GPT-3.5 Turbo Jun 2023
GPT-3.5 Turbo places in the top three on 3 benchmarks.
OpenAI Released 13 Jun 2023
24
Benchmarks with a score
0
Ranked first, out of five or more models
3
In the top three
OpenAI Jun 2023
GPT-3.5 Turbo
Jun 2023 snapshot Closed weights
113.3
#218 of 271
Epoch Capabilities Index
- Situational Awareness Dataset (SAD) 38.4% #13 /17
- CommonsenseQA 2.0 57% #3 /6
- L-Eval 71.6% #2 /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 | |
|---|---|---|---|---|
| WinoGrande | 81.6% | #13 of 76 | Epoch AI | |
| BoolQ | 87% | #17 of 75 | Epoch AI | |
| BIG-Bench Hard | 61.6% | #14 of 45 | Epoch AI | |
| AlpacaEval | 93.4% | #7 of 19 | Official leaderboard | |
| L-Eval | 71.6% | #2 of 5 | Official leaderboard | |
| MMLU | 68.9% | #60 of 127 | Epoch AI | |
| CommonsenseQA 2.0 | 57% | #3 of 6 | Epoch AI | |
| EQ-Bench v2 | 69.3 | #53 of 85 | Official leaderboard | |
| AlpacaEval 2.0 | 22.7% | #26 of 40 | Official leaderboard | |
| BuzzBench | 39.0 | #17 of 23 | Official leaderboard | |
| QuALITY | 74.7% | #3 of 4 | Official leaderboard | |
| Creative Writing v3 | 42.5 | #116 of 120 | Official leaderboard |
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| GSM8K | 57.8% | #29 of 82 | Epoch AI | |
| SimpleBench | 8.00% | #100 of 100 | Official leaderboard |
Coding
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| CRUXEval | 59% | #4 of 11 | Official leaderboard |
Safety and security
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Anthropic Red Team | 99.6% | #15 of 75 | Official leaderboard | |
| OR-Bench | 38.4% | #11 of 28 | Official leaderboard | |
| SuperCLUE-Safety | 83.8 | #3 of 7 | Official leaderboard | |
| AIR-Bench 2024 | 63.1% | #47 of 82 | Official leaderboard | |
| Situational Awareness Dataset (SAD) | 38.4% | #13 of 17 | Official leaderboard | |
| SimpleSafetyTests | 95.8% | #63 of 75 | Official leaderboard | |
| HELM Safety | 85.3 | #64 of 75 | Official leaderboard |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| HELM Classic | 78.3 | #4 of 17 | Official leaderboard | |
| HELM Lite | 35.8 | #53 of 71 | Official leaderboard |
OpenAI's models over time
OpenAI's models in color, against every other model on the Epoch Capabilities Index, by release date.