Model comparison
Phi 3 Mini 4k Instruct vs Trinity Large Thinking
Trinity Large Thinking is the stronger model overall, scoring 38.6 to 27.9 on the Noometry Index.
Last verified . 17 shared benchmarks.
Microsoft
Arcee AISummary
- They share 17 benchmarks with published results for both. Phi 3 Mini 4k Instruct scores higher in 0 categories and Trinity Large Thinking in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Trinity Large Thinking leads 53.8 to 27.6.
Side by side
| Phi 3 Mini 4k Instruct | Trinity Large Thinking | |
|---|---|---|
| Provider | Microsoft | Arcee AI |
| Noometry Index | 27.9 | 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 | 35 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Trinity Large Thinking leads
Phi 3 Mini 4k Instruct: 26.6 (#323), Trinity Large Thinking: 34.1 (#244)
| Benchmark | Phi 3 Mini 4k Instruct | Trinity Large Thinking |
|---|---|---|
| LMArena Coding | 1093 | 1381 |
| LMArena WebDev | — | 1238 |
| SciCode | — | 36.1% |
| LiveBench Coding | 15.5% | — |
| HumanEval+ | 59.1% | — |
| MBPP+ | 54.2% | — |
Reasoning Trinity Large Thinking leads
Phi 3 Mini 4k Instruct: 14.1 (#328), Trinity Large Thinking: 16.9 (#298)
| Benchmark | Phi 3 Mini 4k Instruct | Trinity Large Thinking |
|---|---|---|
| LMArena Hard Prompts | 1072 | 1350 |
| NYT Connections (extended) | — | 16.5% |
| CritPt | — | 0.9% |
| Chess Puzzles | 0% | — |
| Thematic Generalization | — | 41.6% |
| LiveBench Reasoning | 26.8% | — |
| LiveBench Data Analysis | 34.7% | — |
| Surface Evolver Bench | — | 15.6% |
| Adversarial NLI | 52.8% | — |
| BIG-Bench Hard | 71.7% | — |
| HellaSwag | 76.7% | — |
| LiveBench | 22.4% | — |
| WinoGrande | 70.8% | — |
Math Trinity Large Thinking leads
Phi 3 Mini 4k Instruct: 26.6 (#257), Trinity Large Thinking: 37.6 (#149)
| Benchmark | Phi 3 Mini 4k Instruct | Trinity Large Thinking |
|---|---|---|
| LMArena Math | 1111 | 1366 |
| LiveBench Math | 15.7% | — |
Knowledge Trinity Large Thinking leads
Phi 3 Mini 4k Instruct: 28.5 (#246), Trinity Large Thinking: 40.9 (#113)
| Benchmark | Phi 3 Mini 4k Instruct | Trinity Large Thinking |
|---|---|---|
| LMArena Expert | 1045 | 1360 |
| Vectara Hallucination Rate | — | 6.9% |
| ARC (AI2) Challenge | 84.9% | — |
| MMLU | 68.8% | — |
| OpenBookQA | 88% | — |
| TriviaQA | 64% | — |
Multilingual Trinity Large Thinking leads
Phi 3 Mini 4k Instruct: 26.3 (#280), Trinity Large Thinking: 46.2 (#160)
| Benchmark | Phi 3 Mini 4k Instruct | Trinity Large Thinking |
|---|---|---|
| LMArena Non-English | 1021 | 1325 |
| LMArena Chinese | 1021 | 1373 |
| LMArena French | 1076 | 1374 |
| LMArena German | 1044 | 1356 |
| LMArena Japanese | 935 | 1311 |
| LMArena Korean | 905 | 1306 |
| LMArena Russian | 1022 | 1337 |
| LMArena Spanish | 1085 | 1357 |
Instruction Following Trinity Large Thinking leads
Phi 3 Mini 4k Instruct: 47.7 (#303), Trinity Large Thinking: 70.5 (#162)
| Benchmark | Phi 3 Mini 4k Instruct | Trinity Large Thinking |
|---|---|---|
| LMArena Instruction Following | 1053 | 1334 |
| LiveBench Instruction Following | 39.1% | — |
Long Context Trinity Large Thinking leads
Phi 3 Mini 4k Instruct: 31.7 (#276), Trinity Large Thinking: 41.3 (#144)
| Benchmark | Phi 3 Mini 4k Instruct | Trinity Large Thinking |
|---|---|---|
| LMArena Longer Query | 1044 | 1355 |
Writing & Preference Trinity Large Thinking leads
Phi 3 Mini 4k Instruct: 27.6 (#300), Trinity Large Thinking: 53.8 (#158)
| Benchmark | Phi 3 Mini 4k Instruct | Trinity Large Thinking |
|---|---|---|
| LMArena Text | 1073 | 1340 |
| LMArena Creative Writing | 1037 | 1320 |
| LMArena Multi-Turn | 1018 | 1342 |
| LiveBench Language | 9.2% | — |
Frequently asked questions
Is Phi 3 Mini 4k Instruct better than Trinity Large Thinking?
Trinity Large Thinking is the stronger model overall, scoring 38.6 to 27.9 on the Noometry Index.
Is Phi 3 Mini 4k Instruct or Trinity Large Thinking better for coding?
Trinity Large Thinking scores higher on coding benchmarks: 34.1 versus 26.6 in the Noometry coding category.
How many benchmarks do Phi 3 Mini 4k Instruct and Trinity Large Thinking share?
17 benchmarks have published results for both models. Phi 3 Mini 4k Instruct has 35 scored results on Noometry and Trinity Large Thinking has 24.