Model comparison

GPT-5.4 Pro vs Llama 3.2 3B

GPT-5.4 Pro is the stronger model overall, scoring 58.8 to 28.4 on the Noometry Index. Llama 3.2 3B costs 563× less per token, which makes it the better buy when GPT-5.4 Pro's lead doesn't matter for your workload.

Last verified October 10, 2026. 0 shared benchmarks.

GPT-5.4 Pro OpenAI

58.8

Rank #16 Confirmed

Llama 3.2 3B

Summary

The widest gap is in reasoning, where GPT-5.4 Pro leads 71.0 to 20.1.
Llama 3.2 3B is cheaper at $0.05 / $0.33 per million input/output tokens, against $30 / $180 for GPT-5.4 Pro.
GPT-5.4 Pro accepts more context: 1.05M tokens versus 131K.
Llama 3.2 3B has downloadable open weights; the other is API-only.

Side by side

GPT-5.4 Pro and Llama 3.2 3B specifications
	GPT-5.4 Pro	Llama 3.2 3B
Provider	OpenAI	Meta
Noometry Index	58.8	28.4
Released	2026-03-05	2024-09-24
Weights	Proprietary	Open
Context window	1.05M	131K
Max output	128K	118K
Input $ / M tokens	$30	$0.05
Output $ / M tokens	$180	$0.33
Results tracked	16	18

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

Category by category

Coding GPT-5.4 Pro leads

GPT-5.4 Pro: 42.6 (#89), Llama 3.2 3B: 27.1 (#314)

Coding benchmarks
Benchmark	GPT-5.4 Pro	Llama 3.2 3B
WeirdML	57.4%	—
BigCodeBench Instruct	—	23.4%
LMArena Coding	—	1098
BigCodeBench Complete	—	28.3%

Agentic & Tool Use Not comparable

GPT-5.4 Pro: —, Llama 3.2 3B: 19.9 (#135)

Agentic & Tool Use benchmarks
Benchmark	GPT-5.4 Pro	Llama 3.2 3B
Berkeley Function Calling Leaderboard	—	21.9%
BALROG	—	10.1%

Reasoning GPT-5.4 Pro leads

GPT-5.4 Pro: 71.0 (#10), Llama 3.2 3B: 20.1 (#225)

Reasoning benchmarks
Benchmark	GPT-5.4 Pro	Llama 3.2 3B
ARC-AGI-2	83.3%	—
SimpleBench	74.1%	—
ARC-AGI-1	94.5%	—
CritPt	30%	—
Chess Puzzles	58.6%	—
EnigmaEval	23.8%	—
LMArena Hard Prompts	—	1095
Epoch Capabilities Index	159.12	—

Math GPT-5.4 Pro leads

GPT-5.4 Pro: 72.0 (#17), Llama 3.2 3B: 29.9 (#213)

Math benchmarks
Benchmark	GPT-5.4 Pro	Llama 3.2 3B
FrontierMath (Tiers 1-3)	82.5%	—
FrontierMath Tier 4	58.5%	—
LMArena Math	—	1126
FrontierMath (Feb 2025 set)	50%	—
FrontierMath Tier 4 (v1)	37.5%	—

Knowledge GPT-5.4 Pro leads

GPT-5.4 Pro: 68.3 (#6), Llama 3.2 3B: 29.1 (#232)

Knowledge benchmarks
Benchmark	GPT-5.4 Pro	Llama 3.2 3B
GPQA Diamond	94.6%	—
Humanity's Last Exam	44.3%	—
SimpleQA Verified	46.3%	—
Vectara Hallucination Rate	8.3%	—
LMArena Expert	—	1090

Multilingual Not comparable

GPT-5.4 Pro: —, Llama 3.2 3B: 26.4 (#276)

Multilingual benchmarks
Benchmark	GPT-5.4 Pro	Llama 3.2 3B
LMArena Non-English	—	1019
LMArena Chinese	—	1017
LMArena German	—	1056
LMArena Russian	—	949

Instruction Following Not comparable

GPT-5.4 Pro: —, Llama 3.2 3B: 56.3 (#270)

Instruction Following benchmarks
Benchmark	GPT-5.4 Pro	Llama 3.2 3B
LMArena Instruction Following	—	1089

Long Context Not comparable

GPT-5.4 Pro: —, Llama 3.2 3B: 33.4 (#256)

Long Context benchmarks
Benchmark	GPT-5.4 Pro	Llama 3.2 3B
LMArena Longer Query	—	1101

Writing & Preference Not comparable

GPT-5.4 Pro: —, Llama 3.2 3B: 24.9 (#302)

Writing & Preference benchmarks
Benchmark	GPT-5.4 Pro	Llama 3.2 3B
LMArena Text	—	1110
LMArena Creative Writing	—	1094
EQ-Bench Creative Writing	—	595
LMArena Multi-Turn	—	1105

Frequently asked questions

Is GPT-5.4 Pro better than Llama 3.2 3B?

Which is cheaper, GPT-5.4 Pro or Llama 3.2 3B?

Llama 3.2 3B is cheaper. It lists at $0.05 per million input tokens and $0.33 per million output tokens; GPT-5.4 Pro lists at $30 and $180.

Is GPT-5.4 Pro or Llama 3.2 3B better for coding?

GPT-5.4 Pro scores higher on coding benchmarks: 42.6 versus 27.1 in the Noometry coding category.

Which has the bigger context window?

GPT-5.4 Pro does, with 1.05M tokens against 131K.

How many benchmarks do GPT-5.4 Pro and Llama 3.2 3B share?

0 benchmarks have published results for both models. GPT-5.4 Pro has 16 scored results on Noometry and Llama 3.2 3B has 18.