Model comparison
Grok 4.20 (Non-Reasoning) vs Llama 3.2 3B
Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.5 to 28.4 on the Noometry Index. Llama 3.2 3B costs 13× less per token, which makes it the better buy when Grok 4.20 (Non-Reasoning)'s lead doesn't matter for your workload.
Last verified . 14 shared benchmarks.
MetaSummary
- They share 14 benchmarks with published results for both. Grok 4.20 (Non-Reasoning) scores higher in 9 categories and Llama 3.2 3B in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Grok 4.20 (Non-Reasoning) leads 65.9 to 24.9.
- Llama 3.2 3B is cheaper at $0.05 / $0.33 per million input/output tokens, against $1.25 / $2.50 for Grok 4.20 (Non-Reasoning).
- Grok 4.20 (Non-Reasoning) accepts more context: 1M tokens versus 131K.
- Llama 3.2 3B has downloadable open weights; the other is API-only.
Side by side
| Grok 4.20 (Non-Reasoning) | Llama 3.2 3B | |
|---|---|---|
| Provider | xAI | Meta |
| Noometry Index | 48.5 | 28.4 |
| Released | 2026-02-17 | 2024-09-24 |
| Weights | Proprietary | Open |
| Context window | 1M | 131K |
| Max output | 30K | 118K |
| Input $ / M tokens | $1.25 | $0.05 |
| Output $ / M tokens | $2.50 | $0.33 |
| Results tracked | 46 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 41.8 (#104), Llama 3.2 3B: 27.1 (#314)
| Benchmark | Grok 4.20 (Non-Reasoning) | Llama 3.2 3B |
|---|---|---|
| LMArena Coding | 1458 | 1098 |
| LMArena WebDev | 1374 | — |
| WeirdML | 52.3% | — |
| BigCodeBench Instruct | — | 23.4% |
| BigCodeBench Complete | — | 28.3% |
| ALE-Bench | 1,150 | — |
Agentic & Tool Use Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 34.3 (#43), Llama 3.2 3B: 19.9 (#135)
| Benchmark | Grok 4.20 (Non-Reasoning) | Llama 3.2 3B |
|---|---|---|
| Terminal-Bench | 57.3% | — |
| Berkeley Function Calling Leaderboard | — | 21.9% |
| τ²-bench Banking | 18% | — |
| BALROG | — | 10.1% |
| LMArena Search | 1189 | — |
| Vending-Bench 2 | 4,663 | — |
Reasoning Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 52.2 (#30), Llama 3.2 3B: 20.1 (#225)
| Benchmark | Grok 4.20 (Non-Reasoning) | Llama 3.2 3B |
|---|---|---|
| LMArena Hard Prompts | 1451 | 1095 |
| ARC-AGI-2 | 65.1% | — |
| Kagi LLM Benchmark | 75% | — |
| NYT Connections (extended) | 85.4% | — |
| ARC-AGI-1 | 89.5% | — |
| Chess Puzzles | 24% | — |
| Thematic Generalization | 63.8% | — |
| DTBench | 90.1% | — |
| LMCA | 38.7% | — |
| Epoch Capabilities Index | 152.01 | — |
| ForecastBench | 61.4 | — |
Math Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 48.0 (#54), Llama 3.2 3B: 29.9 (#213)
| Benchmark | Grok 4.20 (Non-Reasoning) | Llama 3.2 3B |
|---|---|---|
| LMArena Math | 1455 | 1126 |
| FrontierMath (Tiers 1-3) | 44.9% | — |
| FrontierMath Tier 4 | 17.1% | — |
| OTIS Mock AIME 2024-2025 | 92.2% | — |
| ProofBench | 14% | — |
Knowledge Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 52.8 (#54), Llama 3.2 3B: 29.1 (#232)
| Benchmark | Grok 4.20 (Non-Reasoning) | Llama 3.2 3B |
|---|---|---|
| LMArena Expert | 1440 | 1090 |
| GPQA Diamond | 89.3% | — |
| SimpleQA Verified | 30.2% | — |
Multimodal Not comparable
Grok 4.20 (Non-Reasoning): 33.2 (#88), Llama 3.2 3B: —
| Benchmark | Grok 4.20 (Non-Reasoning) | Llama 3.2 3B |
|---|---|---|
| LMArena Vision | 1263 | — |
| Blueprint-Bench 2 | 0% | — |
| LMArena Document | 1416 | — |
Multilingual Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 54.7 (#38), Llama 3.2 3B: 26.4 (#276)
| Benchmark | Grok 4.20 (Non-Reasoning) | Llama 3.2 3B |
|---|---|---|
| LMArena Non-English | 1440 | 1019 |
| LMArena Chinese | 1481 | 1017 |
| LMArena German | 1463 | 1056 |
| LMArena Russian | 1457 | 949 |
| LMArena French | 1477 | — |
| LMArena Japanese | 1450 | — |
| LMArena Korean | 1417 | — |
| LMArena Spanish | 1442 | — |
Instruction Following Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 75.0 (#79), Llama 3.2 3B: 56.3 (#270)
| Benchmark | Grok 4.20 (Non-Reasoning) | Llama 3.2 3B |
|---|---|---|
| LMArena Instruction Following | 1420 | 1089 |
Long Context Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 45.4 (#33), Llama 3.2 3B: 33.4 (#256)
| Benchmark | Grok 4.20 (Non-Reasoning) | Llama 3.2 3B |
|---|---|---|
| LMArena Longer Query | 1436 | 1101 |
| CL-bench | 22.2% | — |
| CL-bench Life | 11.9% | — |
Writing & Preference Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 65.9 (#42), Llama 3.2 3B: 24.9 (#302)
| Benchmark | Grok 4.20 (Non-Reasoning) | Llama 3.2 3B |
|---|---|---|
| LMArena Text | 1451 | 1110 |
| LMArena Creative Writing | 1439 | 1094 |
| EQ-Bench Creative Writing | 1574 | 595 |
| LMArena Multi-Turn | 1456 | 1105 |
Frequently asked questions
Is Grok 4.20 (Non-Reasoning) better than Llama 3.2 3B?
Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.5 to 28.4 on the Noometry Index. Llama 3.2 3B costs 13× less per token, which makes it the better buy when Grok 4.20 (Non-Reasoning)'s lead doesn't matter for your workload.
Which is cheaper, Grok 4.20 (Non-Reasoning) or Llama 3.2 3B?
Llama 3.2 3B is cheaper. It lists at $0.05 per million input tokens and $0.33 per million output tokens; Grok 4.20 (Non-Reasoning) lists at $1.25 and $2.50.
Is Grok 4.20 (Non-Reasoning) or Llama 3.2 3B better for coding?
Grok 4.20 (Non-Reasoning) scores higher on coding benchmarks: 41.8 versus 27.1 in the Noometry coding category.
Which has the bigger context window?
Grok 4.20 (Non-Reasoning) does, with 1M tokens against 131K.
How many benchmarks do Grok 4.20 (Non-Reasoning) and Llama 3.2 3B share?
14 benchmarks have published results for both models. Grok 4.20 (Non-Reasoning) has 46 scored results on Noometry and Llama 3.2 3B has 18.