Model comparison
Grok 3 vs Grok 4 Fast
Grok 3 and Grok 4 Fast score almost the same on the Noometry Index (39.6 vs 39.0), so choose on price, context window or the category you care about most.
Last verified . 24 shared benchmarks.
Summary
- They share 24 benchmarks with published results for both. Grok 3 scores higher in 6 categories and Grok 4 Fast in 3 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in long context, where Grok 4 Fast leads 63.2 to 38.7.
- The biggest single-benchmark swing is ARC-AGI-1: 5.5% for Grok 3 and 48.5% for Grok 4 Fast.
Side by side
| Grok 3 | Grok 4 Fast | |
|---|---|---|
| Provider | xAI | xAI |
| Noometry Index | 39.6 | 39.0 |
| Released | 2025-04-09 | 2025-09-19 |
| Weights | Proprietary | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 40 | 30 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 3 leads
Grok 3: 41.5 (#113), Grok 4 Fast: 32.3 (#264)
| Benchmark | Grok 3 | Grok 4 Fast |
|---|---|---|
| WeirdML | 37.2% | 42.9% |
| LMArena Coding | 1432 | 1429 |
| Aider Polyglot | 53.3% | — |
| LMArena WebDev | — | 1160 |
Agentic & Tool Use Too close to call
Grok 3: 30.2 (#69), Grok 4 Fast: 29.3 (#80)
| Benchmark | Grok 3 | Grok 4 Fast |
|---|---|---|
| τ²-bench Banking | — | 15.7% |
| Cybench | — | 30% |
| BALROG | 29.5% | — |
| LMArena Search | — | 1171 |
Reasoning Grok 4 Fast leads
Grok 3: 13.8 (#322), Grok 4 Fast: 22.5 (#179)
| Benchmark | Grok 3 | Grok 4 Fast |
|---|---|---|
| ARC-AGI-2 | 0% | 5.3% |
| Kagi LLM Benchmark | 61.3% | 66.1% |
| ARC-AGI-1 | 5.5% | 48.5% |
| LMArena Hard Prompts | 1433 | 1413 |
| Epoch Capabilities Index | 138.34 | 144.21 |
| SimpleBench | 36.1% | — |
| DTBench | — | 82.7% |
| ForecastBench | — | 60.5 |
Math Too close to call
Grok 3: 36.2 (#122), Grok 4 Fast: 36.1 (#126)
| Benchmark | Grok 3 | Grok 4 Fast |
|---|---|---|
| LMArena Math | 1390 | 1419 |
| OTIS Mock AIME 2024-2025 | 55.6% | — |
| Omni-MATH | 46.4% | — |
| MATH Level 5 | 88.7% | — |
| FrontierMath (Feb 2025 set) | 3.8% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Grok 3 leads
Grok 3: 46.0 (#76), Grok 4 Fast: 31.5 (#211)
| Benchmark | Grok 3 | Grok 4 Fast |
|---|---|---|
| Vectara Hallucination Rate | 5.8% | 19.7% |
| LMArena Expert | 1420 | 1411 |
| GPQA Diamond | 75.8% | — |
| MMLU-Pro | 78.8% | — |
| Confabulations | 14.2% | — |
| GPQA (HELM) | 65% | — |
Multilingual Grok 3 leads
Grok 3: 52.5 (#81), Grok 4 Fast: 51.5 (#106)
| Benchmark | Grok 3 | Grok 4 Fast |
|---|---|---|
| LMArena Non-English | 1411 | 1397 |
| LMArena Chinese | 1448 | 1458 |
| LMArena French | 1460 | 1433 |
| LMArena German | 1431 | 1383 |
| LMArena Japanese | 1389 | 1358 |
| LMArena Korean | 1374 | 1359 |
| LMArena Russian | 1416 | 1387 |
| LMArena Spanish | 1417 | 1414 |
Instruction Following Grok 3 leads
Grok 3: 75.2 (#69), Grok 4 Fast: 73.4 (#116)
| Benchmark | Grok 3 | Grok 4 Fast |
|---|---|---|
| LMArena Instruction Following | 1409 | 1388 |
| IFEval | 88.4% | — |
Long Context Grok 4 Fast leads
Grok 3: 38.7 (#187), Grok 4 Fast: 63.2 (#3)
| Benchmark | Grok 3 | Grok 4 Fast |
|---|---|---|
| Fiction.LiveBench | 58.3% | 94.4% |
| LMArena Longer Query | 1439 | 1415 |
Writing & Preference Grok 4 Fast leads
Grok 3: 56.0 (#136), Grok 4 Fast: 60.2 (#96)
| Benchmark | Grok 3 | Grok 4 Fast |
|---|---|---|
| LMArena Text | 1426 | 1407 |
| LMArena Creative Writing | 1414 | 1388 |
| LMArena Multi-Turn | 1424 | 1414 |
| Short-Story Creative Writing | 76.4% | — |
| EQ-Bench Creative Writing | 1186 | — |
| WildBench | 84.9% | — |
Frequently asked questions
Is Grok 3 better than Grok 4 Fast?
Grok 3 and Grok 4 Fast score almost the same on the Noometry Index (39.6 vs 39.0), so choose on price, context window or the category you care about most.
Is Grok 3 or Grok 4 Fast better for coding?
Grok 3 scores higher on coding benchmarks: 41.5 versus 32.3 in the Noometry coding category.
How many benchmarks do Grok 3 and Grok 4 Fast share?
24 benchmarks have published results for both models. Grok 3 has 40 scored results on Noometry and Grok 4 Fast has 30.