Model comparison
GPT-4.1 nano vs GPT-5.2 Pro
GPT-5.2 Pro is the stronger model overall, scoring 52.3 to 27.9 on the Noometry Index. GPT-4.1 nano costs 330× less per token, which makes it the better buy when GPT-5.2 Pro's lead doesn't matter for your workload.
Last verified . 3 shared benchmarks.
Summary
- They share 3 benchmarks with published results for both. GPT-4.1 nano scores higher in 0 categories and GPT-5.2 Pro in 2 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-5.2 Pro leads 51.5 to 8.5.
- The biggest single-benchmark swing is ARC-AGI-1: 0% for GPT-4.1 nano and 90.5% for GPT-5.2 Pro.
- GPT-4.1 nano is cheaper at $0.10 / $0.40 per million input/output tokens, against $21 / $168 for GPT-5.2 Pro.
- GPT-4.1 nano accepts more context: 1.05M tokens versus 400K.
Side by side
| GPT-4.1 nano | GPT-5.2 Pro | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 27.9 | 52.3 |
| Released | 2025-04-14 | 2025-12-11 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 400K |
| Max output | 33K | 128K |
| Input $ / M tokens | $0.10 | $21 |
| Output $ / M tokens | $0.40 | $168 |
| Results tracked | 38 | 8 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
GPT-4.1 nano: 24.1 (#330), GPT-5.2 Pro: —
| Benchmark | GPT-4.1 nano | GPT-5.2 Pro |
|---|---|---|
| Aider Polyglot | 8.9% | — |
| SciCode | 25.9% | — |
| WeirdML | 19% | — |
| LMArena Coding | 1306 | — |
Agentic & Tool Use Not comparable
GPT-4.1 nano: 26.5 (#104), GPT-5.2 Pro: —
| Benchmark | GPT-4.1 nano | GPT-5.2 Pro |
|---|---|---|
| Berkeley Function Calling Leaderboard | 33% | — |
Reasoning GPT-5.2 Pro leads
GPT-4.1 nano: 8.5 (#349), GPT-5.2 Pro: 51.5 (#33)
| Benchmark | GPT-4.1 nano | GPT-5.2 Pro |
|---|---|---|
| ARC-AGI-2 | 0% | 54.2% |
| ARC-AGI-1 | 0% | 90.5% |
| Epoch Capabilities Index | 129.62 | 155.4 |
| SimpleBench | — | 57.4% |
| Kagi LLM Benchmark | 33.3% | — |
| NYT Connections (extended) | — | 79.3% |
| CritPt | 0% | — |
| LMArena Hard Prompts | 1286 | — |
| DTBench | 52.5% | — |
| LMCA | 5.5% | — |
Math GPT-5.2 Pro leads
GPT-4.1 nano: 26.9 (#252), GPT-5.2 Pro: 65.3 (#29)
| Benchmark | GPT-4.1 nano | GPT-5.2 Pro |
|---|---|---|
| FrontierMath (Tiers 1-3) | — | 74% |
| FrontierMath Tier 4 | — | 46% |
| OTIS Mock AIME 2024-2025 | 28.9% | — |
| Omni-MATH | 36.7% | — |
| LMArena Math | 1274 | — |
| MATH Level 5 | 70% | — |
| FrontierMath (Feb 2025 set) | 1% | — |
| FrontierMath Tier 4 (v1) | — | 31.3% |
Knowledge Not comparable
GPT-4.1 nano: 21.8 (#273), GPT-5.2 Pro: —
| Benchmark | GPT-4.1 nano | GPT-5.2 Pro |
|---|---|---|
| GPQA Diamond | 48.9% | — |
| SimpleQA Verified | 6% | — |
| MMLU-Pro | 55% | — |
| GPQA (HELM) | 50.7% | — |
| LMArena Expert | 1272 | — |
Multimodal Not comparable
GPT-4.1 nano: 29.2 (#113), GPT-5.2 Pro: —
| Benchmark | GPT-4.1 nano | GPT-5.2 Pro |
|---|---|---|
| LMArena Vision | 1063 | — |
Multilingual Not comparable
GPT-4.1 nano: 41.6 (#205), GPT-5.2 Pro: —
| Benchmark | GPT-4.1 nano | GPT-5.2 Pro |
|---|---|---|
| LMArena Non-English | 1260 | — |
| LMArena Chinese | 1270 | — |
| LMArena German | 1288 | — |
| LMArena Japanese | 1198 | — |
| LMArena Russian | 1261 | — |
Instruction Following Not comparable
GPT-4.1 nano: 67.8 (#193), GPT-5.2 Pro: —
| Benchmark | GPT-4.1 nano | GPT-5.2 Pro |
|---|---|---|
| IFEval | 84.3% | — |
| LMArena Instruction Following | 1267 | — |
Long Context Not comparable
GPT-4.1 nano: 23.7 (#296), GPT-5.2 Pro: —
| Benchmark | GPT-4.1 nano | GPT-5.2 Pro |
|---|---|---|
| Fiction.LiveBench | 25% | — |
| LMArena Longer Query | 1283 | — |
Writing & Preference Not comparable
GPT-4.1 nano: 40.5 (#243), GPT-5.2 Pro: —
| Benchmark | GPT-4.1 nano | GPT-5.2 Pro |
|---|---|---|
| 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-5.2 Pro?
GPT-5.2 Pro is the stronger model overall, scoring 52.3 to 27.9 on the Noometry Index. GPT-4.1 nano costs 330× less per token, which makes it the better buy when GPT-5.2 Pro's lead doesn't matter for your workload.
Which is cheaper, GPT-4.1 nano or GPT-5.2 Pro?
GPT-4.1 nano is cheaper. It lists at $0.10 per million input tokens and $0.40 per million output tokens; GPT-5.2 Pro lists at $21 and $168.
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-5.2 Pro share?
3 benchmarks have published results for both models. GPT-4.1 nano has 38 scored results on Noometry and GPT-5.2 Pro has 8.