Model comparison
Llama 3.1-70B vs Yi-34B
Llama 3.1-70B is the stronger model overall, scoring 29.6 to 27.8 on the Noometry Index.
Last verified . 21 shared benchmarks.
MetaSummary
- They share 21 benchmarks with published results for both. Llama 3.1-70B 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 3.1-70B leads 24.2 to 7.5.
- The biggest single-benchmark swing is MATH Level 5: 36.7% for Llama 3.1-70B and 5.1% for Yi-34B.
Side by side
| Llama 3.1-70B | Yi-34B | |
|---|---|---|
| Provider | Meta | 01.AI |
| Noometry Index | 29.6 | 27.8 |
| Released | 2024-07-23 | 2023-11-02 |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.40 | — |
| Output $ / M tokens | $0.40 | — |
| Results tracked | 35 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Yi-34B leads
Llama 3.1-70B: 30.3 (#296), Yi-34B: 32.3 (#274)
| Benchmark | Llama 3.1-70B | Yi-34B |
|---|---|---|
| LMArena Coding | 1260 | 1112 |
| WeirdML | 9% | — |
| BigCodeBench Instruct | 46.1% | — |
| BigCodeBench Complete | 54.8% | — |
Agentic & Tool Use Not comparable
Llama 3.1-70B: 25.1 (#112), Yi-34B: —
| Benchmark | Llama 3.1-70B | Yi-34B |
|---|---|---|
| TheAgentCompany | 6.9% | — |
| BALROG | 27.9% | — |
Reasoning Too close to call
Llama 3.1-70B: 21.6 (#220), Yi-34B: 21.2 (#226)
| Benchmark | Llama 3.1-70B | Yi-34B |
|---|---|---|
| LMArena Hard Prompts | 1241 | 1104 |
| Epoch Capabilities Index | 125.92 | 117.39 |
| DTBench | 60% | — |
| LMCA | 14.8% | — |
| BIG-Bench Hard | — | 71.7% |
Math Yi-34B leads
Llama 3.1-70B: 13.5 (#304), Yi-34B: 21.6 (#282)
| Benchmark | Llama 3.1-70B | Yi-34B |
|---|---|---|
| LMArena Math | 1252 | 1114 |
| MATH Level 5 | 36.7% | 5.1% |
| OTIS Mock AIME 2024-2025 | 3.6% | — |
| Omni-MATH | 21% | — |
| GSM8K | — | 76% |
Knowledge Llama 3.1-70B leads
Llama 3.1-70B: 24.2 (#269), Yi-34B: 7.5 (#309)
| Benchmark | Llama 3.1-70B | Yi-34B |
|---|---|---|
| GPQA Diamond | 44.2% | 14.7% |
| LMArena Expert | 1209 | 1061 |
| MMLU | 80.1% | 76.3% |
| MMLU-Pro | 65.3% | — |
| GPQA (HELM) | 42.6% | — |
Multilingual Llama 3.1-70B leads
Llama 3.1-70B: 38.8 (#225), Yi-34B: 29.7 (#264)
| Benchmark | Llama 3.1-70B | Yi-34B |
|---|---|---|
| LMArena Non-English | 1219 | 1079 |
| LMArena Chinese | 1215 | 1176 |
| LMArena French | 1261 | 1081 |
| LMArena German | 1222 | 1042 |
| LMArena Japanese | 1132 | 993 |
| LMArena Korean | 1140 | 959 |
| LMArena Russian | 1234 | 1050 |
| LMArena Spanish | 1253 | 1070 |
Instruction Following Llama 3.1-70B leads
Llama 3.1-70B: 65.3 (#223), Yi-34B: 56.2 (#274)
| Benchmark | Llama 3.1-70B | Yi-34B |
|---|---|---|
| LMArena Instruction Following | 1231 | 1091 |
| IFEval | 82.1% | — |
Long Context Llama 3.1-70B leads
Llama 3.1-70B: 37.6 (#214), Yi-34B: 33.2 (#264)
| Benchmark | Llama 3.1-70B | Yi-34B |
|---|---|---|
| LMArena Longer Query | 1241 | 1094 |
Writing & Preference Llama 3.1-70B leads
Llama 3.1-70B: 35.4 (#267), Yi-34B: 34.1 (#273)
| Benchmark | Llama 3.1-70B | Yi-34B |
|---|---|---|
| LMArena Text | 1261 | 1129 |
| LMArena Creative Writing | 1232 | 1108 |
| LMArena Multi-Turn | 1256 | 1113 |
| EQ-Bench Creative Writing | 784 | — |
| WildBench | 75.8% | — |
Frequently asked questions
Is Llama 3.1-70B better than Yi-34B?
Llama 3.1-70B is the stronger model overall, scoring 29.6 to 27.8 on the Noometry Index.
Is Llama 3.1-70B or Yi-34B better for coding?
Yi-34B scores higher on coding benchmarks: 32.3 versus 30.3 in the Noometry coding category.
How many benchmarks do Llama 3.1-70B and Yi-34B share?
21 benchmarks have published results for both models. Llama 3.1-70B has 35 scored results on Noometry and Yi-34B has 23.