Model comparison
Grok-2 (Dec 2024) vs Sonar
Sonar is the stronger model overall, scoring 38.5 to 33.7 on the Noometry Index.
Last verified . 7 shared benchmarks.
PerplexitySummary
- They share 7 benchmarks with published results for both. Grok-2 (Dec 2024) scores higher in 0 categories and Sonar in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in math, where Sonar leads 33.7 to 20.8.
- The biggest single-benchmark swing is LiveBench Data Analysis: 54.5% for Grok-2 (Dec 2024) and 37.9% for Sonar.
Side by side
| Grok-2 (Dec 2024) | Sonar | |
|---|---|---|
| Provider | xAI | Perplexity |
| Noometry Index | 33.7 | 38.5 |
| Released | 2024-08-13 | 2024-01-01 |
| Weights | Proprietary | Proprietary |
| Context window | — | 128K |
| Max output | — | 4K |
| Input $ / M tokens | — | $1 |
| Output $ / M tokens | — | $1 |
| Results tracked | 34 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Sonar leads
Grok-2 (Dec 2024): 33.3 (#258), Sonar: 35.7 (#221)
| Benchmark | Grok-2 (Dec 2024) | Sonar |
|---|---|---|
| LiveBench Coding | 46.4% | 35.1% |
| WeirdML | 22.2% | — |
| LMArena Coding | 1287 | — |
Reasoning Sonar leads
Grok-2 (Dec 2024): 16.9 (#299), Sonar: 21.1 (#227)
| Benchmark | Grok-2 (Dec 2024) | Sonar |
|---|---|---|
| LiveBench Reasoning | 54.8% | 46.3% |
| LiveBench Data Analysis | 54.5% | 37.9% |
| LiveBench | 54.3% | 46.9% |
| SimpleBench | 22.7% | — |
| LMArena Hard Prompts | 1272 | — |
| DTBench | 65.2% | — |
| Epoch Capabilities Index | 130.48 | — |
Math Sonar leads
Grok-2 (Dec 2024): 20.8 (#284), Sonar: 33.7 (#200)
| Benchmark | Grok-2 (Dec 2024) | Sonar |
|---|---|---|
| LiveBench Math | 54.9% | 41.6% |
| OTIS Mock AIME 2024-2025 | 11.5% | — |
| LMArena Math | 1283 | — |
| MATH Level 5 | 63.5% | — |
| FrontierMath (Feb 2025 set) | 0.7% | — |
Knowledge Not comparable
Grok-2 (Dec 2024): 29.8 (#233), Sonar: —
| Benchmark | Grok-2 (Dec 2024) | Sonar |
|---|---|---|
| GPQA Diamond | 53.8% | — |
| Confabulations | 20.1% | — |
| LMArena Expert | 1254 | — |
Multilingual Not comparable
Grok-2 (Dec 2024): 43.1 (#188), Sonar: —
| Benchmark | Grok-2 (Dec 2024) | Sonar |
|---|---|---|
| LMArena Non-English | 1282 | — |
| LMArena Chinese | 1289 | — |
| LMArena French | 1318 | — |
| LMArena German | 1287 | — |
| LMArena Japanese | 1244 | — |
| LMArena Korean | 1237 | — |
| LMArena Russian | 1286 | — |
| LMArena Spanish | 1281 | — |
Instruction Following Sonar leads
Grok-2 (Dec 2024): 66.9 (#202), Sonar: 71.4 (#150)
| Benchmark | Grok-2 (Dec 2024) | Sonar |
|---|---|---|
| LiveBench Instruction Following | 69.6% | 76.2% |
| LMArena Instruction Following | 1270 | — |
Long Context Not comparable
Grok-2 (Dec 2024): 38.8 (#190), Sonar: —
| Benchmark | Grok-2 (Dec 2024) | Sonar |
|---|---|---|
| LMArena Longer Query | 1276 | — |
Writing & Preference Sonar leads
Grok-2 (Dec 2024): 48.6 (#198), Sonar: 52.6 (#167)
| Benchmark | Grok-2 (Dec 2024) | Sonar |
|---|---|---|
| LiveBench Language | 45.6% | 44.1% |
| LMArena Text | 1305 | — |
| LMArena Creative Writing | 1284 | — |
| Short-Story Creative Writing | 63.6% | — |
| LMArena Multi-Turn | 1290 | — |
Frequently asked questions
Is Grok-2 (Dec 2024) better than Sonar?
Sonar is the stronger model overall, scoring 38.5 to 33.7 on the Noometry Index.
Is Grok-2 (Dec 2024) or Sonar better for coding?
Sonar scores higher on coding benchmarks: 35.7 versus 33.3 in the Noometry coding category.
How many benchmarks do Grok-2 (Dec 2024) and Sonar share?
7 benchmarks have published results for both models. Grok-2 (Dec 2024) has 34 scored results on Noometry and Sonar has 7.