for both. Llama 3.2 90B scores higher in 0 categories and o3 in 5 categories; 5 gaps are clear of the uncertainty.
The widest gap is in math, where o3 leads 50.2 to 11.1.
The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 2.6% for Llama 3.2 90B and 84.4% for o3.
Llama 3.2 90B has downloadable open weights; the other is API-only.

Side by side

Llama 3.2 90B and o3 specifications
	Llama 3.2 90B	o3
Provider	Meta	OpenAI
Noometry Index	27.5	47.5
Released	2024-09-24	2025-04-16
Weights	Open	Proprietary
Context window	—	200K
Max output	—	100K
Input $ / M tokens	—	$2
Output $ / M tokens	—	$8
Results tracked	9	63

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

Category by category

Coding Not comparable

Llama 3.2 90B: —, o3: 46.8 (#64)

Coding benchmarks
Benchmark	Llama 3.2 90B	o3
SWE-bench Verified	—	62.3%
SWE-bench Verified (bash only)	—	58.4%
Aider Polyglot	—	81.3%
GSO	—	8.8%
WeirdML	—	52.4%
LMArena Coding	—	1408
CadEval	—	74%
ALE-Bench	—	933.55

Agentic & Tool Use o3 leads

Llama 3.2 90B: 30.0 (#80), o3: 34.5 (#44)

Agentic & Tool Use benchmarks
Benchmark	Llama 3.2 90B	o3
Berkeley Function Calling Leaderboard	—	63%
GDPval	—	30.8%
DeepResearch Bench	—	45.2%
OSWorld	—	23%
BALROG	27.3%	—
LMArena Search	—	1144
METR Time Horizons	—	65.4%

Reasoning o3 leads

Llama 3.2 90B: 21.7 (#217), o3: 32.0 (#78)

Reasoning benchmarks
Benchmark	Llama 3.2 90B	o3
EnigmaEval	0.4%	13.1%
Epoch Capabilities Index	125.5	146.86
ARC-AGI-2	—	6.5%
SimpleBench	—	53.1%
Kagi LLM Benchmark	—	67.6%
ARC-AGI-1	—	60.8%
CritPt	—	1.4%
Chess Puzzles	—	38%
LMArena Hard Prompts	—	1402
Mystery Game Puzzles	—	29%
DTBench	—	84.8%
LMCA	—	39.7%
ForecastBench	—	62.5

Math o3 leads

Llama 3.2 90B: 11.1 (#308), o3: 50.2 (#58)

Math benchmarks
Benchmark	Llama 3.2 90B	o3
OTIS Mock AIME 2024-2025	2.6%	84.4%
MATH Level 5	39.4%	97.8%
FrontierMath (Tiers 1-3)	—	33.3%
Omni-MATH	—	71.4%
LMArena Math	—	1426
FrontierMath (Feb 2025 set)	—	18.7%
FrontierMath Tier 4 (v1)	—	2.1%

Knowledge o3 leads

Llama 3.2 90B: 21.7 (#274), o3: 54.6 (#52)

Knowledge benchmarks
Benchmark	Llama 3.2 90B	o3
GPQA Diamond	41%	81.8%
Humanity's Last Exam	—	20.3%
SimpleQA Verified	—	49.4%
MMLU-Pro	—	85.9%
Confabulations	—	14.4%
GPQA (HELM)	—	75.3%
LMArena Expert	—	1402
MMLU	80.3%	—

Multimodal o3 leads

Llama 3.2 90B: 25.4 (#124), o3: 41.4 (#36)

Multimodal benchmarks
Benchmark	Llama 3.2 90B	o3
LMArena Vision	1000	1214
GeoBench	52%	74%
VPCT	—	52%

Multilingual Not comparable

Llama 3.2 90B: —, o3: 51.7 (#105)

Multilingual benchmarks
Benchmark	Llama 3.2 90B	o3
LMArena Non-English	—	1401
LMArena Chinese	—	1437
LMArena French	—	1430
LMArena German	—	1420
LMArena Japanese	—	1403
LMArena Korean	—	1370
LMArena Russian	—	1406
LMArena Spanish	—	1395

Instruction Following Not comparable

Llama 3.2 90B: —, o3: 72.8 (#127)

Instruction Following benchmarks
Benchmark	Llama 3.2 90B	o3
IFEval	—	86.9%
LMArena Instruction Following	—	1368

Long Context Not comparable

Llama 3.2 90B: —, o3: 53.3 (#6)

Long Context benchmarks
Benchmark	Llama 3.2 90B	o3
Fiction.LiveBench	—	88.9%
CL-bench	—	17.8%
LMArena Longer Query	—	1372

Writing & Preference Not comparable

Llama 3.2 90B: —, o3: 63.5 (#64)

Writing & Preference benchmarks
Benchmark	Llama 3.2 90B	o3
LMArena Text	—	1410
LMArena Creative Writing	—	1359
Short-Story Creative Writing	—	83.9%
EQ-Bench Creative Writing	—	1676
WildBench	—	86.1%
LMArena Multi-Turn	—	1405

Frequently asked questions

Is Llama 3.2 90B better than o3?