Model comparison
GPT-4.5 vs Grok 3
Grok 3 is the stronger model overall, scoring 39.9 to 37.2 on the Noometry Index.
Last verified . 29 shared benchmarks.
Summary
- They share 29 benchmarks with published results for both. GPT-4.5 scores higher in 5 categories and Grok 3 in 4 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Grok 3 leads 46.2 to 32.5.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 37.8% for GPT-4.5 and 55.6% for Grok 3.
Side by side
| GPT-4.5 | Grok 3 | |
|---|---|---|
| Provider | OpenAI | xAI |
| Noometry Index | 37.2 | 39.9 |
| Released | 2025-02-27 | 2025-04-09 |
| Weights | Proprietary | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 42 | 40 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
GPT-4.5: 42.2 (#109), Grok 3: 41.9 (#115)
| Benchmark | GPT-4.5 | Grok 3 |
|---|---|---|
| Aider Polyglot | 44.9% | 53.3% |
| WeirdML | 39.4% | 37.2% |
| LMArena Coding | 1396 | 1432 |
| LiveBench Coding | 75.2% | — |
Agentic & Tool Use Grok 3 leads
GPT-4.5: 27.9 (#97), Grok 3: 30.5 (#76)
Reasoning Too close to call
GPT-4.5: 13.9 (#330), Grok 3: 13.7 (#333)
| Benchmark | GPT-4.5 | Grok 3 |
|---|---|---|
| ARC-AGI-2 | 0.8% | 0% |
| SimpleBench | 34.5% | 36.1% |
| ARC-AGI-1 | 10.3% | 5.5% |
| LMArena Hard Prompts | 1403 | 1434 |
| Epoch Capabilities Index | 136.74 | 138.33 |
| Kagi LLM Benchmark | — | 61.3% |
| EnigmaEval | 3.2% | — |
| LiveBench Reasoning | 71.1% | — |
| LiveBench Data Analysis | 64.3% | — |
| ForecastBench | 61.7 | — |
| LiveBench | 69% | — |
Math Grok 3 leads
GPT-4.5: 32.6 (#211), Grok 3: 38.0 (#145)
| Benchmark | GPT-4.5 | Grok 3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 37.8% | 55.6% |
| LMArena Math | 1412 | 1391 |
| MATH Level 5 | 78.6% | 88.7% |
| Omni-MATH | — | 46.4% |
| LiveBench Math | 69.3% | — |
| FrontierMath (Feb 2025 set) | — | 3.8% |
| FrontierMath Tier 4 (v1) | — | 0% |
Knowledge Grok 3 leads
GPT-4.5: 32.5 (#211), Grok 3: 46.2 (#82)
| Benchmark | GPT-4.5 | Grok 3 |
|---|---|---|
| GPQA Diamond | 68.7% | 75.8% |
| Confabulations | 13.6% | 14.2% |
| LMArena Expert | 1394 | 1421 |
| Humanity's Last Exam | 5.4% | — |
| MMLU-Pro | — | 78.8% |
| Vectara Hallucination Rate | — | 5.8% |
| GPQA (HELM) | — | 65% |
Multimodal Not comparable
GPT-4.5: 37.6 (#71), Grok 3: —
| Benchmark | GPT-4.5 | Grok 3 |
|---|---|---|
| LMArena Vision | 1195 | — |
| VPCT | 45% | — |
Multilingual Too close to call
GPT-4.5: 52.5 (#83), Grok 3: 52.3 (#87)
| Benchmark | GPT-4.5 | Grok 3 |
|---|---|---|
| LMArena Non-English | 1413 | 1410 |
| LMArena Chinese | 1421 | 1448 |
| LMArena French | 1418 | 1460 |
| LMArena German | 1457 | 1431 |
| LMArena Japanese | 1416 | 1387 |
| LMArena Korean | 1392 | 1373 |
| LMArena Russian | 1419 | 1416 |
| LMArena Spanish | — | 1417 |
Instruction Following Grok 3 leads
GPT-4.5: 72.6 (#134), Grok 3: 75.0 (#73)
| Benchmark | GPT-4.5 | Grok 3 |
|---|---|---|
| LMArena Instruction Following | 1404 | 1409 |
| LiveBench Instruction Following | 72.3% | — |
| IFEval | — | 88.4% |
Long Context GPT-4.5 leads
GPT-4.5: 40.4 (#155), Grok 3: 38.7 (#192)
| Benchmark | GPT-4.5 | Grok 3 |
|---|---|---|
| Fiction.LiveBench | 63.9% | 58.3% |
| LMArena Longer Query | 1406 | 1439 |
Writing & Preference GPT-4.5 leads
GPT-4.5: 56.9 (#134), Grok 3: 55.8 (#141)
| Benchmark | GPT-4.5 | Grok 3 |
|---|---|---|
| LMArena Text | 1417 | 1426 |
| LMArena Creative Writing | 1394 | 1414 |
| Short-Story Creative Writing | 75.6% | 76.4% |
| EQ-Bench Creative Writing | 1258 | 1186 |
| LMArena Multi-Turn | 1444 | 1425 |
| WildBench | — | 84.9% |
| LiveBench Language | 61.5% | — |
Frequently asked questions
Is GPT-4.5 better than Grok 3?
Grok 3 is the stronger model overall, scoring 39.9 to 37.2 on the Noometry Index.
Is GPT-4.5 or Grok 3 better for coding?
They score almost the same on coding (42.2 vs 41.9); test both on your own repository before choosing.
How many benchmarks do GPT-4.5 and Grok 3 share?
29 benchmarks have published results for both models. GPT-4.5 has 42 scored results on Noometry and Grok 3 has 40.