Model comparison
Kimi K2 Thinking Turbo vs Phi 3 Mini 4k Instruct
Kimi K2 Thinking Turbo is the stronger model overall, scoring 45.8 to 27.9 on the Noometry Index.
Last verified . 18 shared benchmarks.
MicrosoftSummary
- They share 18 benchmarks with published results for both. Kimi K2 Thinking Turbo 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 Kimi K2 Thinking Turbo leads 60.0 to 27.6.
- The biggest single-benchmark swing is Chess Puzzles: 20% for Kimi K2 Thinking Turbo and 0% for Phi 3 Mini 4k Instruct.
Side by side
| Kimi K2 Thinking Turbo | Phi 3 Mini 4k Instruct | |
|---|---|---|
| Provider | Moonshot AI | Microsoft |
| Noometry Index | 45.8 | 27.9 |
| Released | 2025-11-06 | 2024-04-23 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 21 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2 Thinking Turbo leads
Kimi K2 Thinking Turbo: 38.4 (#178), Phi 3 Mini 4k Instruct: 26.6 (#323)
| Benchmark | Kimi K2 Thinking Turbo | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Coding | 1454 | 1093 |
| LMArena WebDev | 1322 | — |
| LiveBench Coding | — | 15.5% |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 54.2% |
Reasoning Kimi K2 Thinking Turbo leads
Kimi K2 Thinking Turbo: 32.5 (#75), Phi 3 Mini 4k Instruct: 14.1 (#328)
| Benchmark | Kimi K2 Thinking Turbo | Phi 3 Mini 4k Instruct |
|---|---|---|
| Chess Puzzles | 20% | 0% |
| LMArena Hard Prompts | 1428 | 1072 |
| 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 Kimi K2 Thinking Turbo leads
Kimi K2 Thinking Turbo: 47.4 (#68), Phi 3 Mini 4k Instruct: 26.6 (#257)
| Benchmark | Kimi K2 Thinking Turbo | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Math | 1429 | 1111 |
| OTIS Mock AIME 2024-2025 | 83.1% | — |
| LiveBench Math | — | 15.7% |
Knowledge Kimi K2 Thinking Turbo leads
Kimi K2 Thinking Turbo: 50.9 (#69), Phi 3 Mini 4k Instruct: 28.5 (#246)
| Benchmark | Kimi K2 Thinking Turbo | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Expert | 1439 | 1045 |
| GPQA Diamond | 84.2% | — |
| ARC (AI2) Challenge | — | 84.9% |
| MMLU | — | 68.8% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 64% |
Multilingual Kimi K2 Thinking Turbo leads
Kimi K2 Thinking Turbo: 51.4 (#109), Phi 3 Mini 4k Instruct: 26.3 (#280)
| Benchmark | Kimi K2 Thinking Turbo | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Non-English | 1398 | 1021 |
| LMArena Chinese | 1456 | 1021 |
| LMArena French | 1425 | 1076 |
| LMArena German | 1390 | 1044 |
| LMArena Japanese | 1357 | 935 |
| LMArena Korean | 1330 | 905 |
| LMArena Russian | 1391 | 1022 |
| LMArena Spanish | 1406 | 1085 |
Instruction Following Kimi K2 Thinking Turbo leads
Kimi K2 Thinking Turbo: 74.0 (#109), Phi 3 Mini 4k Instruct: 47.7 (#303)
| Benchmark | Kimi K2 Thinking Turbo | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Instruction Following | 1403 | 1053 |
| LiveBench Instruction Following | — | 39.1% |
Long Context Kimi K2 Thinking Turbo leads
Kimi K2 Thinking Turbo: 43.2 (#102), Phi 3 Mini 4k Instruct: 31.7 (#276)
| Benchmark | Kimi K2 Thinking Turbo | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Longer Query | 1415 | 1044 |
Writing & Preference Kimi K2 Thinking Turbo leads
Kimi K2 Thinking Turbo: 60.0 (#104), Phi 3 Mini 4k Instruct: 27.6 (#300)
| Benchmark | Kimi K2 Thinking Turbo | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Text | 1415 | 1073 |
| LMArena Creative Writing | 1374 | 1037 |
| LMArena Multi-Turn | 1414 | 1018 |
| LiveBench Language | — | 9.2% |
Frequently asked questions
Is Kimi K2 Thinking Turbo better than Phi 3 Mini 4k Instruct?
Kimi K2 Thinking Turbo is the stronger model overall, scoring 45.8 to 27.9 on the Noometry Index.
Is Kimi K2 Thinking Turbo or Phi 3 Mini 4k Instruct better for coding?
Kimi K2 Thinking Turbo scores higher on coding benchmarks: 38.4 versus 26.6 in the Noometry coding category.
How many benchmarks do Kimi K2 Thinking Turbo and Phi 3 Mini 4k Instruct share?
18 benchmarks have published results for both models. Kimi K2 Thinking Turbo has 21 scored results on Noometry and Phi 3 Mini 4k Instruct has 35.