Model comparison
Grok 4.20 (Non-Reasoning) vs Sonar
Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.6 to 38.5 on the Noometry Index. Sonar costs 1.6× 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 . 0 shared benchmarks.
PerplexitySummary
- The widest gap is in reasoning, where Grok 4.20 (Non-Reasoning) leads 52.3 to 21.1.
- Sonar is cheaper at $1 / $1 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 128K.
Side by side
| Grok 4.20 (Non-Reasoning) | Sonar | |
|---|---|---|
| Provider | xAI | Perplexity |
| Noometry Index | 48.6 | 38.5 |
| Released | 2026-02-17 | 2024-01-01 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | 128K |
| Max output | 30K | 4K |
| Input $ / M tokens | $1.25 | $1 |
| Output $ / M tokens | $2.50 | $1 |
| Results tracked | 46 | 7 |
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): 42.1 (#112), Sonar: 35.7 (#221)
| Benchmark | Grok 4.20 (Non-Reasoning) | Sonar |
|---|---|---|
| LMArena WebDev | 1375 | — |
| WeirdML | 52.3% | — |
| LiveBench Coding | — | 35.1% |
| LMArena Coding | 1459 | — |
| ALE-Bench | 1,150 | — |
Agentic & Tool Use Not comparable
Grok 4.20 (Non-Reasoning): 34.4 (#46), Sonar: —
| Benchmark | Grok 4.20 (Non-Reasoning) | Sonar |
|---|---|---|
| Terminal-Bench | 57.3% | — |
| τ²-bench Banking | 18% | — |
| LMArena Search | 1189 | — |
| Vending-Bench 2 | 4,663 | — |
Reasoning Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 52.3 (#32), Sonar: 21.1 (#227)
| Benchmark | Grok 4.20 (Non-Reasoning) | Sonar |
|---|---|---|
| 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% | — |
| LiveBench Reasoning | — | 46.3% |
| LMArena Hard Prompts | 1451 | — |
| DTBench | 90.1% | — |
| LiveBench Data Analysis | — | 37.9% |
| LMCA | 38.7% | — |
| Epoch Capabilities Index | 151.98 | — |
| ForecastBench | 61.4 | — |
| LiveBench | — | 46.9% |
Math Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 48.2 (#65), Sonar: 33.7 (#200)
| Benchmark | Grok 4.20 (Non-Reasoning) | Sonar |
|---|---|---|
| FrontierMath (Tiers 1-3) | 44.9% | — |
| FrontierMath Tier 4 | 17.1% | — |
| OTIS Mock AIME 2024-2025 | 92.2% | — |
| ProofBench | 14% | — |
| LiveBench Math | — | 41.6% |
| LMArena Math | 1455 | — |
Knowledge Not comparable
Grok 4.20 (Non-Reasoning): 52.8 (#60), Sonar: —
| Benchmark | Grok 4.20 (Non-Reasoning) | Sonar |
|---|---|---|
| GPQA Diamond | 89.3% | — |
| SimpleQA Verified | 30.2% | — |
| LMArena Expert | 1439 | — |
Multimodal Not comparable
Grok 4.20 (Non-Reasoning): 33.3 (#98), Sonar: —
| Benchmark | Grok 4.20 (Non-Reasoning) | Sonar |
|---|---|---|
| LMArena Vision | 1263 | — |
| Blueprint-Bench 2 | 0% | — |
| LMArena Document | 1416 | — |
Multilingual Not comparable
Grok 4.20 (Non-Reasoning): 54.5 (#40), Sonar: —
| Benchmark | Grok 4.20 (Non-Reasoning) | Sonar |
|---|---|---|
| LMArena Non-English | 1441 | — |
| LMArena Chinese | 1481 | — |
| LMArena French | 1476 | — |
| LMArena German | 1465 | — |
| LMArena Japanese | 1449 | — |
| LMArena Korean | 1417 | — |
| LMArena Russian | 1458 | — |
| LMArena Spanish | 1443 | — |
Instruction Following Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 74.8 (#83), Sonar: 71.4 (#150)
| Benchmark | Grok 4.20 (Non-Reasoning) | Sonar |
|---|---|---|
| LiveBench Instruction Following | — | 76.2% |
| LMArena Instruction Following | 1420 | — |
Long Context Not comparable
Grok 4.20 (Non-Reasoning): 45.5 (#34), Sonar: —
| Benchmark | Grok 4.20 (Non-Reasoning) | Sonar |
|---|---|---|
| CL-bench | 22.2% | — |
| CL-bench Life | 11.9% | — |
| LMArena Longer Query | 1437 | — |
Writing & Preference Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 65.7 (#44), Sonar: 52.6 (#167)
| Benchmark | Grok 4.20 (Non-Reasoning) | Sonar |
|---|---|---|
| LMArena Text | 1451 | — |
| LMArena Creative Writing | 1438 | — |
| EQ-Bench Creative Writing | 1574 | — |
| LMArena Multi-Turn | 1456 | — |
| LiveBench Language | — | 44.1% |
Frequently asked questions
Is Grok 4.20 (Non-Reasoning) better than Sonar?
Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.6 to 38.5 on the Noometry Index. Sonar costs 1.6× 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 Sonar?
Sonar is cheaper. It lists at $1 per million input tokens and $1 per million output tokens; Grok 4.20 (Non-Reasoning) lists at $1.25 and $2.50.
Is Grok 4.20 (Non-Reasoning) or Sonar better for coding?
Grok 4.20 (Non-Reasoning) scores higher on coding benchmarks: 42.1 versus 35.7 in the Noometry coding category.
Which has the bigger context window?
Grok 4.20 (Non-Reasoning) does, with 1M tokens against 128K.
How many benchmarks do Grok 4.20 (Non-Reasoning) and Sonar share?
0 benchmarks have published results for both models. Grok 4.20 (Non-Reasoning) has 46 scored results on Noometry and Sonar has 7.