Model comparison
GPT-4 vs Yi-34B
GPT-4 is the stronger model overall, scoring 28.9 to 27.4 on the Noometry Index.
Last verified . 23 shared benchmarks.
Summary
- They share 23 benchmarks with published results for both. GPT-4 scores higher in 5 categories and Yi-34B in 3 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GPT-4 leads 18.4 to 7.5.
- The biggest single-benchmark swing is GPQA Diamond: 35.7% for GPT-4 and 14.7% for Yi-34B.
- Yi-34B has downloadable open weights; the other is API-only.
Side by side
| GPT-4 | Yi-34B | |
|---|---|---|
| Provider | OpenAI | 01.AI |
| Noometry Index | 28.9 | 27.4 |
| Released | 2023-03-14 | 2023-11-02 |
| Weights | Proprietary | Open |
| Context window | 8K | — |
| Max output | 8K | — |
| Input $ / M tokens | $30 | — |
| Output $ / M tokens | $60 | — |
| Results tracked | 38 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
GPT-4: 31.2 (#277), Yi-34B: 31.8 (#269)
| Benchmark | GPT-4 | Yi-34B |
|---|---|---|
| LMArena Coding | 1254 | 1112 |
| WeirdML | 12.4% | — |
| BigCodeBench Instruct | 46% | — |
| BigCodeBench Complete | 57.2% | — |
| HumanEval+ | 79.3% | — |
Agentic & Tool Use Not comparable
GPT-4: —, Yi-34B: —
| Benchmark | GPT-4 | Yi-34B |
|---|---|---|
| METR Time Horizons | 36.1% | — |
Reasoning Yi-34B leads
GPT-4: 17.3 (#285), Yi-34B: 20.3 (#222)
| Benchmark | GPT-4 | Yi-34B |
|---|---|---|
| LMArena Hard Prompts | 1241 | 1104 |
| BIG-Bench Hard | 75.1% | 71.7% |
| Epoch Capabilities Index | 125.88 | 117.28 |
| Chess Puzzles | 4% | — |
| Mystery Game Puzzles | 12% | — |
| DTBench | 62.7% | — |
| LMCA | 17.1% | — |
| ForecastBench | 57.8 | — |
| HellaSwag | 95.3% | — |
| WinoGrande | 87.5% | — |
Math Yi-34B leads
GPT-4: 10.1 (#304), Yi-34B: 19.8 (#277)
| Benchmark | GPT-4 | Yi-34B |
|---|---|---|
| LMArena Math | 1269 | 1114 |
| MATH Level 5 | 23% | 5.1% |
| GSM8K | 92% | 76% |
| OTIS Mock AIME 2024-2025 | 1.1% | — |
Knowledge GPT-4 leads
GPT-4: 18.4 (#277), Yi-34B: 7.5 (#304)
| Benchmark | GPT-4 | Yi-34B |
|---|---|---|
| GPQA Diamond | 35.7% | 14.7% |
| LMArena Expert | 1211 | 1061 |
| MMLU | 86.4% | 76.3% |
| TriviaQA | 84.8% | — |
Multilingual GPT-4 leads
GPT-4: 40.8 (#210), Yi-34B: 29.9 (#259)
| Benchmark | GPT-4 | Yi-34B |
|---|---|---|
| LMArena Non-English | 1246 | 1079 |
| LMArena Chinese | 1242 | 1175 |
| LMArena French | 1282 | 1080 |
| LMArena German | 1251 | 1042 |
| LMArena Japanese | 1209 | 993 |
| LMArena Korean | 1184 | 959 |
| LMArena Russian | 1251 | 1050 |
| LMArena Spanish | 1261 | 1070 |
Instruction Following GPT-4 leads
GPT-4: 65.5 (#217), Yi-34B: 56.4 (#269)
| Benchmark | GPT-4 | Yi-34B |
|---|---|---|
| LMArena Instruction Following | 1241 | 1091 |
Long Context GPT-4 leads
GPT-4: 37.7 (#207), Yi-34B: 33.2 (#259)
| Benchmark | GPT-4 | Yi-34B |
|---|---|---|
| LMArena Longer Query | 1244 | 1094 |
Writing & Preference Too close to call
GPT-4: 35.0 (#263), Yi-34B: 34.3 (#268)
| Benchmark | GPT-4 | Yi-34B |
|---|---|---|
| LMArena Text | 1263 | 1129 |
| LMArena Creative Writing | 1244 | 1108 |
| LMArena Multi-Turn | 1257 | 1113 |
| EQ-Bench Creative Writing | 752 | — |
Frequently asked questions
Is GPT-4 better than Yi-34B?
GPT-4 is the stronger model overall, scoring 28.9 to 27.4 on the Noometry Index.
Is GPT-4 or Yi-34B better for coding?
They score almost the same on coding (31.2 vs 31.8); test both on your own repository before choosing.
How many benchmarks do GPT-4 and Yi-34B share?
23 benchmarks have published results for both models. GPT-4 has 38 scored results on Noometry and Yi-34B has 23.