Model comparison
Grok 4.3 vs o1-mini
Grok 4.3 is the stronger model overall, scoring 43.8 to 34.0 on the Noometry Index.
Last verified . 21 shared benchmarks.
Summary
- They share 21 benchmarks with published results for both. Grok 4.3 scores higher in 9 categories and o1-mini in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.3 leads 35.9 to 8.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 93.3% for Grok 4.3 and 46.9% for o1-mini.
Side by side
| Grok 4.3 | o1-mini | |
|---|---|---|
| Provider | xAI | OpenAI |
| Noometry Index | 43.8 | 34.0 |
| Released | 2026-04-17 | 2024-09-12 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | — |
| Max output | 30K | — |
| Input $ / M tokens | $1.25 | — |
| Output $ / M tokens | $2.50 | — |
| Results tracked | 40 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4.3 leads
Grok 4.3: 41.6 (#121), o1-mini: 35.5 (#224)
| Benchmark | Grok 4.3 | o1-mini |
|---|---|---|
| WeirdML | 49.9% | 36.3% |
| LMArena Coding | 1415 | 1362 |
| Aider Polyglot | — | 32.9% |
| LMArena WebDev | 1357 | — |
| SciCode | 47.3% | — |
| LiveBench Coding | — | 48% |
| ALE-Bench | 944.17 | — |
| HumanEval+ | — | 89% |
| MBPP+ | — | 78.8% |
Agentic & Tool Use Grok 4.3 leads
Grok 4.3: 27.7 (#99), o1-mini: 24.6 (#118)
| Benchmark | Grok 4.3 | o1-mini |
|---|---|---|
| Cybench | — | 10% |
| GDP.pdf | 8% | — |
| LMArena Search | 1165 | — |
| Vending-Bench 2 | 35.26 | — |
Reasoning Grok 4.3 leads
Grok 4.3: 35.9 (#68), o1-mini: 8.8 (#346)
| Benchmark | Grok 4.3 | o1-mini |
|---|---|---|
| LMArena Hard Prompts | 1396 | 1333 |
| Epoch Capabilities Index | 149.16 | 135.82 |
| ARC-AGI-2 | — | 0.8% |
| SimpleBench | — | 18.1% |
| NYT Connections (extended) | 55.2% | — |
| ARC-AGI-1 | — | 14% |
| CritPt | 8% | — |
| Chess Puzzles | 25% | — |
| LiveBench Reasoning | — | 72.3% |
| DTBench | 90.7% | — |
| LiveBench Data Analysis | — | 57.9% |
| LMCA | 38.3% | — |
| ForecastBench | 60.3 | — |
| LiveBench | — | 57.8% |
Math Grok 4.3 leads
Grok 4.3: 46.0 (#74), o1-mini: 35.4 (#186)
| Benchmark | Grok 4.3 | o1-mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 93.3% | 46.9% |
| LMArena Math | 1388 | 1358 |
| FrontierMath (Tiers 1-3) | 42.8% | — |
| FrontierMath Tier 4 | 14.6% | — |
| ProofBench | 11% | — |
| LiveBench Math | — | 62% |
| MATH Level 5 | — | 89.2% |
| FrontierMath (Feb 2025 set) | — | 1.7% |
Knowledge Grok 4.3 leads
Grok 4.3: 52.5 (#62), o1-mini: 34.9 (#192)
| Benchmark | Grok 4.3 | o1-mini |
|---|---|---|
| GPQA Diamond | 88.8% | 62.4% |
| LMArena Expert | 1385 | 1316 |
| SimpleQA Verified | 33.2% | — |
| Confabulations | — | 18.6% |
Multimodal Not comparable
Grok 4.3: 31.6 (#104), o1-mini: —
| Benchmark | Grok 4.3 | o1-mini |
|---|---|---|
| LMArena Vision | 1229 | — |
| Blueprint-Bench 2 | 0% | — |
Multilingual Grok 4.3 leads
Grok 4.3: 50.5 (#120), o1-mini: 43.6 (#182)
| Benchmark | Grok 4.3 | o1-mini |
|---|---|---|
| LMArena Non-English | 1385 | 1289 |
| LMArena Chinese | 1422 | 1314 |
| LMArena French | 1412 | 1293 |
| LMArena German | 1395 | 1278 |
| LMArena Japanese | 1379 | 1245 |
| LMArena Korean | 1356 | 1223 |
| LMArena Russian | 1399 | 1283 |
| LMArena Spanish | 1398 | 1303 |
Instruction Following Grok 4.3 leads
Grok 4.3: 72.1 (#140), o1-mini: 66.7 (#206)
| Benchmark | Grok 4.3 | o1-mini |
|---|---|---|
| LMArena Instruction Following | 1366 | 1304 |
| LiveBench Instruction Following | — | 65.4% |
Long Context Grok 4.3 leads
Grok 4.3: 42.5 (#123), o1-mini: 40.1 (#161)
| Benchmark | Grok 4.3 | o1-mini |
|---|---|---|
| LMArena Longer Query | 1393 | 1320 |
Writing & Preference Grok 4.3 leads
Grok 4.3: 58.5 (#118), o1-mini: 48.4 (#202)
| Benchmark | Grok 4.3 | o1-mini |
|---|---|---|
| LMArena Text | 1397 | 1317 |
| LMArena Creative Writing | 1380 | 1244 |
| LMArena Multi-Turn | 1406 | 1314 |
| Short-Story Creative Writing | — | 64.9% |
| EQ-Bench 4 | 1075 | — |
| LiveBench Language | — | 40.9% |
Frequently asked questions
Is Grok 4.3 better than o1-mini?
Grok 4.3 is the stronger model overall, scoring 43.8 to 34.0 on the Noometry Index.
Is Grok 4.3 or o1-mini better for coding?
Grok 4.3 scores higher on coding benchmarks: 41.6 versus 35.5 in the Noometry coding category.
How many benchmarks do Grok 4.3 and o1-mini share?
21 benchmarks have published results for both models. Grok 4.3 has 40 scored results on Noometry and o1-mini has 39.