Model comparison
Codellama 70b Instruct vs Sonar
Sonar is the stronger model overall, scoring 38.5 to 33.7 on the Noometry Index.
Last verified . 0 shared benchmarks.
Meta
PerplexitySummary
- The widest gap is in instruction following, where Sonar leads 71.4 to 51.9.
- Codellama 70b Instruct has downloadable open weights; the other is API-only.
Side by side
| Codellama 70b Instruct | Sonar | |
|---|---|---|
| Provider | Meta | Perplexity |
| Noometry Index | 33.7 | 38.5 |
| Released | — | 2024-01-01 |
| Weights | Open | Proprietary |
| Context window | — | 128K |
| Max output | — | 4K |
| Input $ / M tokens | — | $1 |
| Output $ / M tokens | — | $1 |
| Results tracked | 7 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Codellama 70b Instruct leads
Codellama 70b Instruct: 37.6 (#193), Sonar: 35.7 (#221)
| Benchmark | Codellama 70b Instruct | Sonar |
|---|---|---|
| BigCodeBench Instruct | 40.7% | — |
| LiveBench Coding | — | 35.1% |
| BigCodeBench Complete | 49.6% | — |
| HumanEval+ | 65.9% | — |
Reasoning Sonar leads
Codellama 70b Instruct: 20.1 (#242), Sonar: 21.1 (#227)
| Benchmark | Codellama 70b Instruct | Sonar |
|---|---|---|
| LiveBench Reasoning | — | 46.3% |
| LMArena Hard Prompts | 1052 | — |
| LiveBench Data Analysis | — | 37.9% |
| LiveBench | — | 46.9% |
Math Not comparable
Codellama 70b Instruct: —, Sonar: 33.7 (#200)
| Benchmark | Codellama 70b Instruct | Sonar |
|---|---|---|
| LiveBench Math | — | 41.6% |
Multilingual Not comparable
Codellama 70b Instruct: 24.8 (#288), Sonar: —
| Benchmark | Codellama 70b Instruct | Sonar |
|---|---|---|
| LMArena Non-English | 992 | — |
Instruction Following Sonar leads
Codellama 70b Instruct: 51.9 (#293), Sonar: 71.4 (#150)
| Benchmark | Codellama 70b Instruct | Sonar |
|---|---|---|
| LiveBench Instruction Following | — | 76.2% |
| LMArena Instruction Following | 1024 | — |
Writing & Preference Sonar leads
Codellama 70b Instruct: 33.4 (#277), Sonar: 52.6 (#167)
| Benchmark | Codellama 70b Instruct | Sonar |
|---|---|---|
| LMArena Text | 1057 | — |
| LiveBench Language | — | 44.1% |
Frequently asked questions
Is Codellama 70b Instruct better than Sonar?
Sonar is the stronger model overall, scoring 38.5 to 33.7 on the Noometry Index.
Is Codellama 70b Instruct or Sonar better for coding?
Codellama 70b Instruct scores higher on coding benchmarks: 37.6 versus 35.7 in the Noometry coding category.
How many benchmarks do Codellama 70b Instruct and Sonar share?
0 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and Sonar has 7.