Model comparison
GPT-4o mini vs Grok 4
Grok 4 is the stronger model overall, scoring 48.1 to 25.5 on the Noometry Index.
Last verified . 36 shared benchmarks.
Summary
- They share 36 benchmarks with published results for both. GPT-4o mini scores higher in 0 categories and Grok 4 in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where Grok 4 leads 48.4 to 10.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 6.9% for GPT-4o mini and 84% for Grok 4.
Side by side
| GPT-4o mini | Grok 4 | |
|---|---|---|
| Provider | OpenAI | xAI |
| Noometry Index | 25.5 | 48.1 |
| Released | 2024-07-18 | 2025-07-09 |
| Weights | Proprietary | Proprietary |
| Context window | 128K | — |
| Max output | 16K | — |
| Input $ / M tokens | $0.15 | — |
| Output $ / M tokens | $0.60 | — |
| Results tracked | 60 | 48 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4 leads
GPT-4o mini: 22.0 (#335), Grok 4: 50.3 (#46)
| Benchmark | GPT-4o mini | Grok 4 |
|---|---|---|
| Aider Polyglot | 3.6% | 79.6% |
| WeirdML | 11.8% | 45.7% |
| LMArena Coding | 1290 | 1408 |
| BigCodeBench Instruct | 46.1% | — |
| LiveBench Coding | 43.1% | — |
| BigCodeBench Complete | 57.4% | — |
| HumanEval+ | 83.5% | — |
| MBPP+ | 72.2% | — |
Agentic & Tool Use Grok 4 leads
GPT-4o mini: 27.5 (#101), Grok 4: 32.3 (#68)
| Benchmark | GPT-4o mini | Grok 4 |
|---|---|---|
| BALROG | 17.4% | 43.6% |
| Terminal-Bench | — | 27.2% |
| Berkeley Function Calling Leaderboard | — | 63% |
| GDPval | — | 21.1% |
| Cybench | — | 43% |
| DeepResearch Bench | — | 47.3% |
| LMArena Search | — | 1142 |
| METR Time Horizons | — | 66.6% |
Reasoning Grok 4 leads
GPT-4o mini: 8.7 (#347), Grok 4: 36.7 (#65)
| Benchmark | GPT-4o mini | Grok 4 |
|---|---|---|
| ARC-AGI-2 | 0% | 16% |
| SimpleBench | 10.7% | 60.5% |
| Kagi LLM Benchmark | 28.8% | 73.6% |
| Chess Puzzles | 0% | 28% |
| LMArena Hard Prompts | 1267 | 1409 |
| Epoch Capabilities Index | 126.56 | 146.44 |
| ARC-AGI-1 | — | 66.7% |
| LiveBench Reasoning | 32.8% | — |
| Mystery Game Puzzles | 12% | — |
| DTBench | 54.4% | — |
| LiveBench Data Analysis | 50% | — |
| LMCA | 10.4% | — |
| ForecastBench | — | 60.9 |
| LiveBench | 41.3% | — |
| PIQA | 88.7% | — |
Math Grok 4 leads
GPT-4o mini: 10.4 (#314), Grok 4: 48.4 (#64)
| Benchmark | GPT-4o mini | Grok 4 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 6.9% | 84% |
| Omni-MATH | 28% | 60.3% |
| LMArena Math | 1267 | 1422 |
| FrontierMath (Tiers 1-3) | 0.7% | — |
| LiveBench Math | 36.3% | — |
| MATH Level 5 | 52.6% | — |
| FrontierMath (Feb 2025 set) | — | 19.7% |
| FrontierMath Tier 4 (v1) | — | 2.1% |
| GSM8K | 91.3% | — |
Knowledge Grok 4 leads
GPT-4o mini: 17.7 (#284), Grok 4: 53.8 (#55)
| Benchmark | GPT-4o mini | Grok 4 |
|---|---|---|
| GPQA Diamond | 37.7% | 87% |
| MMLU-Pro | 60.3% | 85.1% |
| Confabulations | 37.2% | 12.4% |
| GPQA (HELM) | 36.8% | 72.7% |
| LMArena Expert | 1235 | 1415 |
| SimpleQA Verified | 8.3% | — |
| BoolQ | 88.7% | — |
| MMLU | 81.8% | — |
Multimodal Grok 4 leads
GPT-4o mini: 25.9 (#122), Grok 4: 33.7 (#94)
| Benchmark | GPT-4o mini | Grok 4 |
|---|---|---|
| LMArena Vision | 1066 | 1210 |
| GeoBench | 64% | 45% |
| Video-MME | 64.8% | — |
| VPCT | 34% | — |
Multilingual Grok 4 leads
GPT-4o mini: 42.0 (#199), Grok 4: 51.8 (#103)
| Benchmark | GPT-4o mini | Grok 4 |
|---|---|---|
| LMArena Non-English | 1266 | 1403 |
| LMArena Chinese | 1265 | 1427 |
| LMArena French | 1297 | 1418 |
| LMArena German | 1272 | 1429 |
| LMArena Japanese | 1216 | 1394 |
| LMArena Korean | 1195 | 1377 |
| LMArena Russian | 1275 | 1410 |
| LMArena Spanish | 1276 | 1420 |
Instruction Following Grok 4 leads
GPT-4o mini: 61.9 (#239), Grok 4: 79.2 (#5)
| Benchmark | GPT-4o mini | Grok 4 |
|---|---|---|
| IFEval | 78.2% | 94.9% |
| LMArena Instruction Following | 1258 | 1387 |
| LiveBench Instruction Following | 56.8% | — |
Long Context Grok 4 leads
GPT-4o mini: 39.1 (#186), Grok 4: 63.1 (#4)
| Benchmark | GPT-4o mini | Grok 4 |
|---|---|---|
| LMArena Longer Query | 1289 | 1409 |
| Fiction.LiveBench | — | 94.4% |
Writing & Preference Grok 4 leads
GPT-4o mini: 39.5 (#248), Grok 4: 58.5 (#116)
| Benchmark | GPT-4o mini | Grok 4 |
|---|---|---|
| LMArena Text | 1286 | 1411 |
| LMArena Creative Writing | 1268 | 1397 |
| Short-Story Creative Writing | 67.2% | 76.9% |
| WildBench | 79.1% | 79.7% |
| LMArena Multi-Turn | 1285 | 1416 |
| EQ-Bench Creative Writing | 873 | — |
| LiveBench Language | 28.6% | — |
Frequently asked questions
Is GPT-4o mini better than Grok 4?
Grok 4 is the stronger model overall, scoring 48.1 to 25.5 on the Noometry Index.
Is GPT-4o mini or Grok 4 better for coding?
Grok 4 scores higher on coding benchmarks: 50.3 versus 22.0 in the Noometry coding category.
How many benchmarks do GPT-4o mini and Grok 4 share?
36 benchmarks have published results for both models. GPT-4o mini has 60 scored results on Noometry and Grok 4 has 48.