Model comparison
Llama 3.1-405B vs Yi-Lightning
Yi-Lightning is the stronger model overall, scoring 37.1 to 30.7 on the Noometry Index.
Last verified . 17 shared benchmarks.
MetaSummary
- They share 17 benchmarks with published results for both. Llama 3.1-405B scores higher in 1 category and Yi-Lightning in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Yi-Lightning leads 36.2 to 18.4.
- Llama 3.1-405B has downloadable open weights; the other is API-only.
Side by side
| Llama 3.1-405B | Yi-Lightning | |
|---|---|---|
| Provider | Meta | 01.AI |
| Noometry Index | 30.7 | 37.1 |
| Released | 2024-07-23 | 2024-12-02 |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 42 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama 3.1-405B leads
Llama 3.1-405B: 33.1 (#262), Yi-Lightning: 27.4 (#320)
| Benchmark | Llama 3.1-405B | Yi-Lightning |
|---|---|---|
| LMArena Coding | 1291 | 1312 |
| Aider Polyglot | — | 12.9% |
| WeirdML | 21.4% | — |
Agentic & Tool Use Not comparable
Llama 3.1-405B: 21.0 (#140), Yi-Lightning: —
| Benchmark | Llama 3.1-405B | Yi-Lightning |
|---|---|---|
| TheAgentCompany | 7.4% | — |
| Cybench | 7.5% | — |
Reasoning Yi-Lightning leads
Llama 3.1-405B: 16.8 (#300), Yi-Lightning: 25.9 (#139)
| Benchmark | Llama 3.1-405B | Yi-Lightning |
|---|---|---|
| LMArena Hard Prompts | 1269 | 1302 |
| SimpleBench | 23% | — |
| Kagi LLM Benchmark | 45% | — |
| DTBench | 61.4% | — |
| BIG-Bench Hard | 82.9% | — |
| Epoch Capabilities Index | 128.75 | — |
| ForecastBench | 59.9 | — |
| HellaSwag | 89.2% | — |
| PIQA | 85.9% | — |
| WinoGrande | 89.2% | — |
Math Yi-Lightning leads
Llama 3.1-405B: 18.4 (#290), Yi-Lightning: 36.2 (#172)
| Benchmark | Llama 3.1-405B | Yi-Lightning |
|---|---|---|
| LMArena Math | 1281 | 1300 |
| OTIS Mock AIME 2024-2025 | 9.7% | — |
| Omni-MATH | 24.9% | — |
| MATH Level 5 | 49.8% | — |
Knowledge Yi-Lightning leads
Llama 3.1-405B: 30.4 (#227), Yi-Lightning: 35.4 (#185)
| Benchmark | Llama 3.1-405B | Yi-Lightning |
|---|---|---|
| LMArena Expert | 1243 | 1286 |
| GPQA Diamond | 50.9% | — |
| MMLU-Pro | 72.3% | — |
| Confabulations | 17.6% | — |
| GPQA (HELM) | 52.2% | — |
| ARC (AI2) Challenge | 95.3% | — |
| MMLU | 84.5% | — |
| TriviaQA | 82.7% | — |
Multilingual Yi-Lightning leads
Llama 3.1-405B: 40.7 (#214), Yi-Lightning: 42.2 (#196)
| Benchmark | Llama 3.1-405B | Yi-Lightning |
|---|---|---|
| LMArena Non-English | 1248 | 1269 |
| LMArena Chinese | 1242 | 1320 |
| LMArena French | 1279 | 1305 |
| LMArena German | 1252 | 1267 |
| LMArena Japanese | 1208 | 1228 |
| LMArena Korean | 1184 | 1192 |
| LMArena Russian | 1265 | 1255 |
| LMArena Spanish | 1260 | 1315 |
Instruction Following Yi-Lightning leads
Llama 3.1-405B: 65.9 (#214), Yi-Lightning: 67.4 (#196)
| Benchmark | Llama 3.1-405B | Yi-Lightning |
|---|---|---|
| LMArena Instruction Following | 1259 | 1278 |
| IFEval | 81.1% | — |
Long Context Too close to call
Llama 3.1-405B: 38.4 (#197), Yi-Lightning: 39.4 (#181)
| Benchmark | Llama 3.1-405B | Yi-Lightning |
|---|---|---|
| LMArena Longer Query | 1266 | 1297 |
Writing & Preference Yi-Lightning leads
Llama 3.1-405B: 38.9 (#251), Yi-Lightning: 50.2 (#184)
| Benchmark | Llama 3.1-405B | Yi-Lightning |
|---|---|---|
| LMArena Text | 1284 | 1302 |
| LMArena Creative Writing | 1262 | 1280 |
| LMArena Multi-Turn | 1297 | 1311 |
| EQ-Bench Creative Writing | 870 | — |
| WildBench | 78.3% | — |
Frequently asked questions
Is Llama 3.1-405B better than Yi-Lightning?
Yi-Lightning is the stronger model overall, scoring 37.1 to 30.7 on the Noometry Index.
Is Llama 3.1-405B or Yi-Lightning better for coding?
Llama 3.1-405B scores higher on coding benchmarks: 33.1 versus 27.4 in the Noometry coding category.
How many benchmarks do Llama 3.1-405B and Yi-Lightning share?
17 benchmarks have published results for both models. Llama 3.1-405B has 42 scored results on Noometry and Yi-Lightning has 18.