Model comparison
Llama 3.2 90B vs Sonar
Sonar is the stronger model overall, scoring 38.5 to 27.5 on the Noometry Index.
Last verified . 0 shared benchmarks.
Meta
PerplexitySummary
- The widest gap is in math, where Sonar leads 33.7 to 11.1.
- Llama 3.2 90B has downloadable open weights; the other is API-only.
Side by side
| Llama 3.2 90B | Sonar | |
|---|---|---|
| Provider | Meta | Perplexity |
| Noometry Index | 27.5 | 38.5 |
| Released | 2024-09-24 | 2024-01-01 |
| Weights | Open | Proprietary |
| Context window | — | 128K |
| Max output | — | 4K |
| Input $ / M tokens | — | $1 |
| Output $ / M tokens | — | $1 |
| Results tracked | 9 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Llama 3.2 90B: —, Sonar: 35.7 (#221)
| Benchmark | Llama 3.2 90B | Sonar |
|---|---|---|
| LiveBench Coding | — | 35.1% |
Agentic & Tool Use Not comparable
Llama 3.2 90B: 30.0 (#80), Sonar: —
| Benchmark | Llama 3.2 90B | Sonar |
|---|---|---|
| BALROG | 27.3% | — |
Reasoning Too close to call
Llama 3.2 90B: 21.7 (#217), Sonar: 21.1 (#227)
| Benchmark | Llama 3.2 90B | Sonar |
|---|---|---|
| EnigmaEval | 0.4% | — |
| LiveBench Reasoning | — | 46.3% |
| LiveBench Data Analysis | — | 37.9% |
| Epoch Capabilities Index | 125.5 | — |
| LiveBench | — | 46.9% |
Math Sonar leads
Llama 3.2 90B: 11.1 (#308), Sonar: 33.7 (#200)
| Benchmark | Llama 3.2 90B | Sonar |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.6% | — |
| LiveBench Math | — | 41.6% |
| MATH Level 5 | 39.4% | — |
Knowledge Not comparable
Llama 3.2 90B: 21.7 (#274), Sonar: —
| Benchmark | Llama 3.2 90B | Sonar |
|---|---|---|
| GPQA Diamond | 41% | — |
| MMLU | 80.3% | — |
Multimodal Not comparable
Llama 3.2 90B: 25.4 (#124), Sonar: —
| Benchmark | Llama 3.2 90B | Sonar |
|---|---|---|
| LMArena Vision | 1000 | — |
| GeoBench | 52% | — |
Instruction Following Not comparable
Llama 3.2 90B: —, Sonar: 71.4 (#150)
| Benchmark | Llama 3.2 90B | Sonar |
|---|---|---|
| LiveBench Instruction Following | — | 76.2% |
Writing & Preference Not comparable
Llama 3.2 90B: —, Sonar: 52.6 (#167)
| Benchmark | Llama 3.2 90B | Sonar |
|---|---|---|
| LiveBench Language | — | 44.1% |
Frequently asked questions
Is Llama 3.2 90B better than Sonar?
Sonar is the stronger model overall, scoring 38.5 to 27.5 on the Noometry Index.
How many benchmarks do Llama 3.2 90B and Sonar share?
0 benchmarks have published results for both models. Llama 3.2 90B has 9 scored results on Noometry and Sonar has 7.