Model comparison

GPT-5.2 Codex vs Nemotron 3.5 Lightning

GPT-5.2 Codex is the stronger model overall, scoring 42.2 to 39.3 on the Noometry Index. Nemotron 3.5 Lightning costs 57× less per token, which makes it the better buy when GPT-5.2 Codex's lead doesn't matter for your workload.

Last verified October 10, 2026. 0 shared benchmarks.

GPT-5.2 Codex OpenAI

42.2

Rank #107 Reported

Nemotron 3.5 Lightning

NVIDIA

39.3

Rank #156 Confirmed

Summary

The widest gap is in coding, where GPT-5.2 Codex leads 45.4 to 39.6.
Nemotron 3.5 Lightning is cheaper at $0.06 / $0.16 per million input/output tokens, against $1.75 / $14 for GPT-5.2 Codex.
GPT-5.2 Codex accepts more context: 400K tokens versus 262K.
Nemotron 3.5 Lightning has downloadable open weights; the other is API-only.

Side by side

GPT-5.2 Codex and Nemotron 3.5 Lightning specifications
	GPT-5.2 Codex	Nemotron 3.5 Lightning
Provider	OpenAI	NVIDIA
Noometry Index	42.2	39.3
Released	2025-12-18	2026-08-11
Weights	Proprietary	Open
Context window	400K	262K
Max output	128K	262K
Input $ / M tokens	$1.75	$0.06
Output $ / M tokens	$14	$0.16
Results tracked	5	18

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

Category by category

Coding GPT-5.2 Codex leads

GPT-5.2 Codex: 45.4 (#66), Nemotron 3.5 Lightning: 39.6 (#143)

Coding benchmarks
Benchmark	GPT-5.2 Codex	Nemotron 3.5 Lightning
SWE-bench Verified (bash only)	72.8%	—
LMArena WebDev	1339	—
SWE-bench Multilingual	66.3%	—
LMArena Coding	—	1370
ALE-Bench	1,300	—

Agentic & Tool Use Not comparable

GPT-5.2 Codex: 40.7 (#20), Nemotron 3.5 Lightning: —

Agentic & Tool Use benchmarks
Benchmark	GPT-5.2 Codex	Nemotron 3.5 Lightning
Terminal-Bench	66.5%	—

Reasoning Not comparable

GPT-5.2 Codex: —, Nemotron 3.5 Lightning: 25.7 (#128)

Reasoning benchmarks
Benchmark	GPT-5.2 Codex	Nemotron 3.5 Lightning
LMArena Hard Prompts	—	1335

Math Not comparable

GPT-5.2 Codex: —, Nemotron 3.5 Lightning: 34.7 (#156)

Math benchmarks
Benchmark	GPT-5.2 Codex	Nemotron 3.5 Lightning
LMArena Math	—	1355

Knowledge Not comparable

GPT-5.2 Codex: —, Nemotron 3.5 Lightning: 36.9 (#154)

Knowledge benchmarks
Benchmark	GPT-5.2 Codex	Nemotron 3.5 Lightning
LMArena Expert	—	1354

Multilingual Not comparable

GPT-5.2 Codex: —, Nemotron 3.5 Lightning: 44.0 (#175)

Multilingual benchmarks
Benchmark	GPT-5.2 Codex	Nemotron 3.5 Lightning
LMArena Non-English	—	1292
LMArena Chinese	—	1356
LMArena French	—	1369
LMArena German	—	1280
LMArena Japanese	—	1213
LMArena Korean	—	1233
LMArena Russian	—	1257
LMArena Spanish	—	1321

Instruction Following Not comparable

GPT-5.2 Codex: —, Nemotron 3.5 Lightning: 69.8 (#166)

Instruction Following benchmarks
Benchmark	GPT-5.2 Codex	Nemotron 3.5 Lightning
LMArena Instruction Following	—	1317

Long Context Not comparable

GPT-5.2 Codex: —, Nemotron 3.5 Lightning: 39.9 (#160)

Long Context benchmarks
Benchmark	GPT-5.2 Codex	Nemotron 3.5 Lightning
LMArena Longer Query	—	1312

Writing & Preference Not comparable

GPT-5.2 Codex: —, Nemotron 3.5 Lightning: 48.5 (#198)

Writing & Preference benchmarks
Benchmark	GPT-5.2 Codex	Nemotron 3.5 Lightning
LMArena Text	—	1324
LMArena Creative Writing	—	1254
EQ-Bench Creative Writing	—	1280
LMArena Multi-Turn	—	1327

Frequently asked questions

Is GPT-5.2 Codex better than Nemotron 3.5 Lightning?

Which is cheaper, GPT-5.2 Codex or Nemotron 3.5 Lightning?

Nemotron 3.5 Lightning is cheaper. It lists at $0.06 per million input tokens and $0.16 per million output tokens; GPT-5.2 Codex lists at $1.75 and $14.

Is GPT-5.2 Codex or Nemotron 3.5 Lightning better for coding?

GPT-5.2 Codex scores higher on coding benchmarks: 45.4 versus 39.6 in the Noometry coding category.

Which has the bigger context window?

GPT-5.2 Codex does, with 400K tokens against 262K.

How many benchmarks do GPT-5.2 Codex and Nemotron 3.5 Lightning share?

0 benchmarks have published results for both models. GPT-5.2 Codex has 5 scored results on Noometry and Nemotron 3.5 Lightning has 18.