Model comparison

GPT-5.1-Codex vs Llama 3.2 1B

GPT-5.1-Codex is the stronger model overall, scoring 38.6 to 20.1 on the Noometry Index. Llama 3.2 1B costs 49× less per token, which makes it the better buy when GPT-5.1-Codex's lead doesn't matter for your workload.

Last verified October 10, 2026. 0 shared benchmarks.

GPT-5.1-Codex OpenAI

38.6

Rank #186 Reported

Llama 3.2 1B

Summary

The widest gap is in agentic & tool use, where GPT-5.1-Codex leads 38.0 to 14.6.
Llama 3.2 1B is cheaper at $0.027 / $0.20 per million input/output tokens, against $1.25 / $10 for GPT-5.1-Codex.
GPT-5.1-Codex accepts more context: 400K tokens versus 60K.
Llama 3.2 1B has downloadable open weights; the other is API-only.

Side by side

GPT-5.1-Codex and Llama 3.2 1B specifications
	GPT-5.1-Codex	Llama 3.2 1B
Provider	OpenAI	Meta
Noometry Index	38.6	20.1
Released	2025-11-12	2024-09-24
Weights	Proprietary	Open
Context window	400K	60K
Max output	128K	54K
Input $ / M tokens	$1.25	$0.027
Output $ / M tokens	$10	$0.20
Results tracked	6	22

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

Category by category

Coding GPT-5.1-Codex leads

GPT-5.1-Codex: 41.9 (#116), Llama 3.2 1B: 21.1 (#338)

Coding benchmarks
Benchmark	GPT-5.1-Codex	Llama 3.2 1B
SWE-bench Verified (bash only)	66%	—
LMArena WebDev	1337	—
BigCodeBench Instruct	—	8.2%
LMArena Coding	—	1070
BigCodeBench Complete	—	11.3%
ALE-Bench	1,245	—

Agentic & Tool Use GPT-5.1-Codex leads

GPT-5.1-Codex: 38.0 (#33), Llama 3.2 1B: 14.6 (#150)

Agentic & Tool Use benchmarks
Benchmark	GPT-5.1-Codex	Llama 3.2 1B
Terminal-Bench	60.4%	—
Berkeley Function Calling Leaderboard	—	10.8%
BALROG	—	6.6%
METR Time Horizons	70.8%	—

Reasoning Not comparable

GPT-5.1-Codex: —, Llama 3.2 1B: 16.2 (#308)

Reasoning benchmarks
Benchmark	GPT-5.1-Codex	Llama 3.2 1B
Chess Puzzles	—	0%
LMArena Hard Prompts	—	1044
Epoch Capabilities Index	—	101.99

Math GPT-5.1-Codex leads

GPT-5.1-Codex: 30.3 (#235), Llama 3.2 1B: 10.4 (#313)

Math benchmarks
Benchmark	GPT-5.1-Codex	Llama 3.2 1B
OTIS Mock AIME 2024-2025	—	0.6%
ProofBench	9%	—
LMArena Math	—	1086

Knowledge Not comparable

GPT-5.1-Codex: —, Llama 3.2 1B: 7.2 (#312)

Knowledge benchmarks
Benchmark	GPT-5.1-Codex	Llama 3.2 1B
GPQA Diamond	—	23.9%
LMArena Expert	—	1007

Multilingual Not comparable

GPT-5.1-Codex: —, Llama 3.2 1B: 23.8 (#292)

Multilingual benchmarks
Benchmark	GPT-5.1-Codex	Llama 3.2 1B
LMArena Non-English	—	973
LMArena Chinese	—	959
LMArena German	—	1014
LMArena Russian	—	941

Instruction Following Not comparable

GPT-5.1-Codex: —, Llama 3.2 1B: 52.4 (#290)

Instruction Following benchmarks
Benchmark	GPT-5.1-Codex	Llama 3.2 1B
LMArena Instruction Following	—	1031

Long Context Not comparable

GPT-5.1-Codex: —, Llama 3.2 1B: 31.9 (#274)

Long Context benchmarks
Benchmark	GPT-5.1-Codex	Llama 3.2 1B
LMArena Longer Query	—	1050

Writing & Preference Not comparable

GPT-5.1-Codex: —, Llama 3.2 1B: 21.3 (#310)

Writing & Preference benchmarks
Benchmark	GPT-5.1-Codex	Llama 3.2 1B
LMArena Text	—	1055
LMArena Creative Writing	—	1033
EQ-Bench Creative Writing	—	200
LMArena Multi-Turn	—	1030

Frequently asked questions

Is GPT-5.1-Codex better than Llama 3.2 1B?

Which is cheaper, GPT-5.1-Codex or Llama 3.2 1B?

Llama 3.2 1B is cheaper. It lists at $0.027 per million input tokens and $0.20 per million output tokens; GPT-5.1-Codex lists at $1.25 and $10.

Is GPT-5.1-Codex or Llama 3.2 1B better for coding?

GPT-5.1-Codex scores higher on coding benchmarks: 41.9 versus 21.1 in the Noometry coding category.

Which has the bigger context window?

GPT-5.1-Codex does, with 400K tokens against 60K.

How many benchmarks do GPT-5.1-Codex and Llama 3.2 1B share?

0 benchmarks have published results for both models. GPT-5.1-Codex has 6 scored results on Noometry and Llama 3.2 1B has 22.