Model comparison
Kimi K2 Thinking Turbo vs phi-3-medium 14B
Kimi K2 Thinking Turbo is the stronger model overall, scoring 45.4 to 29.1 on the Noometry Index.
Last verified . 1 shared benchmarks.
MicrosoftSummary
- They share 1 benchmark with published results for both. Kimi K2 Thinking Turbo scores higher in 3 categories and phi-3-medium 14B in 0 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Kimi K2 Thinking Turbo leads 50.9 to 9.1.
- The biggest single-benchmark swing is GPQA Diamond: 84.2% for Kimi K2 Thinking Turbo and 27.6% for phi-3-medium 14B.
Side by side
| Kimi K2 Thinking Turbo | phi-3-medium 14B | |
|---|---|---|
| Provider | Moonshot AI | Microsoft |
| Noometry Index | 45.4 | 29.1 |
| Released | 2025-11-06 | 2024-04-23 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 21 | 13 |
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: 38.1 (#166), phi-3-medium 14B: 36.3 (#198)
| Benchmark | Kimi K2 Thinking Turbo | phi-3-medium 14B |
|---|---|---|
| LMArena WebDev | 1322 | — |
| BigCodeBench Instruct | — | 37.6% |
| LMArena Coding | 1454 | — |
| BigCodeBench Complete | — | 48.7% |
Reasoning Not comparable
Kimi K2 Thinking Turbo: 31.4 (#72), phi-3-medium 14B: —
| Benchmark | Kimi K2 Thinking Turbo | phi-3-medium 14B |
|---|---|---|
| Chess Puzzles | 20% | — |
| LMArena Hard Prompts | 1428 | — |
| Adversarial NLI | — | 55.8% |
| BIG-Bench Hard | — | 81.4% |
| Epoch Capabilities Index | — | 121.18 |
| HellaSwag | — | 82.4% |
| WinoGrande | — | 81.5% |
Math Kimi K2 Thinking Turbo leads
Kimi K2 Thinking Turbo: 45.5 (#62), phi-3-medium 14B: 25.2 (#249)
| Benchmark | Kimi K2 Thinking Turbo | phi-3-medium 14B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 83.1% | — |
| LMArena Math | 1429 | — |
| MATH Level 5 | — | 17.6% |
Knowledge Kimi K2 Thinking Turbo leads
Kimi K2 Thinking Turbo: 50.9 (#64), phi-3-medium 14B: 9.1 (#301)
| Benchmark | Kimi K2 Thinking Turbo | phi-3-medium 14B |
|---|---|---|
| GPQA Diamond | 84.2% | 27.6% |
| LMArena Expert | 1439 | — |
| ARC (AI2) Challenge | — | 91.6% |
| MMLU | — | 78% |
| OpenBookQA | — | 87.4% |
| TriviaQA | — | 73.9% |
Multilingual Not comparable
Kimi K2 Thinking Turbo: 51.6 (#104), phi-3-medium 14B: —
| Benchmark | Kimi K2 Thinking Turbo | phi-3-medium 14B |
|---|---|---|
| LMArena Non-English | 1398 | — |
| LMArena Chinese | 1457 | — |
| LMArena French | 1425 | — |
| LMArena German | 1390 | — |
| LMArena Japanese | 1356 | — |
| LMArena Korean | 1329 | — |
| LMArena Russian | 1390 | — |
| LMArena Spanish | 1407 | — |
Instruction Following Not comparable
Kimi K2 Thinking Turbo: 74.2 (#103), phi-3-medium 14B: —
| Benchmark | Kimi K2 Thinking Turbo | phi-3-medium 14B |
|---|---|---|
| LMArena Instruction Following | 1403 | — |
Long Context Not comparable
Kimi K2 Thinking Turbo: 43.2 (#99), phi-3-medium 14B: —
| Benchmark | Kimi K2 Thinking Turbo | phi-3-medium 14B |
|---|---|---|
| LMArena Longer Query | 1415 | — |
Writing & Preference Not comparable
Kimi K2 Thinking Turbo: 60.2 (#99), phi-3-medium 14B: —
| Benchmark | Kimi K2 Thinking Turbo | phi-3-medium 14B |
|---|---|---|
| LMArena Text | 1415 | — |
| LMArena Creative Writing | 1373 | — |
| LMArena Multi-Turn | 1414 | — |
Frequently asked questions
Is Kimi K2 Thinking Turbo better than phi-3-medium 14B?
Kimi K2 Thinking Turbo is the stronger model overall, scoring 45.4 to 29.1 on the Noometry Index.
Is Kimi K2 Thinking Turbo or phi-3-medium 14B better for coding?
Kimi K2 Thinking Turbo scores higher on coding benchmarks: 38.1 versus 36.3 in the Noometry coding category.
How many benchmarks do Kimi K2 Thinking Turbo and phi-3-medium 14B share?
1 benchmark has published results for both models. Kimi K2 Thinking Turbo has 21 scored results on Noometry and phi-3-medium 14B has 13.