Model comparison
Grok 4.3 vs o1
Grok 4.3 is the stronger model overall, scoring 43.8 to 40.9 on the Noometry Index.
Last verified . 27 shared benchmarks.
Summary
- They share 27 benchmarks with published results for both. Grok 4.3 scores higher in 6 categories and o1 in 4 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Grok 4.3 leads 52.5 to 41.5.
- The biggest single-benchmark swing is FrontierMath (Tiers 1-3): 42.8% for Grok 4.3 and 14.7% for o1.
- Grok 4.3 is cheaper at $1.25 / $2.50 per million input/output tokens, against $15 / $60 for o1.
- Grok 4.3 accepts more context: 1M tokens versus 200K.
Side by side
| Grok 4.3 | o1 | |
|---|---|---|
| Provider | xAI | OpenAI |
| Noometry Index | 43.8 | 40.9 |
| Released | 2026-04-17 | 2024-09-12 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | 200K |
| Max output | 30K | 100K |
| Input $ / M tokens | $1.25 | $15 |
| Output $ / M tokens | $2.50 | $60 |
| Results tracked | 40 | 52 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o1 leads
Grok 4.3: 41.6 (#121), o1: 46.1 (#70)
| Benchmark | Grok 4.3 | o1 |
|---|---|---|
| WeirdML | 49.9% | 47.6% |
| LMArena Coding | 1415 | 1367 |
| Aider Polyglot | — | 61.7% |
| LMArena WebDev | 1357 | — |
| SciCode | 47.3% | — |
| LiveBench Coding | — | 69.7% |
| CadEval | — | 56% |
| ALE-Bench | 944.17 | — |
| HumanEval+ | — | 89% |
| MBPP+ | — | 80.2% |
Agentic & Tool Use Grok 4.3 leads
Grok 4.3: 27.7 (#99), o1: 24.6 (#117)
| Benchmark | Grok 4.3 | o1 |
|---|---|---|
| Cybench | — | 10% |
| GDP.pdf | 8% | — |
| LMArena Search | 1165 | — |
| METR Time Horizons | — | 51.1% |
| Vending-Bench 2 | 35.26 | — |
Reasoning Grok 4.3 leads
Grok 4.3: 35.9 (#68), o1: 27.9 (#111)
| Benchmark | Grok 4.3 | o1 |
|---|---|---|
| Chess Puzzles | 25% | 15% |
| LMArena Hard Prompts | 1396 | 1371 |
| DTBench | 90.7% | 74.7% |
| LMCA | 38.3% | 22.3% |
| Epoch Capabilities Index | 149.16 | 141.91 |
| SimpleBench | — | 41.7% |
| NYT Connections (extended) | 55.2% | — |
| ARC-AGI-1 | — | 30.7% |
| CritPt | 8% | — |
| EnigmaEval | — | 5.7% |
| LiveBench Reasoning | — | 91.6% |
| LiveBench Data Analysis | — | 65.5% |
| ForecastBench | 60.3 | — |
| LiveBench | — | 75.7% |
Math Grok 4.3 leads
Grok 4.3: 46.0 (#74), o1: 36.1 (#175)
| Benchmark | Grok 4.3 | o1 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 42.8% | 14.7% |
| OTIS Mock AIME 2024-2025 | 93.3% | 73.3% |
| LMArena Math | 1388 | 1388 |
| FrontierMath Tier 4 | 14.6% | — |
| ProofBench | 11% | — |
| LiveBench Math | — | 80.3% |
| MATH Level 5 | — | 94.7% |
| FrontierMath (Feb 2025 set) | — | 9.3% |
Knowledge Grok 4.3 leads
Grok 4.3: 52.5 (#62), o1: 41.5 (#110)
| Benchmark | Grok 4.3 | o1 |
|---|---|---|
| GPQA Diamond | 88.8% | 76.8% |
| SimpleQA Verified | 33.2% | 41.1% |
| LMArena Expert | 1385 | 1361 |
| Humanity's Last Exam | — | 8% |
| Confabulations | — | 11.7% |
Multimodal o1 leads
Grok 4.3: 31.6 (#104), o1: 34.2 (#93)
| Benchmark | Grok 4.3 | o1 |
|---|---|---|
| LMArena Vision | 1229 | 1168 |
| GeoBench | — | 80% |
| VPCT | — | 37% |
| Blueprint-Bench 2 | 0% | — |
| SpatialViz-Bench | — | 41.4% |
Multilingual Grok 4.3 leads
Grok 4.3: 50.5 (#120), o1: 48.6 (#142)
| Benchmark | Grok 4.3 | o1 |
|---|---|---|
| LMArena Non-English | 1385 | 1358 |
| LMArena Chinese | 1422 | 1394 |
| LMArena French | 1412 | 1344 |
| LMArena German | 1395 | 1337 |
| LMArena Japanese | 1379 | 1346 |
| LMArena Korean | 1356 | 1396 |
| LMArena Russian | 1399 | 1356 |
| LMArena Spanish | 1398 | 1345 |
Instruction Following o1 leads
Grok 4.3: 72.1 (#140), o1: 74.8 (#86)
| Benchmark | Grok 4.3 | o1 |
|---|---|---|
| LMArena Instruction Following | 1366 | 1367 |
| LiveBench Instruction Following | — | 81.5% |
Long Context o1 leads
Grok 4.3: 42.5 (#123), o1: 50.3 (#9)
| Benchmark | Grok 4.3 | o1 |
|---|---|---|
| LMArena Longer Query | 1393 | 1378 |
| Fiction.LiveBench | — | 83.3% |
Writing & Preference Grok 4.3 leads
Grok 4.3: 58.5 (#118), o1: 55.6 (#144)
| Benchmark | Grok 4.3 | o1 |
|---|---|---|
| LMArena Text | 1397 | 1366 |
| LMArena Creative Writing | 1380 | 1348 |
| LMArena Multi-Turn | 1406 | 1369 |
| Short-Story Creative Writing | — | 70.2% |
| EQ-Bench 4 | 1075 | — |
| LiveBench Language | — | 65.4% |
Frequently asked questions
Is Grok 4.3 better than o1?
Grok 4.3 is the stronger model overall, scoring 43.8 to 40.9 on the Noometry Index.
Which is cheaper, Grok 4.3 or o1?
Grok 4.3 is cheaper. It lists at $1.25 per million input tokens and $2.50 per million output tokens; o1 lists at $15 and $60.
Is Grok 4.3 or o1 better for coding?
o1 scores higher on coding benchmarks: 46.1 versus 41.6 in the Noometry coding category.
Which has the bigger context window?
Grok 4.3 does, with 1M tokens against 200K.
How many benchmarks do Grok 4.3 and o1 share?
27 benchmarks have published results for both models. Grok 4.3 has 40 scored results on Noometry and o1 has 52.