Model comparison
GPT-4o vs Grok 4.3
Grok 4.3 is the stronger model overall, scoring 43.8 to 28.6 on the Noometry Index.
Last verified . 30 shared benchmarks.
Summary
- They share 30 benchmarks with published results for both. GPT-4o scores higher in 1 category and Grok 4.3 in 9 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where Grok 4.3 leads 46.0 to 10.6.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 6.4% for GPT-4o and 93.3% for Grok 4.3.
- Grok 4.3 is cheaper at $1.25 / $2.50 per million input/output tokens, against $2.50 / $10 for GPT-4o.
- Grok 4.3 accepts more context: 1M tokens versus 128K.
Side by side
| GPT-4o | Grok 4.3 | |
|---|---|---|
| Provider | OpenAI | xAI |
| Noometry Index | 28.6 | 43.8 |
| Released | 2024-05-13 | 2026-04-17 |
| Weights | Proprietary | Proprietary |
| Context window | 128K | 1M |
| Max output | 16K | 30K |
| Input $ / M tokens | $2.50 | $1.25 |
| Output $ / M tokens | $10 | $2.50 |
| Results tracked | 72 | 40 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4.3 leads
GPT-4o: 24.8 (#328), Grok 4.3: 41.6 (#121)
| Benchmark | GPT-4o | Grok 4.3 |
|---|---|---|
| WeirdML | 25.1% | 49.9% |
| LMArena Coding | 1297 | 1415 |
| SWE-bench Verified | 31% | — |
| SWE-bench Verified (bash only) | 21.6% | — |
| Aider Polyglot | 45.3% | — |
| LMArena WebDev | — | 1357 |
| SciCode | — | 47.3% |
| GSO | 0% | — |
| BigCodeBench Instruct | 51.1% | — |
| LiveBench Coding | 51.4% | — |
| BigCodeBench Complete | 61.1% | — |
| CadEval | 26% | — |
| ALE-Bench | — | 944.17 |
| HumanEval+ | 87.2% | — |
| MBPP+ | 72.2% | — |
Agentic & Tool Use Grok 4.3 leads
GPT-4o: 21.0 (#141), Grok 4.3: 27.7 (#99)
| Benchmark | GPT-4o | Grok 4.3 |
|---|---|---|
| LMArena Search | 1006 | 1165 |
| GDPval | 9.9% | — |
| TheAgentCompany | 8.6% | — |
| Cybench | 12.5% | — |
| BALROG | 32.3% | — |
| GDP.pdf | — | 8% |
| METR Time Horizons | 40.8% | — |
| Vending-Bench 2 | — | 35.26 |
Reasoning Grok 4.3 leads
GPT-4o: 9.4 (#343), Grok 4.3: 35.9 (#68)
| Benchmark | GPT-4o | Grok 4.3 |
|---|---|---|
| CritPt | 0% | 8% |
| Chess Puzzles | 13% | 25% |
| LMArena Hard Prompts | 1281 | 1396 |
| DTBench | 64.5% | 90.7% |
| LMCA | 16.6% | 38.3% |
| Epoch Capabilities Index | 128.97 | 149.16 |
| ForecastBench | 57.7 | 60.3 |
| ARC-AGI-2 | 0% | — |
| SimpleBench | 17.8% | — |
| NYT Connections (extended) | — | 55.2% |
| ARC-AGI-1 | 4.5% | — |
| EnigmaEval | 0.8% | — |
| LiveBench Reasoning | 55.8% | — |
| LiveBench Data Analysis | 60.9% | — |
| LiveBench | 55.3% | — |
Math Grok 4.3 leads
GPT-4o: 10.6 (#312), Grok 4.3: 46.0 (#74)
| Benchmark | GPT-4o | Grok 4.3 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 0.4% | 42.8% |
| OTIS Mock AIME 2024-2025 | 6.4% | 93.3% |
