Model comparison
Phi 3 Mini 4k Instruct vs Yi-1.5-34B
Yi-1.5-34B is the stronger model overall, scoring 30.6 to 27.9 on the Noometry Index.
Last verified . 17 shared benchmarks.
MicrosoftSummary
- They share 17 benchmarks with published results for both. Phi 3 Mini 4k Instruct scores higher in 1 category and Yi-1.5-34B in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Phi 3 Mini 4k Instruct leads 28.5 to 14.8.
Side by side
| Phi 3 Mini 4k Instruct | Yi-1.5-34B | |
|---|---|---|
| Provider | Microsoft | 01.AI |
| Noometry Index | 27.9 | 30.6 |
| Released | 2024-04-23 | 2024-05-13 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 35 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Yi-1.5-34B leads
Phi 3 Mini 4k Instruct: 26.6 (#323), Yi-1.5-34B: 32.4 (#272)
| Benchmark | Phi 3 Mini 4k Instruct | Yi-1.5-34B |
|---|---|---|
| LMArena Coding | 1093 | 1169 |
| BigCodeBench Instruct | — | 33.9% |
| LiveBench Coding | 15.5% | — |
| BigCodeBench Complete | — | 43.8% |
| HumanEval+ | 59.1% | — |
| MBPP+ | 54.2% | — |
Reasoning Yi-1.5-34B leads
Phi 3 Mini 4k Instruct: 14.1 (#328), Yi-1.5-34B: 22.5 (#191)
| Benchmark | Phi 3 Mini 4k Instruct | Yi-1.5-34B |
|---|---|---|
| LMArena Hard Prompts | 1072 | 1160 |
| Chess Puzzles | 0% | — |
| LiveBench Reasoning | 26.8% | — |
| LiveBench Data Analysis | 34.7% | — |
| Adversarial NLI | 52.8% | — |
| BIG-Bench Hard | 71.7% | — |
| HellaSwag | 76.7% | — |
| LiveBench | 22.4% | — |
| WinoGrande | 70.8% | — |
Math Too close to call
Phi 3 Mini 4k Instruct: 26.6 (#257), Yi-1.5-34B: 27.5 (#249)
| Benchmark | Phi 3 Mini 4k Instruct | Yi-1.5-34B |
|---|---|---|
| LMArena Math | 1111 | 1182 |
| LiveBench Math | 15.7% | — |
| MATH Level 5 | — | 25.5% |
Knowledge Phi 3 Mini 4k Instruct leads
Phi 3 Mini 4k Instruct: 28.5 (#246), Yi-1.5-34B: 14.8 (#295)
| Benchmark | Phi 3 Mini 4k Instruct | Yi-1.5-34B |
|---|---|---|
| LMArena Expert | 1045 | 1144 |
| GPQA Diamond | — | 32% |
| ARC (AI2) Challenge | 84.9% | — |
| MMLU | 68.8% | — |
| OpenBookQA | 88% | — |
| TriviaQA | 64% | — |
Multilingual Yi-1.5-34B leads
Phi 3 Mini 4k Instruct: 26.3 (#280), Yi-1.5-34B: 32.3 (#256)
| Benchmark | Phi 3 Mini 4k Instruct | Yi-1.5-34B |
|---|---|---|
| LMArena Non-English | 1021 | 1121 |
| LMArena Chinese | 1021 | 1213 |
| LMArena French | 1076 | 1156 |
| LMArena German | 1044 | 1111 |
| LMArena Japanese | 935 | 1021 |
| LMArena Korean | 905 | 1005 |
| LMArena Russian | 1022 | 1091 |
| LMArena Spanish | 1085 | 1121 |
Instruction Following Yi-1.5-34B leads
Phi 3 Mini 4k Instruct: 47.7 (#303), Yi-1.5-34B: 59.2 (#257)
| Benchmark | Phi 3 Mini 4k Instruct | Yi-1.5-34B |
|---|---|---|
| LMArena Instruction Following | 1053 | 1139 |
| LiveBench Instruction Following | 39.1% | — |
Long Context Yi-1.5-34B leads
Phi 3 Mini 4k Instruct: 31.7 (#276), Yi-1.5-34B: 34.6 (#248)
| Benchmark | Phi 3 Mini 4k Instruct | Yi-1.5-34B |
|---|---|---|
| LMArena Longer Query | 1044 | 1143 |
Writing & Preference Yi-1.5-34B leads
Phi 3 Mini 4k Instruct: 27.6 (#300), Yi-1.5-34B: 37.4 (#257)
| Benchmark | Phi 3 Mini 4k Instruct | Yi-1.5-34B |
|---|---|---|
| LMArena Text | 1073 | 1173 |
| LMArena Creative Writing | 1037 | 1135 |
| LMArena Multi-Turn | 1018 | 1153 |
| LiveBench Language | 9.2% | — |
Frequently asked questions
Is Phi 3 Mini 4k Instruct better than Yi-1.5-34B?
Yi-1.5-34B is the stronger model overall, scoring 30.6 to 27.9 on the Noometry Index.
Is Phi 3 Mini 4k Instruct or Yi-1.5-34B better for coding?
Yi-1.5-34B scores higher on coding benchmarks: 32.4 versus 26.6 in the Noometry coding category.
How many benchmarks do Phi 3 Mini 4k Instruct and Yi-1.5-34B share?
17 benchmarks have published results for both models. Phi 3 Mini 4k Instruct has 35 scored results on Noometry and Yi-1.5-34B has 21.