Model comparison
Grok-3 mini vs Grok 4 Fast
Grok-3 mini is the stronger model overall, scoring 41.2 to 39.4 on the Noometry Index.
Last verified . 23 shared benchmarks.
Summary
- They share 23 benchmarks with published results for both. Grok-3 mini scores higher in 4 categories and Grok 4 Fast in 4 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in long context, where Grok 4 Fast leads 63.2 to 41.0.
- The biggest single-benchmark swing is ARC-AGI-1: 16.5% for Grok-3 mini and 48.5% for Grok 4 Fast.
Side by side
| Grok-3 mini | Grok 4 Fast | |
|---|---|---|
| Provider | xAI | xAI |
| Noometry Index | 41.2 | 39.4 |
| Released | 2025-04-09 | 2025-09-19 |
| Weights | Proprietary | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 35 | 30 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok-3 mini leads
Grok-3 mini: 40.8 (#131), Grok 4 Fast: 32.5 (#271)
| Benchmark | Grok-3 mini | Grok 4 Fast |
|---|---|---|
| WeirdML | 42.6% | 42.9% |
| LMArena Coding | 1379 | 1429 |
| Aider Polyglot | 49.3% | — |
| LMArena WebDev | — | 1159 |
Agentic & Tool Use Not comparable
Grok-3 mini: —, Grok 4 Fast: 29.5 (#86)
| Benchmark | Grok-3 mini | Grok 4 Fast |
|---|---|---|
| τ²-bench Banking | — | 15.7% |
| Cybench | — | 30% |
| LMArena Search | — | 1171 |
Reasoning Grok 4 Fast leads
Grok-3 mini: 13.6 (#334), Grok 4 Fast: 22.2 (#201)
| Benchmark | Grok-3 mini | Grok 4 Fast |
|---|---|---|
| ARC-AGI-2 | 0.4% | 5.3% |
| Kagi LLM Benchmark | 61.3% | 66.1% |
| ARC-AGI-1 | 16.5% | 48.5% |
| LMArena Hard Prompts | 1375 | 1412 |
| Epoch Capabilities Index | 140.35 | 144.2 |
| DTBench | — | 82.7% |
| ForecastBench | — | 60.5 |
Math Grok-3 mini leads
Grok-3 mini: 42.1 (#85), Grok 4 Fast: 38.9 (#123)
| Benchmark | Grok-3 mini | Grok 4 Fast |
|---|---|---|
| LMArena Math | 1386 | 1419 |
| OTIS Mock AIME 2024-2025 | 77.8% | — |
| Omni-MATH | 31.8% | — |
| MATH Level 5 | 90.9% | — |
| FrontierMath (Feb 2025 set) | 5.9% | — |
Knowledge Grok-3 mini leads
Grok-3 mini: 46.4 (#81), Grok 4 Fast: 32.0 (#214)
| Benchmark | Grok-3 mini | Grok 4 Fast |
|---|---|---|
| LMArena Expert | 1395 | 1411 |
| GPQA Diamond | 76.3% | — |
| MMLU-Pro | 79.9% | — |
| Confabulations | 10.8% | — |
| Vectara Hallucination Rate | — | 19.7% |
| GPQA (HELM) | 67.5% | — |
Multilingual Grok 4 Fast leads
Grok-3 mini: 48.1 (#145), Grok 4 Fast: 51.3 (#111)
| Benchmark | Grok-3 mini | Grok 4 Fast |
|---|---|---|
| LMArena Non-English | 1352 | 1396 |
| LMArena Chinese | 1387 | 1457 |
| LMArena French | 1357 | 1431 |
| LMArena German | 1349 | 1383 |
| LMArena Japanese | 1342 | 1352 |
| LMArena Korean | 1335 | 1357 |
| LMArena Russian | 1353 | 1389 |
| LMArena Spanish | 1381 | 1415 |
Instruction Following Grok-3 mini leads
Grok-3 mini: 78.5 (#9), Grok 4 Fast: 73.2 (#121)
| Benchmark | Grok-3 mini | Grok 4 Fast |
|---|---|---|
| LMArena Instruction Following | 1357 | 1387 |
| IFEval | 95.1% | — |
Long Context Grok 4 Fast leads
Grok-3 mini: 41.0 (#147), Grok 4 Fast: 63.2 (#3)
| Benchmark | Grok-3 mini | Grok 4 Fast |
|---|---|---|
| Fiction.LiveBench | 66.7% | 94.4% |
| LMArena Longer Query | 1372 | 1415 |
Writing & Preference Grok 4 Fast leads
Grok-3 mini: 52.5 (#169), Grok 4 Fast: 60.0 (#102)
| Benchmark | Grok-3 mini | Grok 4 Fast |
|---|---|---|
| LMArena Text | 1370 | 1407 |
| LMArena Creative Writing | 1342 | 1387 |
| LMArena Multi-Turn | 1355 | 1414 |
| Short-Story Creative Writing | 73.5% | — |
| WildBench | 65.1% | — |
Frequently asked questions
Is Grok-3 mini better than Grok 4 Fast?
Grok-3 mini is the stronger model overall, scoring 41.2 to 39.4 on the Noometry Index.
Is Grok-3 mini or Grok 4 Fast better for coding?
Grok-3 mini scores higher on coding benchmarks: 40.8 versus 32.5 in the Noometry coding category.
How many benchmarks do Grok-3 mini and Grok 4 Fast share?
23 benchmarks have published results for both models. Grok-3 mini has 35 scored results on Noometry and Grok 4 Fast has 30.