Model comparison
Llama 3.1-405B vs Yi-34B
Llama 3.1-405B is the stronger model overall, scoring 30.7 to 27.8 on the Noometry Index.
Last verified . 22 shared benchmarks.
MetaSummary
- They share 22 benchmarks with published results for both. Llama 3.1-405B scores higher in 6 categories and Yi-34B in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Llama 3.1-405B leads 30.4 to 7.5.
- The biggest single-benchmark swing is MATH Level 5: 49.8% for Llama 3.1-405B and 5.1% for Yi-34B.
Side by side
| Llama 3.1-405B | Yi-34B | |
|---|---|---|
| Provider | Meta | 01.AI |
| Noometry Index | 30.7 | 27.8 |
| Released | 2024-07-23 | 2023-11-02 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 42 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Llama 3.1-405B: 33.1 (#262), Yi-34B: 32.3 (#274)
| Benchmark | Llama 3.1-405B | Yi-34B |
|---|---|---|
| LMArena Coding | 1291 | 1112 |
| WeirdML | 21.4% | — |
Agentic & Tool Use Not comparable
Llama 3.1-405B: 21.0 (#140), Yi-34B: —
| Benchmark | Llama 3.1-405B | Yi-34B |
|---|---|---|
| TheAgentCompany | 7.4% | — |
| Cybench | 7.5% | — |
Reasoning Yi-34B leads
Llama 3.1-405B: 16.8 (#300), Yi-34B: 21.2 (#226)
| Benchmark | Llama 3.1-405B | Yi-34B |
|---|---|---|
| LMArena Hard Prompts | 1269 | 1104 |
| BIG-Bench Hard | 82.9% | 71.7% |
| Epoch Capabilities Index | 128.75 | 117.39 |
| SimpleBench | 23% | — |
| Kagi LLM Benchmark | 45% | — |
| DTBench | 61.4% | — |
| ForecastBench | 59.9 | — |
| HellaSwag | 89.2% | — |
| PIQA | 85.9% | — |
| WinoGrande | 89.2% | — |
Math Yi-34B leads
Llama 3.1-405B: 18.4 (#290), Yi-34B: 21.6 (#282)
| Benchmark | Llama 3.1-405B | Yi-34B |
|---|---|---|
| LMArena Math | 1281 | 1114 |
| MATH Level 5 | 49.8% | 5.1% |
| OTIS Mock AIME 2024-2025 | 9.7% | — |
| Omni-MATH | 24.9% | — |
| GSM8K | — | 76% |
Knowledge Llama 3.1-405B leads
Llama 3.1-405B: 30.4 (#227), Yi-34B: 7.5 (#309)
| Benchmark | Llama 3.1-405B | Yi-34B |
|---|---|---|
| GPQA Diamond | 50.9% | 14.7% |
| LMArena Expert | 1243 | 1061 |
| MMLU | 84.5% | 76.3% |
| MMLU-Pro | 72.3% | — |
| Confabulations | 17.6% | — |
| GPQA (HELM) | 52.2% | — |
| ARC (AI2) Challenge | 95.3% | — |
| TriviaQA | 82.7% | — |
Multilingual Llama 3.1-405B leads
Llama 3.1-405B: 40.7 (#214), Yi-34B: 29.7 (#264)
| Benchmark | Llama 3.1-405B | Yi-34B |
|---|---|---|
| LMArena Non-English | 1248 | 1079 |
| LMArena Chinese | 1242 | 1176 |
| LMArena French | 1279 | 1081 |
| LMArena German | 1252 | 1042 |
| LMArena Japanese | 1208 | 993 |
| LMArena Korean | 1184 | 959 |
| LMArena Russian | 1265 | 1050 |
| LMArena Spanish | 1260 | 1070 |
Instruction Following Llama 3.1-405B leads
Llama 3.1-405B: 65.9 (#214), Yi-34B: 56.2 (#274)
| Benchmark | Llama 3.1-405B | Yi-34B |
|---|---|---|
| LMArena Instruction Following | 1259 | 1091 |
| IFEval | 81.1% | — |
Long Context Llama 3.1-405B leads
Llama 3.1-405B: 38.4 (#197), Yi-34B: 33.2 (#264)
| Benchmark | Llama 3.1-405B | Yi-34B |
|---|---|---|
| LMArena Longer Query | 1266 | 1094 |
Writing & Preference Llama 3.1-405B leads
Llama 3.1-405B: 38.9 (#251), Yi-34B: 34.1 (#273)
| Benchmark | Llama 3.1-405B | Yi-34B |
|---|---|---|
| LMArena Text | 1284 | 1129 |
| LMArena Creative Writing | 1262 | 1108 |
| LMArena Multi-Turn | 1297 | 1113 |
| EQ-Bench Creative Writing | 870 | — |
| WildBench | 78.3% | — |
Frequently asked questions
Is Llama 3.1-405B better than Yi-34B?
Llama 3.1-405B is the stronger model overall, scoring 30.7 to 27.8 on the Noometry Index.
Is Llama 3.1-405B or Yi-34B better for coding?
They score almost the same on coding (33.1 vs 32.3); test both on your own repository before choosing.
How many benchmarks do Llama 3.1-405B and Yi-34B share?
22 benchmarks have published results for both models. Llama 3.1-405B has 42 scored results on Noometry and Yi-34B has 23.