Model comparison
phi-3-medium 14B vs Yi-1.5-34B
phi-3-medium 14B and Yi-1.5-34B score almost the same on the Noometry Index (29.7 vs 30.6), so choose on price, context window or the category you care about most.
Last verified . 4 shared benchmarks.
MicrosoftSummary
- They share 4 benchmarks with published results for both. phi-3-medium 14B scores higher in 1 category and Yi-1.5-34B in 2 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Yi-1.5-34B leads 14.8 to 9.1.
- The biggest single-benchmark swing is MATH Level 5: 17.6% for phi-3-medium 14B and 25.5% for Yi-1.5-34B.
Side by side
| phi-3-medium 14B | Yi-1.5-34B | |
|---|---|---|
| Provider | Microsoft | 01.AI |
| Noometry Index | 29.7 | 30.6 |
| Released | 2024-04-23 | 2024-05-13 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 13 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding phi-3-medium 14B leads
phi-3-medium 14B: 36.8 (#201), Yi-1.5-34B: 32.4 (#272)
| Benchmark | phi-3-medium 14B | Yi-1.5-34B |
|---|---|---|
| BigCodeBench Instruct | 37.6% | 33.9% |
| BigCodeBench Complete | 48.7% | 43.8% |
| LMArena Coding | — | 1169 |
Reasoning Not comparable
phi-3-medium 14B: —, Yi-1.5-34B: 22.5 (#191)
| Benchmark | phi-3-medium 14B | Yi-1.5-34B |
|---|---|---|
| LMArena Hard Prompts | — | 1160 |
| Adversarial NLI | 55.8% | — |
| BIG-Bench Hard | 81.4% | — |
| Epoch Capabilities Index | 121.23 | — |
| HellaSwag | 82.4% | — |
| WinoGrande | 81.5% | — |
Math Too close to call
phi-3-medium 14B: 27.3 (#250), Yi-1.5-34B: 27.5 (#249)
| Benchmark | phi-3-medium 14B | Yi-1.5-34B |
|---|---|---|
| MATH Level 5 | 17.6% | 25.5% |
| LMArena Math | — | 1182 |
Knowledge Yi-1.5-34B leads
phi-3-medium 14B: 9.1 (#306), Yi-1.5-34B: 14.8 (#295)
| Benchmark | phi-3-medium 14B | Yi-1.5-34B |
|---|---|---|
| GPQA Diamond | 27.6% | 32% |
| LMArena Expert | — | 1144 |
| ARC (AI2) Challenge | 91.6% | — |
| MMLU | 78% | — |
| OpenBookQA | 87.4% | — |
| TriviaQA | 73.9% | — |
Multilingual Not comparable
phi-3-medium 14B: —, Yi-1.5-34B: 32.3 (#256)
| Benchmark | phi-3-medium 14B | Yi-1.5-34B |
|---|---|---|
| LMArena Non-English | — | 1121 |
| LMArena Chinese | — | 1213 |
| LMArena French | — | 1156 |
| LMArena German | — | 1111 |
| LMArena Japanese | — | 1021 |
| LMArena Korean | — | 1005 |
| LMArena Russian | — | 1091 |
| LMArena Spanish | — | 1121 |
Instruction Following Not comparable
phi-3-medium 14B: —, Yi-1.5-34B: 59.2 (#257)
| Benchmark | phi-3-medium 14B | Yi-1.5-34B |
|---|---|---|
| LMArena Instruction Following | — | 1139 |
Long Context Not comparable
phi-3-medium 14B: —, Yi-1.5-34B: 34.6 (#248)
| Benchmark | phi-3-medium 14B | Yi-1.5-34B |
|---|---|---|
| LMArena Longer Query | — | 1143 |
Writing & Preference Not comparable
phi-3-medium 14B: —, Yi-1.5-34B: 37.4 (#257)
| Benchmark | phi-3-medium 14B | Yi-1.5-34B |
|---|---|---|
| LMArena Text | — | 1173 |
| LMArena Creative Writing | — | 1135 |
| LMArena Multi-Turn | — | 1153 |
Frequently asked questions
Is phi-3-medium 14B better than Yi-1.5-34B?
phi-3-medium 14B and Yi-1.5-34B score almost the same on the Noometry Index (29.7 vs 30.6), so choose on price, context window or the category you care about most.
Is phi-3-medium 14B or Yi-1.5-34B better for coding?
phi-3-medium 14B scores higher on coding benchmarks: 36.8 versus 32.4 in the Noometry coding category.
How many benchmarks do phi-3-medium 14B and Yi-1.5-34B share?
4 benchmarks have published results for both models. phi-3-medium 14B has 13 scored results on Noometry and Yi-1.5-34B has 21.