Model comparison
Hunyuan Large Vision vs Phi 3 Mini 4k Instruct
Hunyuan Large Vision is the stronger model overall, scoring 37.6 to 27.9 on the Noometry Index.
Last verified . 12 shared benchmarks.
Tencent
MicrosoftSummary
- They share 12 benchmarks with published results for both. Hunyuan Large Vision scores higher in 8 categories and Phi 3 Mini 4k Instruct in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Hunyuan Large Vision leads 46.5 to 27.6.
- Phi 3 Mini 4k Instruct has downloadable open weights; the other is API-only.
Side by side
| Hunyuan Large Vision | Phi 3 Mini 4k Instruct | |
|---|---|---|
| Provider | Tencent | Microsoft |
| Noometry Index | 37.6 | 27.9 |
| Released | — | 2024-04-23 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 13 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hunyuan Large Vision leads
Hunyuan Large Vision: 38.3 (#180), Phi 3 Mini 4k Instruct: 26.6 (#323)
| Benchmark | Hunyuan Large Vision | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Coding | 1308 | 1093 |
| LiveBench Coding | — | 15.5% |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 54.2% |
Reasoning Hunyuan Large Vision leads
Hunyuan Large Vision: 24.8 (#158), Phi 3 Mini 4k Instruct: 14.1 (#328)
| Benchmark | Hunyuan Large Vision | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1257 | 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 Large Vision leads
Hunyuan Large Vision: 35.5 (#183), Phi 3 Mini 4k Instruct: 26.6 (#257)
| Benchmark | Hunyuan Large Vision | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Math | 1268 | 1111 |
| LiveBench Math | — | 15.7% |
Knowledge Hunyuan Large Vision leads
Hunyuan Large Vision: 34.4 (#196), Phi 3 Mini 4k Instruct: 28.5 (#246)
| Benchmark | Hunyuan Large Vision | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Expert | 1252 | 1045 |
| ARC (AI2) Challenge | — | 84.9% |
| MMLU | — | 68.8% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 64% |
Multimodal Not comparable
Hunyuan Large Vision: 35.7 (#83), Phi 3 Mini 4k Instruct: —
| Benchmark | Hunyuan Large Vision | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Vision | 1180 | — |
Multilingual Hunyuan Large Vision leads
Hunyuan Large Vision: 39.9 (#221), Phi 3 Mini 4k Instruct: 26.3 (#280)
| Benchmark | Hunyuan Large Vision | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Non-English | 1236 | 1021 |
| LMArena Chinese | 1287 | 1021 |
| LMArena Russian | 1243 | 1022 |
| LMArena French | — | 1076 |
| LMArena German | — | 1044 |
| LMArena Japanese | — | 935 |
| LMArena Korean | — | 905 |
| LMArena Spanish | — | 1085 |
Instruction Following Hunyuan Large Vision leads
Hunyuan Large Vision: 65.8 (#215), Phi 3 Mini 4k Instruct: 47.7 (#303)
| Benchmark | Hunyuan Large Vision | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Instruction Following | 1251 | 1053 |
| LiveBench Instruction Following | — | 39.1% |
Long Context Hunyuan Large Vision leads
Hunyuan Large Vision: 38.9 (#189), Phi 3 Mini 4k Instruct: 31.7 (#276)
| Benchmark | Hunyuan Large Vision | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Longer Query | 1280 | 1044 |
Writing & Preference Hunyuan Large Vision leads
Hunyuan Large Vision: 46.5 (#218), Phi 3 Mini 4k Instruct: 27.6 (#300)
| Benchmark | Hunyuan Large Vision | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Text | 1263 | 1073 |
| LMArena Creative Writing | 1248 | 1037 |
| LMArena Multi-Turn | 1254 | 1018 |
| LiveBench Language | — | 9.2% |
Frequently asked questions
Is Hunyuan Large Vision better than Phi 3 Mini 4k Instruct?
Hunyuan Large Vision is the stronger model overall, scoring 37.6 to 27.9 on the Noometry Index.
Is Hunyuan Large Vision or Phi 3 Mini 4k Instruct better for coding?
Hunyuan Large Vision scores higher on coding benchmarks: 38.3 versus 26.6 in the Noometry coding category.
How many benchmarks do Hunyuan Large Vision and Phi 3 Mini 4k Instruct share?
12 benchmarks have published results for both models. Hunyuan Large Vision has 13 scored results on Noometry and Phi 3 Mini 4k Instruct has 35.