Model comparison
Llama 3.1-8B vs Yi-1.5-34B
Yi-1.5-34B is the stronger model overall, scoring 30.2 to 22.8 on the Noometry Index.
Last verified . 21 shared benchmarks.
MetaSummary
- They share 21 benchmarks with published results for both. Llama 3.1-8B scores higher in 2 categories and Yi-1.5-34B in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Yi-1.5-34B leads 25.3 to 9.5.
- The biggest single-benchmark swing is GPQA Diamond: 27% for Llama 3.1-8B and 32% for Yi-1.5-34B.
Side by side
| Llama 3.1-8B | Yi-1.5-34B | |
|---|---|---|
| Provider | Meta | 01.AI |
| Noometry Index | 22.8 | 30.2 |
| Released | 2024-07-23 | 2024-05-13 |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.05 | — |
| Output $ / M tokens | $0.08 | — |
| Results tracked | 43 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Yi-1.5-34B leads
Llama 3.1-8B: 19.9 (#335), Yi-1.5-34B: 31.9 (#267)
| Benchmark | Llama 3.1-8B | Yi-1.5-34B |
|---|---|---|
| BigCodeBench Instruct | 32.8% | 33.9% |
| LMArena Coding | 1195 | 1169 |
| BigCodeBench Complete | 40.5% | 43.8% |
| SciCode | 13.2% | — |
| WeirdML | 1.7% | — |
| HumanEval+ | 62.8% | — |
| MBPP+ | 55.6% | — |
Agentic & Tool Use Not comparable
Llama 3.1-8B: 22.3 (#123), Yi-1.5-34B: —
| Benchmark | Llama 3.1-8B | Yi-1.5-34B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 25.8% | — |
| BALROG | 15.1% | — |
Reasoning Yi-1.5-34B leads
Llama 3.1-8B: 14.5 (#316), Yi-1.5-34B: 21.5 (#195)
| Benchmark | Llama 3.1-8B | Yi-1.5-34B |
|---|---|---|
| LMArena Hard Prompts | 1175 | 1160 |
| CritPt | 0% | — |
| Chess Puzzles | 0% | — |
| DTBench | 50.9% | — |
| LMCA | 5.4% | — |
| Epoch Capabilities Index | 116.48 | — |
| PIQA | 81.2% | — |
Math Yi-1.5-34B leads
Llama 3.1-8B: 9.5 (#311), Yi-1.5-34B: 25.3 (#248)
| Benchmark | Llama 3.1-8B | Yi-1.5-34B |
|---|---|---|
| LMArena Math | 1179 | 1182 |
| MATH Level 5 | 22.9% | 25.5% |
| OTIS Mock AIME 2024-2025 | 1.7% | — |
| Omni-MATH | 13.7% | — |
| GSM8K | 82.4% | — |
Knowledge Yi-1.5-34B leads
Llama 3.1-8B: 8.0 (#302), Yi-1.5-34B: 14.8 (#290)
| Benchmark | Llama 3.1-8B | Yi-1.5-34B |
|---|---|---|
| GPQA Diamond | 27% | 32% |
| LMArena Expert | 1144 | 1144 |
| MMLU-Pro | 40.6% | — |
| GPQA (HELM) | 24.7% | — |
| BoolQ | 82.8% | — |
| MMLU | 56.1% | — |
Multilingual Llama 3.1-8B leads
Llama 3.1-8B: 34.2 (#244), Yi-1.5-34B: 32.5 (#251)
| Benchmark | Llama 3.1-8B | Yi-1.5-34B |
|---|---|---|
| LMArena Non-English | 1148 | 1121 |
| LMArena Chinese | 1151 | 1213 |
| LMArena French | 1176 | 1155 |
| LMArena German | 1144 | 1111 |
| LMArena Japanese | 1061 | 1021 |
| LMArena Korean | 1053 | 1005 |
| LMArena Russian | 1158 | 1091 |
| LMArena Spanish | 1169 | 1120 |
Instruction Following Too close to call
Llama 3.1-8B: 59.1 (#253), Yi-1.5-34B: 59.4 (#252)
| Benchmark | Llama 3.1-8B | Yi-1.5-34B |
|---|---|---|
| LMArena Instruction Following | 1159 | 1139 |
| IFEval | 74.3% | — |
Long Context Llama 3.1-8B leads
Llama 3.1-8B: 35.8 (#233), Yi-1.5-34B: 34.6 (#243)
| Benchmark | Llama 3.1-8B | Yi-1.5-34B |
|---|---|---|
| LMArena Longer Query | 1182 | 1144 |
Writing & Preference Yi-1.5-34B leads
Llama 3.1-8B: 29.9 (#285), Yi-1.5-34B: 37.6 (#252)
| Benchmark | Llama 3.1-8B | Yi-1.5-34B |
|---|---|---|
| LMArena Text | 1187 | 1173 |
| LMArena Creative Writing | 1154 | 1135 |
| LMArena Multi-Turn | 1172 | 1153 |
| EQ-Bench Creative Writing | 713 | — |
| WildBench | 68.7% | — |
Frequently asked questions
Is Llama 3.1-8B better than Yi-1.5-34B?
Yi-1.5-34B is the stronger model overall, scoring 30.2 to 22.8 on the Noometry Index.
Is Llama 3.1-8B or Yi-1.5-34B better for coding?
Yi-1.5-34B scores higher on coding benchmarks: 31.9 versus 19.9 in the Noometry coding category.
How many benchmarks do Llama 3.1-8B and Yi-1.5-34B share?
21 benchmarks have published results for both models. Llama 3.1-8B has 43 scored results on Noometry and Yi-1.5-34B has 21.