Model comparison
Llama 3-8B vs Yi-1.5-34B
Yi-1.5-34B is the stronger model overall, scoring 30.6 to 25.5 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 1 category and Yi-1.5-34B in 7 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in math, where Yi-1.5-34B leads 27.5 to 8.8.
- The biggest single-benchmark swing is MATH Level 5: 6.1% for Llama 3-8B and 25.5% for Yi-1.5-34B.
Side by side
| Llama 3-8B | Yi-1.5-34B | |
|---|---|---|
| Provider | Meta | 01.AI |
| Noometry Index | 25.5 | 30.6 |
| Released | 2024-04-18 | 2024-05-13 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 34 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Yi-1.5-34B leads
Llama 3-8B: 31.0 (#289), Yi-1.5-34B: 32.4 (#272)
| Benchmark | Llama 3-8B | Yi-1.5-34B |
|---|---|---|
| BigCodeBench Instruct | 31.9% | 33.9% |
| LMArena Coding | 1152 | 1169 |
| BigCodeBench Complete | 36.9% | 43.8% |
| HumanEval+ | 56.7% | — |
| MBPP+ | 54.8% | — |
Reasoning Yi-1.5-34B leads
Llama 3-8B: 14.3 (#326), Yi-1.5-34B: 22.5 (#191)
| Benchmark | Llama 3-8B | Yi-1.5-34B |
|---|---|---|
| LMArena Hard Prompts | 1133 | 1160 |
| Chess Puzzles | 0% | — |
| DTBench | 43.9% | — |
| Adversarial NLI | 57.3% | — |
| Epoch Capabilities Index | 116.45 | — |
| ForecastBench | 58.6 | — |
| WinoGrande | 75.7% | — |
Math Yi-1.5-34B leads
Llama 3-8B: 8.8 (#323), Yi-1.5-34B: 27.5 (#249)
| Benchmark | Llama 3-8B | Yi-1.5-34B |
|---|---|---|
| LMArena Math | 1151 | 1182 |
| MATH Level 5 | 6.1% | 25.5% |
| OTIS Mock AIME 2024-2025 | 1.9% | — |
Knowledge Yi-1.5-34B leads
Llama 3-8B: 7.8 (#308), Yi-1.5-34B: 14.8 (#295)
| Benchmark | Llama 3-8B | Yi-1.5-34B |
|---|---|---|
| GPQA Diamond | 26.1% | 32% |
| LMArena Expert | 1113 | 1144 |
| ARC (AI2) Challenge | 82.8% | — |
| MMLU | 68.8% | — |
| OpenBookQA | 82.6% | — |
| TriviaQA | 67.7% | — |
Multilingual Yi-1.5-34B leads
Llama 3-8B: 30.8 (#261), Yi-1.5-34B: 32.3 (#256)
| Benchmark | Llama 3-8B | Yi-1.5-34B |
|---|---|---|
| LMArena Non-English | 1098 | 1121 |
| LMArena Chinese | 1076 | 1213 |
| LMArena French | 1159 | 1156 |
| LMArena German | 1104 | 1111 |
| LMArena Japanese | 967 | 1021 |
| LMArena Korean | 1004 | 1005 |
| LMArena Russian | 1109 | 1091 |
| LMArena Spanish | 1173 | 1121 |
Instruction Following Too close to call
Llama 3-8B: 58.4 (#260), Yi-1.5-34B: 59.2 (#257)
| Benchmark | Llama 3-8B | Yi-1.5-34B |
|---|---|---|
| LMArena Instruction Following | 1127 | 1139 |
Long Context Too close to call
Llama 3-8B: 34.2 (#251), Yi-1.5-34B: 34.6 (#248)
| Benchmark | Llama 3-8B | Yi-1.5-34B |
|---|---|---|
| LMArena Longer Query | 1128 | 1143 |
Writing & Preference Too close to call
Llama 3-8B: 37.5 (#256), Yi-1.5-34B: 37.4 (#257)
| Benchmark | Llama 3-8B | Yi-1.5-34B |
|---|---|---|
| LMArena Text | 1166 | 1173 |
| LMArena Creative Writing | 1150 | 1135 |
| LMArena Multi-Turn | 1152 | 1153 |
Frequently asked questions
Is Llama 3-8B better than Yi-1.5-34B?
Yi-1.5-34B is the stronger model overall, scoring 30.6 to 25.5 on the Noometry Index.
Is Llama 3-8B or Yi-1.5-34B better for coding?
Yi-1.5-34B scores higher on coding benchmarks: 32.4 versus 31.0 in the Noometry coding category.
How many benchmarks do Llama 3-8B and Yi-1.5-34B share?
21 benchmarks have published results for both models. Llama 3-8B has 34 scored results on Noometry and Yi-1.5-34B has 21.