Model comparison
GPT-3.5-turbo vs Yi-34B
Yi-34B is the stronger model overall, scoring 27.4 to 23.1 on the Noometry Index.
Last verified . 23 shared benchmarks.
Summary
- They share 23 benchmarks with published results for both. GPT-3.5-turbo scores higher in 4 categories and Yi-34B in 4 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Yi-34B leads 19.8 to 6.0.
- The biggest single-benchmark swing is GPQA Diamond: 28% for GPT-3.5-turbo and 14.7% for Yi-34B.
- Yi-34B has downloadable open weights; the other is API-only.
Side by side
| GPT-3.5-turbo | Yi-34B | |
|---|---|---|
| Provider | OpenAI | 01.AI |
| Noometry Index | 23.1 | 27.4 |
| Released | 2023-03-01 | 2023-11-02 |
| Weights | Proprietary | Open |
| Context window | 16K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.50 | — |
| Output $ / M tokens | $1.50 | — |
| Results tracked | 44 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Yi-34B leads
GPT-3.5-turbo: 23.5 (#326), Yi-34B: 31.8 (#269)
| Benchmark | GPT-3.5-turbo | Yi-34B |
|---|---|---|
| LMArena Coding | 1137 | 1112 |
| 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-34B: —
| Benchmark | GPT-3.5-turbo | Yi-34B |
|---|---|---|
| METR Time Horizons | 21.5% | — |
Reasoning Yi-34B leads
GPT-3.5-turbo: 13.3 (#328), Yi-34B: 20.3 (#222)
| Benchmark | GPT-3.5-turbo | Yi-34B |
|---|---|---|
| LMArena Hard Prompts | 1108 | 1104 |
| BIG-Bench Hard | 61.6% | 71.7% |
| Epoch Capabilities Index | 118.48 | 117.28 |
| Chess Puzzles | 0% | — |
| Mystery Game Puzzles | 3% | — |
| DTBench | 48.5% | — |
| LMCA | 9.7% | — |
| Adversarial NLI | 58.1% | — |
| CommonsenseQA 2.0 | 57% | — |
| ForecastBench | 50.4 | — |
| WinoGrande | 81.6% | — |
Math Yi-34B leads
GPT-3.5-turbo: 6.0 (#321), Yi-34B: 19.8 (#277)
| Benchmark | GPT-3.5-turbo | Yi-34B |
|---|---|---|
| LMArena Math | 1142 | 1114 |
| MATH Level 5 | 15.9% | 5.1% |
| GSM8K | 57.8% | 76% |
| FrontierMath (Tiers 1-3) | 0% | — |
| OTIS Mock AIME 2024-2025 | 2.2% | — |
Knowledge GPT-3.5-turbo leads
GPT-3.5-turbo: 10.0 (#298), Yi-34B: 7.5 (#304)
| Benchmark | GPT-3.5-turbo | Yi-34B |
|---|---|---|
| GPQA Diamond | 28% | 14.7% |
| LMArena Expert | 1070 | 1061 |
| MMLU | 71.4% | 76.3% |
| ARC (AI2) Challenge | 87.4% | — |
| BoolQ | 87% | — |
| OpenBookQA | 86% | — |
| TriviaQA | 85.8% | — |
Multilingual GPT-3.5-turbo leads
GPT-3.5-turbo: 31.6 (#253), Yi-34B: 29.9 (#259)
| Benchmark | GPT-3.5-turbo | Yi-34B |
|---|---|---|
| LMArena Non-English | 1108 | 1079 |
| LMArena Chinese | 1075 | 1175 |
| LMArena French | 1117 | 1080 |
| LMArena German | 1090 | 1042 |
| LMArena Japanese | 1043 | 993 |
| LMArena Korean | 1019 | 959 |
| LMArena Russian | 1123 | 1050 |
| LMArena Spanish | 1120 | 1070 |
Instruction Following GPT-3.5-turbo leads
GPT-3.5-turbo: 58.1 (#257), Yi-34B: 56.4 (#269)
| Benchmark | GPT-3.5-turbo | Yi-34B |
|---|---|---|
| LMArena Instruction Following | 1119 | 1091 |
Long Context Too close to call
GPT-3.5-turbo: 34.0 (#249), Yi-34B: 33.2 (#259)
| Benchmark | GPT-3.5-turbo | Yi-34B |
|---|---|---|
| LMArena Longer Query | 1121 | 1094 |
Writing & Preference Yi-34B leads
GPT-3.5-turbo: 25.4 (#300), Yi-34B: 34.3 (#268)
| Benchmark | GPT-3.5-turbo | Yi-34B |
|---|---|---|
| LMArena Text | 1125 | 1129 |
| LMArena Creative Writing | 1092 | 1108 |
| LMArena Multi-Turn | 1117 | 1113 |
| EQ-Bench Creative Writing | 451 | — |
Frequently asked questions
Is GPT-3.5-turbo better than Yi-34B?
Yi-34B is the stronger model overall, scoring 27.4 to 23.1 on the Noometry Index.
Is GPT-3.5-turbo or Yi-34B better for coding?
Yi-34B scores higher on coding benchmarks: 31.8 versus 23.5 in the Noometry coding category.
How many benchmarks do GPT-3.5-turbo and Yi-34B share?
23 benchmarks have published results for both models. GPT-3.5-turbo has 44 scored results on Noometry and Yi-34B has 23.