Model comparison
Hunyuan Turbo 0110 vs Phi 3 Mini 4k Instruct
Hunyuan Turbo 0110 is the stronger model overall, scoring 39.6 to 27.9 on the Noometry Index.
Last verified . 11 shared benchmarks.
Summary
- They share 11 benchmarks with published results for both. Hunyuan Turbo 0110 scores higher in 7 categories and Phi 3 Mini 4k Instruct in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Hunyuan Turbo 0110 leads 50.2 to 27.6.
- Phi 3 Mini 4k Instruct has downloadable open weights; the other is API-only.
Side by side
| Hunyuan Turbo 0110 | Phi 3 Mini 4k Instruct | |
|---|---|---|
| Provider | Tencent | Microsoft |
| Noometry Index | 39.6 | 27.9 |
| Released | — | 2024-04-23 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 11 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hunyuan Turbo 0110 leads
Hunyuan Turbo 0110: 38.6 (#171), Phi 3 Mini 4k Instruct: 26.6 (#323)
| Benchmark | Hunyuan Turbo 0110 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Coding | 1319 | 1093 |
| LiveBench Coding | — | 15.5% |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 54.2% |
Reasoning Hunyuan Turbo 0110 leads
Hunyuan Turbo 0110: 26.1 (#137), Phi 3 Mini 4k Instruct: 14.1 (#328)
| Benchmark | Hunyuan Turbo 0110 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1308 | 1072 |
| 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 Hunyuan Turbo 0110 leads
Hunyuan Turbo 0110: 35.6 (#180), Phi 3 Mini 4k Instruct: 26.6 (#257)
| Benchmark | Hunyuan Turbo 0110 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Math | 1273 | 1111 |
| LiveBench Math | — | 15.7% |
Knowledge Not comparable
Hunyuan Turbo 0110: —, Phi 3 Mini 4k Instruct: 28.5 (#246)
| Benchmark | Hunyuan Turbo 0110 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Expert | — | 1045 |
| ARC (AI2) Challenge | — | 84.9% |
| MMLU | — | 68.8% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 64% |
Multilingual Hunyuan Turbo 0110 leads
Hunyuan Turbo 0110: 43.3 (#184), Phi 3 Mini 4k Instruct: 26.3 (#280)
| Benchmark | Hunyuan Turbo 0110 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Non-English | 1285 | 1021 |
| LMArena Chinese | 1358 | 1021 |
| LMArena Russian | 1305 | 1022 |
| LMArena French | — | 1076 |
| LMArena German | — | 1044 |
| LMArena Japanese | — | 935 |
| LMArena Korean | — | 905 |
| LMArena Spanish | — | 1085 |
Instruction Following Hunyuan Turbo 0110 leads
Hunyuan Turbo 0110: 67.4 (#195), Phi 3 Mini 4k Instruct: 47.7 (#303)
| Benchmark | Hunyuan Turbo 0110 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Instruction Following | 1278 | 1053 |
| LiveBench Instruction Following | — | 39.1% |
Long Context Hunyuan Turbo 0110 leads
Hunyuan Turbo 0110: 39.8 (#168), Phi 3 Mini 4k Instruct: 31.7 (#276)
| Benchmark | Hunyuan Turbo 0110 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Longer Query | 1309 | 1044 |
Writing & Preference Hunyuan Turbo 0110 leads
Hunyuan Turbo 0110: 50.2 (#183), Phi 3 Mini 4k Instruct: 27.6 (#300)
| Benchmark | Hunyuan Turbo 0110 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Text | 1311 | 1073 |
| LMArena Creative Writing | 1269 | 1037 |
| LMArena Multi-Turn | 1303 | 1018 |
| LiveBench Language | — | 9.2% |
Frequently asked questions
Is Hunyuan Turbo 0110 better than Phi 3 Mini 4k Instruct?
Hunyuan Turbo 0110 is the stronger model overall, scoring 39.6 to 27.9 on the Noometry Index.
Is Hunyuan Turbo 0110 or Phi 3 Mini 4k Instruct better for coding?
Hunyuan Turbo 0110 scores higher on coding benchmarks: 38.6 versus 26.6 in the Noometry coding category.
How many benchmarks do Hunyuan Turbo 0110 and Phi 3 Mini 4k Instruct share?
11 benchmarks have published results for both models. Hunyuan Turbo 0110 has 11 scored results on Noometry and Phi 3 Mini 4k Instruct has 35.