Model comparison
GPT-3.5-turbo vs Sonar
Sonar is the stronger model overall, scoring 37.8 to 23.1 on the Noometry Index.
Last verified . 0 shared benchmarks.
PerplexitySummary
- The widest gap is in writing & preference, where Sonar leads 52.6 to 25.4.
- GPT-3.5-turbo is cheaper at $0.50 / $1.50 per million input/output tokens, against $1 / $1 for Sonar.
- Sonar accepts more context: 128K tokens versus 16K.
Side by side
| GPT-3.5-turbo | Sonar | |
|---|---|---|
| Provider | OpenAI | Perplexity |
| Noometry Index | 23.1 | 37.8 |
| Released | 2023-03-01 | 2024-01-01 |
| Weights | Proprietary | Proprietary |
| Context window | 16K | 128K |
| Max output | 4K | 4K |
| Input $ / M tokens | $0.50 | $1 |
| Output $ / M tokens | $1.50 | $1 |
| Results tracked | 44 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Sonar leads
GPT-3.5-turbo: 23.5 (#326), Sonar: 35.1 (#217)
| Benchmark | GPT-3.5-turbo | Sonar |
|---|---|---|
| WeirdML | 3.5% | — |
| BigCodeBench Instruct | 39.1% | — |
| LiveBench Coding | — | 35.1% |
| LMArena Coding | 1137 | — |
| BigCodeBench Complete | 50.6% | — |
| HumanEval+ | 70.7% | — |
| MBPP+ | 69.7% | — |
Agentic & Tool Use Not comparable
GPT-3.5-turbo: —, Sonar: —
| Benchmark | GPT-3.5-turbo | Sonar |
|---|---|---|
| METR Time Horizons | 21.5% | — |
Reasoning Sonar leads
GPT-3.5-turbo: 13.3 (#328), Sonar: 20.3 (#221)
| Benchmark | GPT-3.5-turbo | Sonar |
|---|---|---|
| Chess Puzzles | 0% | — |
| LiveBench Reasoning | — | 46.3% |
| LMArena Hard Prompts | 1108 | — |
| Mystery Game Puzzles | 3% | — |
| DTBench | 48.5% | — |
| LiveBench Data Analysis | — | 37.9% |
| LMCA | 9.7% | — |
| Adversarial NLI | 58.1% | — |
| BIG-Bench Hard | 61.6% | — |
| CommonsenseQA 2.0 | 57% | — |
| Epoch Capabilities Index | 118.48 | — |
| ForecastBench | 50.4 | — |
| LiveBench | — | 46.9% |
| WinoGrande | 81.6% | — |
Math Sonar leads
GPT-3.5-turbo: 6.0 (#321), Sonar: 31.3 (#197)
| Benchmark | GPT-3.5-turbo | Sonar |
|---|---|---|
| FrontierMath (Tiers 1-3) | 0% | — |
| OTIS Mock AIME 2024-2025 | 2.2% | — |
| LiveBench Math | — | 41.6% |
| LMArena Math | 1142 | — |
| MATH Level 5 | 15.9% | — |
| GSM8K | 57.8% | — |
Knowledge Not comparable
GPT-3.5-turbo: 10.0 (#298), Sonar: —
| Benchmark | GPT-3.5-turbo | Sonar |
|---|---|---|
| GPQA Diamond | 28% | — |
| LMArena Expert | 1070 | — |
| ARC (AI2) Challenge | 87.4% | — |
| BoolQ | 87% | — |
| MMLU | 71.4% | — |
| OpenBookQA | 86% | — |
| TriviaQA | 85.8% | — |
Multilingual Not comparable
GPT-3.5-turbo: 31.6 (#253), Sonar: —
| Benchmark | GPT-3.5-turbo | Sonar |
|---|---|---|
| LMArena Non-English | 1108 | — |
| LMArena Chinese | 1075 | — |
| LMArena French | 1117 | — |
| LMArena German | 1090 | — |
| LMArena Japanese | 1043 | — |
| LMArena Korean | 1019 | — |
| LMArena Russian | 1123 | — |
| LMArena Spanish | 1120 | — |
Instruction Following Sonar leads
GPT-3.5-turbo: 58.1 (#257), Sonar: 71.5 (#146)
| Benchmark | GPT-3.5-turbo | Sonar |
|---|---|---|
| LiveBench Instruction Following | — | 76.2% |
| LMArena Instruction Following | 1119 | — |
Long Context Not comparable
GPT-3.5-turbo: 34.0 (#249), Sonar: —
| Benchmark | GPT-3.5-turbo | Sonar |
|---|---|---|
| LMArena Longer Query | 1121 | — |
Writing & Preference Sonar leads
GPT-3.5-turbo: 25.4 (#300), Sonar: 52.6 (#166)
| Benchmark | GPT-3.5-turbo | Sonar |
|---|---|---|
| LMArena Text | 1125 | — |
| LMArena Creative Writing | 1092 | — |
| EQ-Bench Creative Writing | 451 | — |
| LMArena Multi-Turn | 1117 | — |
| LiveBench Language | — | 44.1% |
Frequently asked questions
Is GPT-3.5-turbo better than Sonar?
Sonar is the stronger model overall, scoring 37.8 to 23.1 on the Noometry Index.
Which is cheaper, GPT-3.5-turbo or Sonar?
GPT-3.5-turbo is cheaper. It lists at $0.50 per million input tokens and $1.50 per million output tokens; Sonar lists at $1 and $1.
Is GPT-3.5-turbo or Sonar better for coding?
Sonar scores higher on coding benchmarks: 35.1 versus 23.5 in the Noometry coding category.
Which has the bigger context window?
Sonar does, with 128K tokens against 16K.
How many benchmarks do GPT-3.5-turbo and Sonar share?
0 benchmarks have published results for both models. GPT-3.5-turbo has 44 scored results on Noometry and Sonar has 7.