GPT-3.5 Turbo (Mar 2023)
GPT-3.5 Turbo (Mar 2023) places in the top three on 2 benchmarks.
10
Benchmarks with a score
0
Ranked first, out of five or more models
2
In the top three
OpenAI Mar 2023
GPT-3.5 Turbo (Mar 2023)
Closed weights Mid-size
No Epoch Capabilities Index score yet
- AIR-Bench 2024 63.5% #46 /82
- AlpacaEval 89.4% #11 /19
- Spider 82.3% #3 /5
Where it ranks
Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.
Knowledge and language
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| AlpacaEval | 89.4% | #11 of 19 | Official leaderboard | |
| EQ-Bench v2 | 70.7 | #51 of 85 | Official leaderboard | |
| AlpacaEval 2.0 | 18.1% | #30 of 40 | Official leaderboard |
Coding
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| HumanEval+ | 66.5% | #21 of 46 | Official leaderboard | |
| Spider | 82.3% | #3 of 5 | Official leaderboard | |
| Aider-Edit | 57.9% | #25 of 37 | Official leaderboard |
Safety and security
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| AIR-Bench 2024 | 63.5% | #46 of 82 | Official leaderboard | |
| OR-Bench | 57.4% | #16 of 28 | Official leaderboard | |
| DecodingTrust | 72.5 | #3 of 5 | Official leaderboard |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| HELM Classic | 76.0 | #5 of 17 | Official leaderboard |