Model comparison
Grok-2 (Dec 2024) vs Grok 4.20 (Non-Reasoning)
Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.5 to 33.4 on the Noometry Index.
Last verified . 22 shared benchmarks.
Summary
- They share 22 benchmarks with published results for both. Grok-2 (Dec 2024) scores higher in 0 categories and Grok 4.20 (Non-Reasoning) in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.20 (Non-Reasoning) leads 52.2 to 16.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 11.5% for Grok-2 (Dec 2024) and 92.2% for Grok 4.20 (Non-Reasoning).
Side by side
| Grok-2 (Dec 2024) | Grok 4.20 (Non-Reasoning) | |
|---|---|---|
| Provider | xAI | xAI |
| Noometry Index | 33.4 | 48.5 |
| Released | 2024-08-13 | 2026-02-17 |
| Weights | Proprietary | Proprietary |
| Context window | — | 1M |
| Max output | — | 30K |
| Input $ / M tokens | — | $1.25 |
| Output $ / M tokens | — | $2.50 |
| Results tracked | 34 | 46 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4.20 (Non-Reasoning) leads
Grok-2 (Dec 2024): 32.9 (#254), Grok 4.20 (Non-Reasoning): 41.8 (#104)
| Benchmark | Grok-2 (Dec 2024) | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| WeirdML | 22.2% | 52.3% |
| LMArena Coding | 1288 | 1458 |
| LMArena WebDev | — | 1374 |
| LiveBench Coding | 46.4% | — |
| ALE-Bench | — | 1,150 |
Agentic & Tool Use Not comparable
Grok-2 (Dec 2024): —, Grok 4.20 (Non-Reasoning): 34.3 (#43)
| Benchmark | Grok-2 (Dec 2024) | 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-2 (Dec 2024): 16.4 (#294), Grok 4.20 (Non-Reasoning): 52.2 (#30)
| Benchmark | Grok-2 (Dec 2024) | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Hard Prompts | 1272 | 1451 |
| DTBench | 65.2% | 90.1% |
| Epoch Capabilities Index | 130.48 | 152.01 |
| ARC-AGI-2 | — | 65.1% |
| SimpleBench | 22.7% | — |
| Kagi LLM Benchmark | — | 75% |
| NYT Connections (extended) | — | 85.4% |
| ARC-AGI-1 | — | 89.5% |
| Chess Puzzles | — | 24% |
| Thematic Generalization | — | 63.8% |
| LiveBench Reasoning | 54.8% | — |
| LiveBench Data Analysis | 54.5% | — |
| LMCA | — | 38.7% |
| ForecastBench | — | 61.4 |
| LiveBench | 54.3% | — |
Math Grok 4.20 (Non-Reasoning) leads
Grok-2 (Dec 2024): 19.6 (#278), Grok 4.20 (Non-Reasoning): 48.0 (#54)
| Benchmark | Grok-2 (Dec 2024) | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 11.5% | 92.2% |
| LMArena Math | 1283 | 1455 |
| FrontierMath (Tiers 1-3) | — | 44.9% |
| FrontierMath Tier 4 | — | 17.1% |
| ProofBench | — | 14% |
| LiveBench Math | 54.9% | — |
| MATH Level 5 | 63.5% | — |
| FrontierMath (Feb 2025 set) | 0.7% | — |
Knowledge Grok 4.20 (Non-Reasoning) leads
Grok-2 (Dec 2024): 29.8 (#225), Grok 4.20 (Non-Reasoning): 52.8 (#54)
| Benchmark | Grok-2 (Dec 2024) | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| GPQA Diamond | 53.8% | 89.3% |
| LMArena Expert | 1254 | 1440 |
| SimpleQA Verified | — | 30.2% |
| Confabulations | 20.1% | — |
Multimodal Not comparable
Grok-2 (Dec 2024): —, Grok 4.20 (Non-Reasoning): 33.2 (#88)
| Benchmark | Grok-2 (Dec 2024) | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Vision | — | 1263 |
| Blueprint-Bench 2 | — | 0% |
| LMArena Document | — | 1416 |
Multilingual Grok 4.20 (Non-Reasoning) leads
Grok-2 (Dec 2024): 43.3 (#183), Grok 4.20 (Non-Reasoning): 54.7 (#38)
| Benchmark | Grok-2 (Dec 2024) | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Non-English | 1282 | 1440 |
| LMArena Chinese | 1289 | 1481 |
| LMArena French | 1317 | 1477 |
| LMArena German | 1287 | 1463 |
| LMArena Japanese | 1244 | 1450 |
| LMArena Korean | 1237 | 1417 |
| LMArena Russian | 1286 | 1457 |
| LMArena Spanish | 1281 | 1442 |
Instruction Following Grok 4.20 (Non-Reasoning) leads
Grok-2 (Dec 2024): 67.1 (#197), Grok 4.20 (Non-Reasoning): 75.0 (#79)
| Benchmark | Grok-2 (Dec 2024) | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Instruction Following | 1270 | 1420 |
| LiveBench Instruction Following | 69.6% | — |
Long Context Grok 4.20 (Non-Reasoning) leads
Grok-2 (Dec 2024): 38.7 (#186), Grok 4.20 (Non-Reasoning): 45.4 (#33)
| Benchmark | Grok-2 (Dec 2024) | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Longer Query | 1276 | 1436 |
| CL-bench | — | 22.2% |
| CL-bench Life | — | 11.9% |
Writing & Preference Grok 4.20 (Non-Reasoning) leads
Grok-2 (Dec 2024): 48.8 (#192), Grok 4.20 (Non-Reasoning): 65.9 (#42)
| Benchmark | Grok-2 (Dec 2024) | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Text | 1305 | 1451 |
| LMArena Creative Writing | 1284 | 1439 |
| LMArena Multi-Turn | 1290 | 1456 |
| Short-Story Creative Writing | 63.6% | — |
| EQ-Bench Creative Writing | — | 1574 |
| LiveBench Language | 45.6% | — |
Frequently asked questions
Is Grok-2 (Dec 2024) better than Grok 4.20 (Non-Reasoning)?
Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.5 to 33.4 on the Noometry Index.
Is Grok-2 (Dec 2024) or Grok 4.20 (Non-Reasoning) better for coding?
Grok 4.20 (Non-Reasoning) scores higher on coding benchmarks: 41.8 versus 32.9 in the Noometry coding category.
How many benchmarks do Grok-2 (Dec 2024) and Grok 4.20 (Non-Reasoning) share?
22 benchmarks have published results for both models. Grok-2 (Dec 2024) has 34 scored results on Noometry and Grok 4.20 (Non-Reasoning) has 46.