Model comparison
phi-3-medium 14B vs Trinity Large Thinking
Trinity Large Thinking is the stronger model overall, scoring 38.6 to 29.7 on the Noometry Index.
Last verified . 0 shared benchmarks.
Microsoft
Arcee AISummary
- The widest gap is in knowledge, where Trinity Large Thinking leads 40.9 to 9.1.
Side by side
| phi-3-medium 14B | Trinity Large Thinking | |
|---|---|---|
| Provider | Microsoft | Arcee AI |
| Noometry Index | 29.7 | 38.6 |
| Released | 2024-04-23 | 2026-04-01 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 80K |
| Input $ / M tokens | — | $0.25 |
| Output $ / M tokens | — | $0.80 |
| Results tracked | 13 | 24 |
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), Trinity Large Thinking: 34.1 (#244)
| Benchmark | phi-3-medium 14B | Trinity Large Thinking |
|---|---|---|
| LMArena WebDev | — | 1238 |
| SciCode | — | 36.1% |
| BigCodeBench Instruct | 37.6% | — |
| LMArena Coding | — | 1381 |
| BigCodeBench Complete | 48.7% | — |
Reasoning Not comparable
phi-3-medium 14B: —, Trinity Large Thinking: 16.9 (#298)
| Benchmark | phi-3-medium 14B | Trinity Large Thinking |
|---|---|---|
| NYT Connections (extended) | — | 16.5% |
| CritPt | — | 0.9% |
| Thematic Generalization | — | 41.6% |
| LMArena Hard Prompts | — | 1350 |
| Surface Evolver Bench | — | 15.6% |
| Adversarial NLI | 55.8% | — |
| BIG-Bench Hard | 81.4% | — |
| Epoch Capabilities Index | 121.23 | — |
| HellaSwag | 82.4% | — |
| WinoGrande | 81.5% | — |
Math Trinity Large Thinking leads
phi-3-medium 14B: 27.3 (#250), Trinity Large Thinking: 37.6 (#149)
| Benchmark | phi-3-medium 14B | Trinity Large Thinking |
|---|---|---|
| LMArena Math | — | 1366 |
| MATH Level 5 | 17.6% | — |
Knowledge Trinity Large Thinking leads
phi-3-medium 14B: 9.1 (#306), Trinity Large Thinking: 40.9 (#113)
| Benchmark | phi-3-medium 14B | Trinity Large Thinking |
|---|---|---|
| GPQA Diamond | 27.6% | — |
| Vectara Hallucination Rate | — | 6.9% |
| LMArena Expert | — | 1360 |
| ARC (AI2) Challenge | 91.6% | — |
| MMLU | 78% | — |
| OpenBookQA | 87.4% | — |
| TriviaQA | 73.9% | — |
Multilingual Not comparable
phi-3-medium 14B: —, Trinity Large Thinking: 46.2 (#160)
| Benchmark | phi-3-medium 14B | Trinity Large Thinking |
|---|---|---|
| LMArena Non-English | — | 1325 |
| LMArena Chinese | — | 1373 |
| LMArena French | — | 1374 |
| LMArena German | — | 1356 |
| LMArena Japanese | — | 1311 |
| LMArena Korean | — | 1306 |
| LMArena Russian | — | 1337 |
| LMArena Spanish | — | 1357 |
Instruction Following Not comparable
phi-3-medium 14B: —, Trinity Large Thinking: 70.5 (#162)
| Benchmark | phi-3-medium 14B | Trinity Large Thinking |
|---|---|---|
| LMArena Instruction Following | — | 1334 |
Long Context Not comparable
phi-3-medium 14B: —, Trinity Large Thinking: 41.3 (#144)
| Benchmark | phi-3-medium 14B | Trinity Large Thinking |
|---|---|---|
| LMArena Longer Query | — | 1355 |
Writing & Preference Not comparable
phi-3-medium 14B: —, Trinity Large Thinking: 53.8 (#158)
| Benchmark | phi-3-medium 14B | Trinity Large Thinking |
|---|---|---|
| LMArena Text | — | 1340 |
| LMArena Creative Writing | — | 1320 |
| LMArena Multi-Turn | — | 1342 |
Frequently asked questions
Is phi-3-medium 14B better than Trinity Large Thinking?
Trinity Large Thinking is the stronger model overall, scoring 38.6 to 29.7 on the Noometry Index.
Is phi-3-medium 14B or Trinity Large Thinking better for coding?
phi-3-medium 14B scores higher on coding benchmarks: 36.8 versus 34.1 in the Noometry coding category.
How many benchmarks do phi-3-medium 14B and Trinity Large Thinking share?
0 benchmarks have published results for both models. phi-3-medium 14B has 13 scored results on Noometry and Trinity Large Thinking has 24.