Model comparison
Grok-3 mini vs Grok 4.20 (Non-Reasoning)
Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.6 to 41.2 on the Noometry Index.
Last verified . 24 shared benchmarks.
Summary
- They share 24 benchmarks with published results for both. Grok-3 mini scores higher in 1 category and Grok 4.20 (Non-Reasoning) in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.20 (Non-Reasoning) leads 52.3 to 13.6.
- The biggest single-benchmark swing is ARC-AGI-1: 16.5% for Grok-3 mini and 89.5% for Grok 4.20 (Non-Reasoning).
Side by side
| Grok-3 mini | Grok 4.20 (Non-Reasoning) | |
|---|---|---|
| Provider | xAI | xAI |
| Noometry Index | 41.2 | 48.6 |
| Released | 2025-04-09 | 2026-02-17 |
| Weights | Proprietary | Proprietary |
| Context window | — | 1M |
| Max output | — | 30K |
| Input $ / M tokens | — | $1.25 |
| Output $ / M tokens | — | $2.50 |
| Results tracked | 35 | 46 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4.20 (Non-Reasoning) leads
Grok-3 mini: 40.8 (#131), Grok 4.20 (Non-Reasoning): 42.1 (#112)
| Benchmark | Grok-3 mini | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| WeirdML | 42.6% | 52.3% |
| LMArena Coding | 1379 | 1459 |
| Aider Polyglot | 49.3% | — |
| LMArena WebDev | — | 1375 |
| ALE-Bench | — | 1,150 |
Agentic & Tool Use Not comparable
Grok-3 mini: —, Grok 4.20 (Non-Reasoning): 34.4 (#46)
| Benchmark | Grok-3 mini | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| Terminal-Bench | — | 57.3% |
| τ²-bench Banking | — | 18% |
| LMArena Search | — | 1189 |
| Vending-Bench 2 | — | 4,663 |
Reasoning Grok 4.20 (Non-Reasoning) leads
Grok-3 mini: 13.6 (#334), Grok 4.20 (Non-Reasoning): 52.3 (#32)
| Benchmark | Grok-3 mini | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| ARC-AGI-2 | 0.4% | 65.1% |
| Kagi LLM Benchmark | 61.3% | 75% |
| ARC-AGI-1 | 16.5% | 89.5% |
| LMArena Hard Prompts | 1375 | 1451 |
| Epoch Capabilities Index | 140.35 | 151.98 |
| NYT Connections (extended) | — | 85.4% |
| Chess Puzzles | — | 24% |
| Thematic Generalization | — | 63.8% |
| DTBench | — | 90.1% |
| LMCA | — | 38.7% |
| ForecastBench | — | 61.4 |
Math Grok 4.20 (Non-Reasoning) leads
Grok-3 mini: 42.1 (#85), Grok 4.20 (Non-Reasoning): 48.2 (#65)
| Benchmark | Grok-3 mini | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 77.8% | 92.2% |
| LMArena Math | 1386 | 1455 |
| FrontierMath (Tiers 1-3) | — | 44.9% |
| FrontierMath Tier 4 | — | 17.1% |
| ProofBench | — | 14% |
| Omni-MATH | 31.8% | — |
| MATH Level 5 | 90.9% | — |
| FrontierMath (Feb 2025 set) | 5.9% | — |
Knowledge Grok 4.20 (Non-Reasoning) leads
Grok-3 mini: 46.4 (#81), Grok 4.20 (Non-Reasoning): 52.8 (#60)
| Benchmark | Grok-3 mini | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| GPQA Diamond | 76.3% | 89.3% |
| LMArena Expert | 1395 | 1439 |
| SimpleQA Verified | — | 30.2% |
| MMLU-Pro | 79.9% | — |
| Confabulations | 10.8% | — |
| GPQA (HELM) | 67.5% | — |
Multimodal Not comparable
Grok-3 mini: —, Grok 4.20 (Non-Reasoning): 33.3 (#98)
| Benchmark | Grok-3 mini | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Vision | — | 1263 |
| Blueprint-Bench 2 | — | 0% |
| LMArena Document | — | 1416 |
Multilingual Grok 4.20 (Non-Reasoning) leads
Grok-3 mini: 48.1 (#145), Grok 4.20 (Non-Reasoning): 54.5 (#40)
| Benchmark | Grok-3 mini | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Non-English | 1352 | 1441 |
| LMArena Chinese | 1387 | 1481 |
| LMArena French | 1357 | 1476 |
| LMArena German | 1349 | 1465 |
| LMArena Japanese | 1342 | 1449 |
| LMArena Korean | 1335 | 1417 |
| LMArena Russian | 1353 | 1458 |
| LMArena Spanish | 1381 | 1443 |
Instruction Following Grok-3 mini leads
Grok-3 mini: 78.5 (#9), Grok 4.20 (Non-Reasoning): 74.8 (#83)
| Benchmark | Grok-3 mini | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Instruction Following | 1357 | 1420 |
| IFEval | 95.1% | — |
Long Context Grok 4.20 (Non-Reasoning) leads
Grok-3 mini: 41.0 (#147), Grok 4.20 (Non-Reasoning): 45.5 (#34)
| Benchmark | Grok-3 mini | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Longer Query | 1372 | 1437 |
| Fiction.LiveBench | 66.7% | — |
| CL-bench | — | 22.2% |
| CL-bench Life | — | 11.9% |
Writing & Preference Grok 4.20 (Non-Reasoning) leads
Grok-3 mini: 52.5 (#169), Grok 4.20 (Non-Reasoning): 65.7 (#44)
| Benchmark | Grok-3 mini | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Text | 1370 | 1451 |
| LMArena Creative Writing | 1342 | 1438 |
| LMArena Multi-Turn | 1355 | 1456 |
| Short-Story Creative Writing | 73.5% | — |
| EQ-Bench Creative Writing | — | 1574 |
| WildBench | 65.1% | — |
Frequently asked questions
Is Grok-3 mini better than Grok 4.20 (Non-Reasoning)?
Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.6 to 41.2 on the Noometry Index.
Is Grok-3 mini or Grok 4.20 (Non-Reasoning) better for coding?
Grok 4.20 (Non-Reasoning) scores higher on coding benchmarks: 42.1 versus 40.8 in the Noometry coding category.
How many benchmarks do Grok-3 mini and Grok 4.20 (Non-Reasoning) share?
24 benchmarks have published results for both models. Grok-3 mini has 35 scored results on Noometry and Grok 4.20 (Non-Reasoning) has 46.