Model comparison
Llama2 70b Steerlm Chat vs Sonar
Sonar is the stronger model overall, scoring 38.5 to 31.8 on the Noometry Index.
Last verified . 0 shared benchmarks.
NVIDIA
PerplexitySummary
- The widest gap is in writing & preference, where Sonar leads 52.6 to 31.6.
- Llama2 70b Steerlm Chat has downloadable open weights; the other is API-only.
Side by side
| Llama2 70b Steerlm Chat | Sonar | |
|---|---|---|
| Provider | NVIDIA | Perplexity |
| Noometry Index | 31.8 | 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 | 9 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Sonar leads
Llama2 70b Steerlm Chat: 29.9 (#300), Sonar: 35.7 (#221)
| Benchmark | Llama2 70b Steerlm Chat | Sonar |
|---|---|---|
| LiveBench Coding | — | 35.1% |
| LMArena Coding | 1025 | — |
Reasoning Sonar leads
Llama2 70b Steerlm Chat: 20.0 (#246), Sonar: 21.1 (#227)
| Benchmark | Llama2 70b Steerlm Chat | Sonar |
|---|---|---|
| LiveBench Reasoning | — | 46.3% |
| LMArena Hard Prompts | 1047 | — |
| LiveBench Data Analysis | — | 37.9% |
| LiveBench | — | 46.9% |
Math Sonar leads
Llama2 70b Steerlm Chat: 31.3 (#226), Sonar: 33.7 (#200)
| Benchmark | Llama2 70b Steerlm Chat | Sonar |
|---|---|---|
| LiveBench Math | — | 41.6% |
| LMArena Math | 1072 | — |
Multilingual Not comparable
Llama2 70b Steerlm Chat: 28.8 (#270), Sonar: —
| Benchmark | Llama2 70b Steerlm Chat | Sonar |
|---|---|---|
| LMArena Non-English | 1063 | — |
Instruction Following Sonar leads
Llama2 70b Steerlm Chat: 54.2 (#279), Sonar: 71.4 (#150)
| Benchmark | Llama2 70b Steerlm Chat | Sonar |
|---|---|---|
| LiveBench Instruction Following | — | 76.2% |
| LMArena Instruction Following | 1060 | — |
Long Context Not comparable
Llama2 70b Steerlm Chat: 30.4 (#288), Sonar: —
| Benchmark | Llama2 70b Steerlm Chat | Sonar |
|---|---|---|
| LMArena Longer Query | 998 | — |
Writing & Preference Sonar leads
Llama2 70b Steerlm Chat: 31.6 (#283), Sonar: 52.6 (#167)
| Benchmark | Llama2 70b Steerlm Chat | Sonar |
|---|---|---|
| LMArena Text | 1098 | — |
| LMArena Creative Writing | 1091 | — |
| LMArena Multi-Turn | 1058 | — |
| LiveBench Language | — | 44.1% |
Frequently asked questions
Is Llama2 70b Steerlm Chat better than Sonar?
Sonar is the stronger model overall, scoring 38.5 to 31.8 on the Noometry Index.
Is Llama2 70b Steerlm Chat or Sonar better for coding?
Sonar scores higher on coding benchmarks: 35.7 versus 29.9 in the Noometry coding category.
How many benchmarks do Llama2 70b Steerlm Chat and Sonar share?
0 benchmarks have published results for both models. Llama2 70b Steerlm Chat has 9 scored results on Noometry and Sonar has 7.