Model comparison
GPT-4.1 nano vs Grok 4.3
Grok 4.3 is the stronger model overall, scoring 43.8 to 27.9 on the Noometry Index. GPT-4.1 nano costs 8.9× less per token, which makes it the better buy when Grok 4.3's lead doesn't matter for your workload.
Last verified . 24 shared benchmarks.
Summary
- They share 24 benchmarks with published results for both. GPT-4.1 nano scores higher in 0 categories and Grok 4.3 in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Grok 4.3 leads 52.5 to 21.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 28.9% for GPT-4.1 nano and 93.3% for Grok 4.3.
- GPT-4.1 nano is cheaper at $0.10 / $0.40 per million input/output tokens, against $1.25 / $2.50 for Grok 4.3.
- GPT-4.1 nano accepts more context: 1.05M tokens versus 1M.
Side by side
| GPT-4.1 nano | Grok 4.3 | |
|---|---|---|
| Provider | OpenAI | xAI |
| Noometry Index | 27.9 | 43.8 |
| Released | 2025-04-14 | 2026-04-17 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 1M |
| Max output | 33K | 30K |
| Input $ / M tokens | $0.10 | $1.25 |
| Output $ / M tokens | $0.40 | $2.50 |
| Results tracked | 38 | 40 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4.3 leads
GPT-4.1 nano: 24.1 (#330), Grok 4.3: 41.6 (#121)
| Benchmark | GPT-4.1 nano | Grok 4.3 |
|---|---|---|
| SciCode | 25.9% | 47.3% |
| WeirdML | 19% | 49.9% |
| LMArena Coding | 1306 | 1415 |
| Aider Polyglot | 8.9% | — |
| LMArena WebDev | — | 1357 |
| ALE-Bench | — | 944.17 |
Agentic & Tool Use Grok 4.3 leads
GPT-4.1 nano: 26.5 (#104), Grok 4.3: 27.7 (#99)
| Benchmark | GPT-4.1 nano | Grok 4.3 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 33% | — |
| GDP.pdf | — | 8% |
| LMArena Search | — | 1165 |
| Vending-Bench 2 | — | 35.26 |
Reasoning Grok 4.3 leads
GPT-4.1 nano: 8.5 (#349), Grok 4.3: 35.9 (#68)
| Benchmark | GPT-4.1 nano | Grok 4.3 |
|---|---|---|
| CritPt | 0% | 8% |
| LMArena Hard Prompts | 1286 | 1396 |
| DTBench | 52.5% | 90.7% |
| LMCA | 5.5% | 38.3% |
| Epoch Capabilities Index | 129.62 | 149.16 |
| ARC-AGI-2 | 0% | — |
| Kagi LLM Benchmark | 33.3% | — |
| NYT Connections (extended) | — | 55.2% |
| ARC-AGI-1 | 0% | — |
| Chess Puzzles | — | 25% |
| ForecastBench | — | 60.3 |
Math Grok 4.3 leads
GPT-4.1 nano: 26.9 (#252), Grok 4.3: 46.0 (#74)
| Benchmark | GPT-4.1 nano | Grok 4.3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 28.9% | 93.3% |
| LMArena Math | 1274 | 1388 |
| FrontierMath (Tiers 1-3) | — | 42.8% |
| FrontierMath Tier 4 | — | 14.6% |
| ProofBench | — | 11% |
| Omni-MATH | 36.7% | — |
| MATH Level 5 | 70% | — |
| FrontierMath (Feb 2025 set) | 1% | — |
Knowledge Grok 4.3 leads
GPT-4.1 nano: 21.8 (#273), Grok 4.3: 52.5 (#62)
| Benchmark | GPT-4.1 nano | Grok 4.3 |
|---|---|---|
| GPQA Diamond | 48.9% | 88.8% |
| SimpleQA Verified | 6% | 33.2% |
| LMArena Expert | 1272 | 1385 |
| MMLU-Pro | 55% | — |
| GPQA (HELM) | 50.7% | — |
Multimodal Grok 4.3 leads
GPT-4.1 nano: 29.2 (#113), Grok 4.3: 31.6 (#104)
| Benchmark | GPT-4.1 nano | Grok 4.3 |
|---|---|---|
| LMArena Vision | 1063 | 1229 |
| Blueprint-Bench 2 | — | 0% |
Multilingual Grok 4.3 leads
GPT-4.1 nano: 41.6 (#205), Grok 4.3: 50.5 (#120)
| Benchmark | GPT-4.1 nano | Grok 4.3 |
|---|---|---|
| LMArena Non-English | 1260 | 1385 |
| LMArena Chinese | 1270 | 1422 |
| LMArena German | 1288 | 1395 |
| LMArena Japanese | 1198 | 1379 |
| LMArena Russian | 1261 | 1399 |
| LMArena French | — | 1412 |
| LMArena Korean | — | 1356 |
| LMArena Spanish | — | 1398 |
Instruction Following Grok 4.3 leads
GPT-4.1 nano: 67.8 (#193), Grok 4.3: 72.1 (#140)
| Benchmark | GPT-4.1 nano | Grok 4.3 |
|---|---|---|
| LMArena Instruction Following | 1267 | 1366 |
| IFEval | 84.3% | — |
Long Context Grok 4.3 leads
GPT-4.1 nano: 23.7 (#296), Grok 4.3: 42.5 (#123)
| Benchmark | GPT-4.1 nano | Grok 4.3 |
|---|---|---|
| LMArena Longer Query | 1283 | 1393 |
| Fiction.LiveBench | 25% | — |
Writing & Preference Grok 4.3 leads
GPT-4.1 nano: 40.5 (#243), Grok 4.3: 58.5 (#118)
| Benchmark | GPT-4.1 nano | Grok 4.3 |
|---|---|---|
| LMArena Text | 1285 | 1397 |
| LMArena Creative Writing | 1260 | 1380 |
| LMArena Multi-Turn | 1277 | 1406 |
| EQ-Bench Creative Writing | 946 | — |
| WildBench | 81.2% | — |
| EQ-Bench 4 | — | 1075 |
Frequently asked questions
Is GPT-4.1 nano better than Grok 4.3?
Grok 4.3 is the stronger model overall, scoring 43.8 to 27.9 on the Noometry Index. GPT-4.1 nano costs 8.9× less per token, which makes it the better buy when Grok 4.3's lead doesn't matter for your workload.
Which is cheaper, GPT-4.1 nano or Grok 4.3?
GPT-4.1 nano is cheaper. It lists at $0.10 per million input tokens and $0.40 per million output tokens; Grok 4.3 lists at $1.25 and $2.50.
Is GPT-4.1 nano or Grok 4.3 better for coding?
Grok 4.3 scores higher on coding benchmarks: 41.6 versus 24.1 in the Noometry coding category.
Which has the bigger context window?
GPT-4.1 nano does, with 1.05M tokens against 1M.
How many benchmarks do GPT-4.1 nano and Grok 4.3 share?
24 benchmarks have published results for both models. GPT-4.1 nano has 38 scored results on Noometry and Grok 4.3 has 40.