| LMArena Math | 1285 | 1388 |
| FrontierMath Tier 4 | — | 14.6% |
| ProofBench | — | 11% |
| Omni-MATH | 29.3% | — |
| LiveBench Math | 49.5% | — |
| MATH Level 5 | 53.3% | — |
| FrontierMath (Feb 2025 set) | 0.3% | — |
Knowledge Grok 4.3 leads
GPT-4o: 28.8 (#242), Grok 4.3: 52.5 (#62)
| Benchmark | GPT-4o | Grok 4.3 |
|---|---|---|
| GPQA Diamond | 49.2% | 88.8% |
| SimpleQA Verified | 26% | 33.2% |
| LMArena Expert | 1250 | 1385 |
| Humanity's Last Exam | 2.7% | — |
| MMLU-Pro | 71.3% | — |
| Confabulations | 15.3% | — |
| Vectara Hallucination Rate | 9.6% | — |
| GPQA (HELM) | 52% | — |
| MMLU | 88.1% | — |
Multimodal GPT-4o leads
GPT-4o: 34.5 (#91), Grok 4.3: 31.6 (#104)
| Benchmark | GPT-4o | Grok 4.3 |
|---|---|---|
| LMArena Vision | 1137 | 1229 |
| Video-MME | 71.9% | — |
| GeoBench | 71% | — |
| VPCT | 40% | — |
| Blueprint-Bench 2 | — | 0% |
| ScienceQA | 88.5% | — |
Multilingual Grok 4.3 leads
GPT-4o: 43.2 (#186), Grok 4.3: 50.5 (#120)
| Benchmark | GPT-4o | Grok 4.3 |
|---|---|---|
| LMArena Non-English | 1283 | 1385 |
| LMArena Chinese | 1277 | 1422 |
| LMArena French | 1304 | 1412 |
| LMArena German | 1282 | 1395 |
| LMArena Japanese | 1257 | 1379 |
| LMArena Korean | 1234 | 1356 |
| LMArena Russian | 1286 | 1399 |
| LMArena Spanish | 1292 | 1398 |
Instruction Following Grok 4.3 leads
GPT-4o: 66.6 (#207), Grok 4.3: 72.1 (#140)
| Benchmark | GPT-4o | Grok 4.3 |
|---|---|---|
| LMArena Instruction Following | 1278 | 1366 |
| LiveBench Instruction Following | 68.6% | — |
| IFEval | 81.7% | — |
Long Context Grok 4.3 leads
GPT-4o: 39.4 (#179), Grok 4.3: 42.5 (#123)
| Benchmark | GPT-4o | Grok 4.3 |
|---|---|---|
| LMArena Longer Query | 1289 | 1393 |
| Fiction.LiveBench | 66.7% | — |
Writing & Preference Grok 4.3 leads
GPT-4o: 52.6 (#166), Grok 4.3: 58.5 (#118)
| Benchmark | GPT-4o | Grok 4.3 |
|---|---|---|
| LMArena Text | 1300 | 1397 |
| LMArena Creative Writing | 1292 | 1380 |
| LMArena Multi-Turn | 1302 | 1406 |
| Short-Story Creative Writing | 81.8% | — |
| WildBench | 82.8% | — |
| EQ-Bench 4 | — | 1075 |
| LiveBench Language | 47.6% | — |
Frequently asked questions
Is GPT-4o better than Grok 4.3?
Grok 4.3 is the stronger model overall, scoring 43.8 to 28.6 on the Noometry Index.
Which is cheaper, GPT-4o 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-4o lists at $2.50 and $10.
Is GPT-4o or Grok 4.3 better for coding?
Grok 4.3 scores higher on coding benchmarks: 41.6 versus 24.8 in the Noometry coding category.
Which has the bigger context window?
Grok 4.3 does, with 1M tokens against 128K.
How many benchmarks do GPT-4o and Grok 4.3 share?
30 benchmarks have published results for both models. GPT-4o has 72 scored results on Noometry and Grok 4.3 has 40.