Model comparison
GPT-4.1 nano vs GPT-5.3 Codex
GPT-5.3 Codex is the stronger model overall, scoring 45.5 to 27.7 on the Noometry Index. GPT-4.1 nano costs 27× less per token, which makes it the better buy when GPT-5.3 Codex's lead doesn't matter for your workload.
Last verified . 2 shared benchmarks.
Summary
- They share 2 benchmarks with published results for both. GPT-4.1 nano scores higher in 0 categories and GPT-5.3 Codex in 2 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in coding, where GPT-5.3 Codex leads 48.5 to 23.8.
- The biggest single-benchmark swing is WeirdML: 19% for GPT-4.1 nano and 79.3% for GPT-5.3 Codex.
- GPT-4.1 nano is cheaper at $0.10 / $0.40 per million input/output tokens, against $1.75 / $14 for GPT-5.3 Codex.
- GPT-4.1 nano accepts more context: 1.05M tokens versus 400K.
Side by side
| GPT-4.1 nano | GPT-5.3 Codex | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 27.7 | 45.5 |
| Released | 2025-04-14 | 2026-02-05 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 400K |
| Max output | 33K | 128K |
| Input $ / M tokens | $0.10 | $1.75 |
| Output $ / M tokens | $0.40 | $14 |
| Results tracked | 38 | 8 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.3 Codex leads
GPT-4.1 nano: 23.8 (#325), GPT-5.3 Codex: 48.5 (#51)
| Benchmark | GPT-4.1 nano | GPT-5.3 Codex |
|---|---|---|
| WeirdML | 19% | 79.3% |
| SWE-bench Verified | — | 74.8% |
| Aider Polyglot | 8.9% | — |
| LMArena WebDev | — | 1408 |
| SciCode | 25.9% | — |
| LMArena Coding | 1306 | — |
| ALE-Bench | — | 1,655 |
Agentic & Tool Use GPT-5.3 Codex leads
GPT-4.1 nano: 26.3 (#98), GPT-5.3 Codex: 47.8 (#9)
| Benchmark | GPT-4.1 nano | GPT-5.3 Codex |
|---|---|---|
| Terminal-Bench | — | 78.4% |
| Berkeley Function Calling Leaderboard | 33% | — |
| METR Time Horizons | — | 74.5% |
| Vending-Bench 2 | — | 5,940 |
Reasoning Not comparable
GPT-4.1 nano: 8.6 (#344), GPT-5.3 Codex: —
| Benchmark | GPT-4.1 nano | GPT-5.3 Codex |
|---|---|---|
| Epoch Capabilities Index | 129.62 | 156.84 |
| ARC-AGI-2 | 0% | — |
| Kagi LLM Benchmark | 33.3% | — |
| ARC-AGI-1 | 0% | — |
| CritPt | 0% | — |
| LMArena Hard Prompts | 1286 | — |
| DTBench | 52.5% | — |
| LMCA | 5.5% | — |
Math Not comparable
GPT-4.1 nano: 25.5 (#246), GPT-5.3 Codex: —
| Benchmark | GPT-4.1 nano | GPT-5.3 Codex |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 28.9% | — |
| Omni-MATH | 36.7% | — |
| LMArena Math | 1274 | — |
| MATH Level 5 | 70% | — |
| FrontierMath (Feb 2025 set) | 1% | — |
Knowledge Not comparable
GPT-4.1 nano: 21.8 (#268), GPT-5.3 Codex: —
| Benchmark | GPT-4.1 nano | GPT-5.3 Codex |
|---|---|---|
| GPQA Diamond | 48.9% | — |
| SimpleQA Verified | 6% | — |
| MMLU-Pro | 55% | — |
| GPQA (HELM) | 50.7% | — |
| LMArena Expert | 1272 | — |
Multimodal Not comparable
GPT-4.1 nano: 28.6 (#108), GPT-5.3 Codex: —
| Benchmark | GPT-4.1 nano | GPT-5.3 Codex |
|---|---|---|
| LMArena Vision | 1063 | — |
Multilingual Not comparable
GPT-4.1 nano: 41.8 (#200), GPT-5.3 Codex: —
| Benchmark | GPT-4.1 nano | GPT-5.3 Codex |
|---|---|---|
| LMArena Non-English | 1260 | — |
| LMArena Chinese | 1270 | — |
| LMArena German | 1288 | — |
| LMArena Japanese | 1199 | — |
| LMArena Russian | 1261 | — |
Instruction Following Not comparable
GPT-4.1 nano: 68.0 (#188), GPT-5.3 Codex: —
| Benchmark | GPT-4.1 nano | GPT-5.3 Codex |
|---|---|---|
| IFEval | 84.3% | — |
| LMArena Instruction Following | 1267 | — |
Long Context Not comparable
GPT-4.1 nano: 23.7 (#291), GPT-5.3 Codex: —
| Benchmark | GPT-4.1 nano | GPT-5.3 Codex |
|---|---|---|
| Fiction.LiveBench | 25% | — |
| LMArena Longer Query | 1283 | — |
Writing & Preference Not comparable
GPT-4.1 nano: 40.7 (#238), GPT-5.3 Codex: —
| Benchmark | GPT-4.1 nano | GPT-5.3 Codex |
|---|---|---|
| LMArena Text | 1285 | — |
| LMArena Creative Writing | 1260 | — |
| EQ-Bench Creative Writing | 946 | — |
| WildBench | 81.2% | — |
| LMArena Multi-Turn | 1277 | — |
Frequently asked questions
Is GPT-4.1 nano better than GPT-5.3 Codex?
GPT-5.3 Codex is the stronger model overall, scoring 45.5 to 27.7 on the Noometry Index. GPT-4.1 nano costs 27× less per token, which makes it the better buy when GPT-5.3 Codex's lead doesn't matter for your workload.
Which is cheaper, GPT-4.1 nano or GPT-5.3 Codex?
GPT-4.1 nano is cheaper. It lists at $0.10 per million input tokens and $0.40 per million output tokens; GPT-5.3 Codex lists at $1.75 and $14.
Is GPT-4.1 nano or GPT-5.3 Codex better for coding?
GPT-5.3 Codex scores higher on coding benchmarks: 48.5 versus 23.8 in the Noometry coding category.
Which has the bigger context window?
GPT-4.1 nano does, with 1.05M tokens against 400K.
How many benchmarks do GPT-4.1 nano and GPT-5.3 Codex share?
2 benchmarks have published results for both models. GPT-4.1 nano has 38 scored results on Noometry and GPT-5.3 Codex has 8.