Model comparison
Llama 3-8B vs Yi-34B
Yi-34B is the stronger model overall, scoring 27.4 to 25.3 on the Noometry Index.
Last verified . 21 shared benchmarks.
MetaSummary
- They share 21 benchmarks with published results for both. Llama 3-8B scores higher in 5 categories and Yi-34B in 3 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Yi-34B leads 19.8 to 8.3.
- The biggest single-benchmark swing is GPQA Diamond: 26.1% for Llama 3-8B and 14.7% for Yi-34B.
Side by side
| Llama 3-8B | Yi-34B | |
|---|---|---|
| Provider | Meta | 01.AI |
| Noometry Index | 25.3 | 27.4 |
| Released | 2024-04-18 | 2023-11-02 |
| Weights | Open | Open |
| Context window | 8K | — |
| Max output | 8K | — |
| Input $ / M tokens | $0.14 | — |
| Output $ / M tokens | $0.14 | — |
| Results tracked | 34 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Yi-34B leads
Llama 3-8B: 30.5 (#285), Yi-34B: 31.8 (#269)
| Benchmark | Llama 3-8B | Yi-34B |
|---|---|---|
| LMArena Coding | 1152 | 1112 |
| BigCodeBench Instruct | 31.9% | — |
| BigCodeBench Complete | 36.9% | — |
| HumanEval+ | 56.7% | — |
| MBPP+ | 54.8% | — |
Reasoning Yi-34B leads
Llama 3-8B: 13.8 (#321), Yi-34B: 20.3 (#222)
| Benchmark | Llama 3-8B | Yi-34B |
|---|---|---|
| LMArena Hard Prompts | 1133 | 1104 |
| Epoch Capabilities Index | 116.33 | 117.28 |
| Chess Puzzles | 0% | — |
| DTBench | 43.9% | — |
| Adversarial NLI | 57.3% | — |
| BIG-Bench Hard | — | 71.7% |
| ForecastBench | 58.6 | — |
| WinoGrande | 75.7% | — |
Math Yi-34B leads
Llama 3-8B: 8.3 (#317), Yi-34B: 19.8 (#277)
| Benchmark | Llama 3-8B | Yi-34B |
|---|---|---|
| LMArena Math | 1151 | 1114 |
| MATH Level 5 | 6.1% | 5.1% |
| OTIS Mock AIME 2024-2025 | 1.9% | — |
| GSM8K | — | 76% |
Knowledge Too close to call
Llama 3-8B: 7.8 (#303), Yi-34B: 7.5 (#304)
| Benchmark | Llama 3-8B | Yi-34B |
|---|---|---|
| GPQA Diamond | 26.1% | 14.7% |
| LMArena Expert | 1113 | 1061 |
| MMLU | 68.8% | 76.3% |
| ARC (AI2) Challenge | 82.8% | — |
| OpenBookQA | 82.6% | — |
| TriviaQA | 67.7% | — |
Multilingual Llama 3-8B leads
Llama 3-8B: 31.0 (#256), Yi-34B: 29.9 (#259)
| Benchmark | Llama 3-8B | Yi-34B |
|---|---|---|
| LMArena Non-English | 1098 | 1079 |
| LMArena Chinese | 1076 | 1175 |
| LMArena French | 1158 | 1080 |
| LMArena German | 1104 | 1042 |
| LMArena Japanese | 967 | 993 |
| LMArena Korean | 1003 | 959 |
| LMArena Russian | 1109 | 1050 |
| LMArena Spanish | 1172 | 1070 |
Instruction Following Llama 3-8B leads
Llama 3-8B: 58.7 (#255), Yi-34B: 56.4 (#269)
| Benchmark | Llama 3-8B | Yi-34B |
|---|---|---|
| LMArena Instruction Following | 1127 | 1091 |
Long Context Llama 3-8B leads
Llama 3-8B: 34.2 (#246), Yi-34B: 33.2 (#259)
| Benchmark | Llama 3-8B | Yi-34B |
|---|---|---|
| LMArena Longer Query | 1128 | 1094 |
Writing & Preference Llama 3-8B leads
Llama 3-8B: 37.7 (#251), Yi-34B: 34.3 (#268)
| Benchmark | Llama 3-8B | Yi-34B |
|---|---|---|
| LMArena Text | 1166 | 1129 |
| LMArena Creative Writing | 1150 | 1108 |
| LMArena Multi-Turn | 1152 | 1113 |
Frequently asked questions
Is Llama 3-8B better than Yi-34B?
Yi-34B is the stronger model overall, scoring 27.4 to 25.3 on the Noometry Index.
Is Llama 3-8B or Yi-34B better for coding?
Yi-34B scores higher on coding benchmarks: 31.8 versus 30.5 in the Noometry coding category.
How many benchmarks do Llama 3-8B and Yi-34B share?
21 benchmarks have published results for both models. Llama 3-8B has 34 scored results on Noometry and Yi-34B has 23.