Model comparison
GPT-4o mini vs Grok 4 Fast
Grok 4 Fast is the stronger model overall, scoring 39.0 to 25.4 on the Noometry Index.
Last verified . 22 shared benchmarks.
Summary
- They share 22 benchmarks with published results for both. GPT-4o mini scores higher in 0 categories and Grok 4 Fast in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Grok 4 Fast leads 36.1 to 9.9.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 28.8% for GPT-4o mini and 66.1% for Grok 4 Fast.
Side by side
| GPT-4o mini | Grok 4 Fast | |
|---|---|---|
| Provider | OpenAI | xAI |
| Noometry Index | 25.4 | 39.0 |
| Released | 2024-07-18 | 2025-09-19 |
| Weights | Proprietary | Proprietary |
| Context window | 128K | — |
| Max output | 16K | — |
| Input $ / M tokens | $0.15 | — |
| Output $ / M tokens | $0.60 | — |
| Results tracked | 60 | 30 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4 Fast leads
GPT-4o mini: 21.6 (#330), Grok 4 Fast: 32.3 (#264)
| Benchmark | GPT-4o mini | Grok 4 Fast |
|---|---|---|
| WeirdML | 11.8% | 42.9% |
| LMArena Coding | 1290 | 1429 |
| Aider Polyglot | 3.6% | — |
| LMArena WebDev | — | 1160 |
| BigCodeBench Instruct | 46.1% | — |
| LiveBench Coding | 43.1% | — |
| BigCodeBench Complete | 57.4% | — |
| HumanEval+ | 83.5% | — |
| MBPP+ | 72.2% | — |
Agentic & Tool Use Grok 4 Fast leads
GPT-4o mini: 27.2 (#95), Grok 4 Fast: 29.3 (#80)
| Benchmark | GPT-4o mini | Grok 4 Fast |
|---|---|---|
| τ²-bench Banking | — | 15.7% |
| Cybench | — | 30% |
| BALROG | 17.4% | — |
| LMArena Search | — | 1171 |
Reasoning Grok 4 Fast leads
GPT-4o mini: 8.7 (#343), Grok 4 Fast: 22.5 (#179)
| Benchmark | GPT-4o mini | Grok 4 Fast |
|---|---|---|
| ARC-AGI-2 | 0% | 5.3% |
| Kagi LLM Benchmark | 28.8% | 66.1% |
| LMArena Hard Prompts | 1267 | 1413 |
| DTBench | 54.4% | 82.7% |
| Epoch Capabilities Index | 126.56 | 144.21 |
| SimpleBench | 10.7% | — |
| ARC-AGI-1 | — | 48.5% |
| Chess Puzzles | 0% | — |
| LiveBench Reasoning | 32.8% | — |
| Mystery Game Puzzles | 12% | — |
| LiveBench Data Analysis | 50% | — |
| LMCA | 10.4% | — |
| ForecastBench | — | 60.5 |
| LiveBench | 41.3% | — |
| PIQA | 88.7% | — |
Math Grok 4 Fast leads
GPT-4o mini: 9.9 (#307), Grok 4 Fast: 36.1 (#126)
| Benchmark | GPT-4o mini | Grok 4 Fast |
|---|---|---|
| LMArena Math | 1267 | 1419 |
| FrontierMath (Tiers 1-3) | 0.7% | — |
| OTIS Mock AIME 2024-2025 | 6.9% | — |
| Omni-MATH | 28% | — |
| LiveBench Math | 36.3% | — |
| MATH Level 5 | 52.6% | — |
| GSM8K | 91.3% | — |
Knowledge Grok 4 Fast leads
GPT-4o mini: 17.7 (#279), Grok 4 Fast: 31.5 (#211)
| Benchmark | GPT-4o mini | Grok 4 Fast |
|---|---|---|
| LMArena Expert | 1235 | 1411 |
| GPQA Diamond | 37.7% | — |
| SimpleQA Verified | 8.3% | — |
| MMLU-Pro | 60.3% | — |
| Confabulations | 37.2% | — |
| Vectara Hallucination Rate | — | 19.7% |
| GPQA (HELM) | 36.8% | — |
| BoolQ | 88.7% | — |
| MMLU | 81.8% | — |
Multimodal Not comparable
GPT-4o mini: 25.3 (#117), Grok 4 Fast: —
| Benchmark | GPT-4o mini | Grok 4 Fast |
|---|---|---|
| LMArena Vision | 1066 | — |
| Video-MME | 64.8% | — |
| GeoBench | 64% | — |
| VPCT | 34% | — |
Multilingual Grok 4 Fast leads
GPT-4o mini: 42.2 (#194), Grok 4 Fast: 51.5 (#106)
| Benchmark | GPT-4o mini | Grok 4 Fast |
|---|---|---|
| LMArena Non-English | 1266 | 1397 |
| LMArena Chinese | 1264 | 1458 |
| LMArena French | 1296 | 1433 |
| LMArena German | 1272 | 1383 |
| LMArena Japanese | 1216 | 1358 |
| LMArena Korean | 1195 | 1359 |
| LMArena Russian | 1275 | 1387 |
| LMArena Spanish | 1276 | 1414 |
Instruction Following Grok 4 Fast leads
GPT-4o mini: 62.1 (#234), Grok 4 Fast: 73.4 (#116)
| Benchmark | GPT-4o mini | Grok 4 Fast |
|---|---|---|
| LMArena Instruction Following | 1259 | 1388 |
| LiveBench Instruction Following | 56.8% | — |
| IFEval | 78.2% | — |
Long Context Grok 4 Fast leads
GPT-4o mini: 39.1 (#181), Grok 4 Fast: 63.2 (#3)
| Benchmark | GPT-4o mini | Grok 4 Fast |
|---|---|---|
| LMArena Longer Query | 1289 | 1415 |
| Fiction.LiveBench | — | 94.4% |
Writing & Preference Grok 4 Fast leads
GPT-4o mini: 39.7 (#243), Grok 4 Fast: 60.2 (#96)
| Benchmark | GPT-4o mini | Grok 4 Fast |
|---|---|---|
| LMArena Text | 1286 | 1407 |
| LMArena Creative Writing | 1268 | 1388 |
| LMArena Multi-Turn | 1285 | 1414 |
| Short-Story Creative Writing | 67.2% | — |
| EQ-Bench Creative Writing | 873 | — |
| WildBench | 79.1% | — |
| LiveBench Language | 28.6% | — |
Frequently asked questions
Is GPT-4o mini better than Grok 4 Fast?
Grok 4 Fast is the stronger model overall, scoring 39.0 to 25.4 on the Noometry Index.
Is GPT-4o mini or Grok 4 Fast better for coding?
Grok 4 Fast scores higher on coding benchmarks: 32.3 versus 21.6 in the Noometry coding category.
How many benchmarks do GPT-4o mini and Grok 4 Fast share?
22 benchmarks have published results for both models. GPT-4o mini has 60 scored results on Noometry and Grok 4 Fast has 30.