Model comparison
GPT-4.1 vs Grok 4.3
Grok 4.3 is the stronger model overall, scoring 43.8 to 35.9 on the Noometry Index.
Last verified . 29 shared benchmarks.
Summary
- They share 29 benchmarks with published results for both. GPT-4.1 scores higher in 2 categories and Grok 4.3 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.3 leads 35.9 to 11.7.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 38.3% for GPT-4.1 and 93.3% for Grok 4.3.
- Grok 4.3 is cheaper at $1.25 / $2.50 per million input/output tokens, against $2 / $8 for GPT-4.1.
- GPT-4.1 accepts more context: 1.05M tokens versus 1M.
Side by side
| GPT-4.1 | Grok 4.3 | |
|---|---|---|
| Provider | OpenAI | xAI |
| Noometry Index | 35.9 | 43.8 |
| Released | 2025-04-14 | 2026-04-17 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 1M |
| Max output | 33K | 30K |
| Input $ / M tokens | $2 | $1.25 |
| Output $ / M tokens | $8 | $2.50 |
| Results tracked | 52 | 40 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4.3 leads
GPT-4.1: 34.4 (#238), Grok 4.3: 41.6 (#121)
| Benchmark | GPT-4.1 | Grok 4.3 |
|---|---|---|
| WeirdML | 39% | 49.9% |
| LMArena Coding | 1391 | 1415 |
| ALE-Bench | 558.1 | 944.17 |
| SWE-bench Verified | 48.5% | — |
| SWE-bench Verified (bash only) | 39.6% | — |
| Aider Polyglot | 52.4% | — |
| LMArena WebDev | — | 1357 |
| SciCode | — | 47.3% |
| CadEval | 42% | — |
Agentic & Tool Use GPT-4.1 leads
GPT-4.1: 34.7 (#43), Grok 4.3: 27.7 (#99)
| Benchmark | GPT-4.1 | Grok 4.3 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 54% | — |
| GDP.pdf | — | 8% |
| LMArena Search | — | 1165 |
| Vending-Bench 2 | — | 35.26 |
Reasoning Grok 4.3 leads
GPT-4.1: 11.7 (#339), Grok 4.3: 35.9 (#68)
| Benchmark | GPT-4.1 | Grok 4.3 |
|---|---|---|
| Chess Puzzles | 6% | 25% |
| LMArena Hard Prompts | 1384 | 1396 |
| DTBench | 68.3% | 90.7% |
| LMCA | 25.6% | 38.3% |
| Epoch Capabilities Index | 136.78 | 149.16 |
| ForecastBench | 61.5 | 60.3 |
| ARC-AGI-2 | 0.4% | — |
| SimpleBench | 27% | — |
| Kagi LLM Benchmark | 52.3% | — |
| NYT Connections (extended) | — | 55.2% |
| ARC-AGI-1 | 5.5% | — |
| CritPt | — | 8% |
| EnigmaEval | 2.2% | — |
Math Grok 4.3 leads
GPT-4.1: 22.3 (#280), Grok 4.3: 46.0 (#74)
| Benchmark | GPT-4.1 | Grok 4.3 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 6% | 42.8% |
| OTIS Mock AIME 2024-2025 | 38.3% | 93.3% |
| LMArena Math | 1370 | 1388 |
| FrontierMath Tier 4 | — | 14.6% |
| ProofBench | — | 11% |
| Omni-MATH | 47.1% | — |
| MATH Level 5 | 83% | — |
| FrontierMath (Feb 2025 set) | 5.5% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Grok 4.3 leads
GPT-4.1: 37.1 (#160), Grok 4.3: 52.5 (#62)
| Benchmark | GPT-4.1 | Grok 4.3 |
|---|---|---|
| GPQA Diamond | 66.9% | 88.8% |
| SimpleQA Verified | 31.1% | 33.2% |
| LMArena Expert | 1364 | 1385 |
| Humanity's Last Exam | 5.4% | — |
| MMLU-Pro | 81.1% | — |
| Vectara Hallucination Rate | 5.6% | — |
| GPQA (HELM) | 65.9% | — |
Multimodal GPT-4.1 leads
GPT-4.1: 38.2 (#67), Grok 4.3: 31.6 (#104)
| Benchmark | GPT-4.1 | Grok 4.3 |
|---|---|---|
| LMArena Vision | 1211 | 1229 |
| GeoBench | 72% | — |
| Blueprint-Bench 2 | — | 0% |
Multilingual Grok 4.3 leads
GPT-4.1: 49.4 (#133), Grok 4.3: 50.5 (#120)
| Benchmark | GPT-4.1 | Grok 4.3 |
|---|---|---|
| LMArena Non-English | 1370 | 1385 |
| LMArena Chinese | 1382 | 1422 |
| LMArena French | 1382 | 1412 |
| LMArena German | 1381 | 1395 |
| LMArena Japanese | 1319 | 1379 |
| LMArena Korean | 1339 | 1356 |
| LMArena Russian | 1377 | 1399 |
| LMArena Spanish | 1376 | 1398 |
Instruction Following Too close to call
GPT-4.1: 71.3 (#153), Grok 4.3: 72.1 (#140)
| Benchmark | GPT-4.1 | Grok 4.3 |
|---|---|---|
| LMArena Instruction Following | 1367 | 1366 |
| IFEval | 83.8% | — |
Long Context Grok 4.3 leads
GPT-4.1: 40.0 (#163), Grok 4.3: 42.5 (#123)
| Benchmark | GPT-4.1 | Grok 4.3 |
|---|---|---|
| LMArena Longer Query | 1385 | 1393 |
| Fiction.LiveBench | 63.9% | — |
Writing & Preference Too close to call
GPT-4.1: 57.6 (#125), Grok 4.3: 58.5 (#118)
| Benchmark | GPT-4.1 | Grok 4.3 |
|---|---|---|
| LMArena Text | 1383 | 1397 |
| LMArena Creative Writing | 1363 | 1380 |
| LMArena Multi-Turn | 1398 | 1406 |
| EQ-Bench Creative Writing | 1420 | — |
| WildBench | 85.4% | — |
| EQ-Bench 4 | — | 1075 |
Frequently asked questions
Is GPT-4.1 better than Grok 4.3?
Grok 4.3 is the stronger model overall, scoring 43.8 to 35.9 on the Noometry Index.
Which is cheaper, GPT-4.1 or Grok 4.3?
Grok 4.3 is cheaper. It lists at $1.25 per million input tokens and $2.50 per million output tokens; GPT-4.1 lists at $2 and $8.
Is GPT-4.1 or Grok 4.3 better for coding?
Grok 4.3 scores higher on coding benchmarks: 41.6 versus 34.4 in the Noometry coding category.
Which has the bigger context window?
GPT-4.1 does, with 1.05M tokens against 1M.
How many benchmarks do GPT-4.1 and Grok 4.3 share?
29 benchmarks have published results for both models. GPT-4.1 has 52 scored results on Noometry and Grok 4.3 has 40.