Model comparison
GPT-3.5-turbo vs Yi-Lightning
Yi-Lightning is the stronger model overall, scoring 37.1 to 23.2 on the Noometry Index.
Last verified . 17 shared benchmarks.
Summary
- They share 17 benchmarks with published results for both. GPT-3.5-turbo scores higher in 0 categories and Yi-Lightning in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Yi-Lightning leads 36.2 to 6.3.
Side by side
| GPT-3.5-turbo | Yi-Lightning | |
|---|---|---|
| Provider | OpenAI | 01.AI |
| Noometry Index | 23.2 | 37.1 |
| Released | 2023-03-01 | 2024-12-02 |
| Weights | Proprietary | Proprietary |
| Context window | 16K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.50 | — |
| Output $ / M tokens | $1.50 | — |
| Results tracked | 44 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Yi-Lightning leads
GPT-3.5-turbo: 23.9 (#331), Yi-Lightning: 27.4 (#320)
| Benchmark | GPT-3.5-turbo | Yi-Lightning |
|---|---|---|
| LMArena Coding | 1136 | 1312 |
| Aider Polyglot | — | 12.9% |
| WeirdML | 3.5% | — |
| BigCodeBench Instruct | 39.1% | — |
| BigCodeBench Complete | 50.6% | — |
| HumanEval+ | 70.7% | — |
| MBPP+ | 69.7% | — |
Agentic & Tool Use Not comparable
GPT-3.5-turbo: —, Yi-Lightning: —
| Benchmark | GPT-3.5-turbo | Yi-Lightning |
|---|---|---|
| METR Time Horizons | 21.5% | — |
Reasoning Yi-Lightning leads
GPT-3.5-turbo: 13.8 (#332), Yi-Lightning: 25.9 (#139)
| Benchmark | GPT-3.5-turbo | Yi-Lightning |
|---|---|---|
| LMArena Hard Prompts | 1108 | 1302 |
| Chess Puzzles | 0% | — |
| Mystery Game Puzzles | 3% | — |
| DTBench | 48.5% | — |
| LMCA | 9.7% | — |
| Adversarial NLI | 58.1% | — |
| BIG-Bench Hard | 61.6% | — |
| CommonsenseQA 2.0 | 57% | — |
| Epoch Capabilities Index | 118.55 | — |
| ForecastBench | 50.4 | — |
| WinoGrande | 81.6% | — |
Math Yi-Lightning leads
GPT-3.5-turbo: 6.3 (#327), Yi-Lightning: 36.2 (#172)
| Benchmark | GPT-3.5-turbo | Yi-Lightning |
|---|---|---|
| LMArena Math | 1142 | 1300 |
| FrontierMath (Tiers 1-3) | 0% | — |
| OTIS Mock AIME 2024-2025 | 2.2% | — |
| MATH Level 5 | 15.9% | — |
| GSM8K | 57.8% | — |
Knowledge Yi-Lightning leads
GPT-3.5-turbo: 10.0 (#303), Yi-Lightning: 35.4 (#185)
| Benchmark | GPT-3.5-turbo | Yi-Lightning |
|---|---|---|
| LMArena Expert | 1070 | 1286 |
| GPQA Diamond | 28% | — |
| ARC (AI2) Challenge | 87.4% | — |
| BoolQ | 87% | — |
| MMLU | 71.4% | — |
| OpenBookQA | 86% | — |
| TriviaQA | 85.8% | — |
Multilingual Yi-Lightning leads
GPT-3.5-turbo: 31.5 (#258), Yi-Lightning: 42.2 (#196)
| Benchmark | GPT-3.5-turbo | Yi-Lightning |
|---|---|---|
| LMArena Non-English | 1108 | 1269 |
| LMArena Chinese | 1075 | 1320 |
| LMArena French | 1118 | 1305 |
| LMArena German | 1090 | 1267 |
| LMArena Japanese | 1043 | 1228 |
| LMArena Korean | 1019 | 1192 |
| LMArena Russian | 1123 | 1255 |
| LMArena Spanish | 1121 | 1315 |
Instruction Following Yi-Lightning leads
GPT-3.5-turbo: 57.9 (#262), Yi-Lightning: 67.4 (#196)
| Benchmark | GPT-3.5-turbo | Yi-Lightning |
|---|---|---|
| LMArena Instruction Following | 1119 | 1278 |
Long Context Yi-Lightning leads
GPT-3.5-turbo: 34.0 (#254), Yi-Lightning: 39.4 (#181)
| Benchmark | GPT-3.5-turbo | Yi-Lightning |
|---|---|---|
| LMArena Longer Query | 1121 | 1297 |
Writing & Preference Yi-Lightning leads
GPT-3.5-turbo: 25.3 (#305), Yi-Lightning: 50.2 (#184)
| Benchmark | GPT-3.5-turbo | Yi-Lightning |
|---|---|---|
| LMArena Text | 1125 | 1302 |
| LMArena Creative Writing | 1092 | 1280 |
| LMArena Multi-Turn | 1117 | 1311 |
| EQ-Bench Creative Writing | 451 | — |
Frequently asked questions
Is GPT-3.5-turbo better than Yi-Lightning?
Yi-Lightning is the stronger model overall, scoring 37.1 to 23.2 on the Noometry Index.
Is GPT-3.5-turbo or Yi-Lightning better for coding?
Yi-Lightning scores higher on coding benchmarks: 27.4 versus 23.9 in the Noometry coding category.
How many benchmarks do GPT-3.5-turbo and Yi-Lightning share?
17 benchmarks have published results for both models. GPT-3.5-turbo has 44 scored results on Noometry and Yi-Lightning has 18.