Model comparison
Kimi K2.7 Code vs phi-3-medium 14B
Kimi K2.7 Code is the stronger model overall, scoring 43.3 to 29.7 on the Noometry Index.
Last verified . 2 shared benchmarks.
MicrosoftSummary
- They share 2 benchmarks with published results for both. Kimi K2.7 Code 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 K2.7 Code leads 53.5 to 9.1.
- The biggest single-benchmark swing is GPQA Diamond: 87.9% for Kimi K2.7 Code and 27.6% for phi-3-medium 14B.
Side by side
| Kimi K2.7 Code | phi-3-medium 14B | |
|---|---|---|
| Provider | Moonshot AI | Microsoft |
| Noometry Index | 43.3 | 29.7 |
| Released | 2026-06-12 | 2024-04-23 |
| Weights | Open | Open |
| Context window | 262K | — |
| Max output | 262K | — |
| Input $ / M tokens | $0.95 | — |
| Output $ / M tokens | $4 | — |
| Results tracked | 19 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2.7 Code leads
Kimi K2.7 Code: 42.9 (#95), phi-3-medium 14B: 36.8 (#201)
| Benchmark | Kimi K2.7 Code | phi-3-medium 14B |
|---|---|---|
| DeepSWE | 30.5% | — |
| FrontierCode | 30.1% | — |
| LMArena WebDev | 1473 | — |
| SciCode | 47.5% | — |
| WeirdML | 54.1% | — |
| BigCodeBench Instruct | — | 37.6% |
| BigCodeBench Complete | — | 48.7% |
| ALE-Bench | 886.23 | — |
Agentic & Tool Use Not comparable
Kimi K2.7 Code: 24.0 (#122), phi-3-medium 14B: —
| Benchmark | Kimi K2.7 Code | phi-3-medium 14B |
|---|---|---|
| APEX-Agents | 37.6% | — |
| GBAEval | 0.9% | — |
| Vending-Bench 2 | 5,083 | — |
Reasoning Not comparable
Kimi K2.7 Code: 39.0 (#61), phi-3-medium 14B: —
| Benchmark | Kimi K2.7 Code | phi-3-medium 14B |
|---|---|---|
| Epoch Capabilities Index | 149.97 | 121.23 |
| SimpleBench | 57.9% | — |
| CritPt | 10% | — |
| Chess Puzzles | 21% | — |
| Surface Evolver Bench | 48.8% | — |
| Adversarial NLI | — | 55.8% |
| BIG-Bench Hard | — | 81.4% |
| HellaSwag | — | 82.4% |
| WinoGrande | — | 81.5% |
Math Kimi K2.7 Code leads
Kimi K2.7 Code: 52.9 (#48), phi-3-medium 14B: 27.3 (#250)
| Benchmark | Kimi K2.7 Code | phi-3-medium 14B |
|---|---|---|
| FrontierMath (Tiers 1-3) | 54% | — |
| FrontierMath Tier 4 | 12.2% | — |
| OTIS Mock AIME 2024-2025 | 95.6% | — |
| MATH Level 5 | — | 17.6% |
Knowledge Kimi K2.7 Code leads
Kimi K2.7 Code: 53.5 (#57), phi-3-medium 14B: 9.1 (#306)
| Benchmark | Kimi K2.7 Code | phi-3-medium 14B |
|---|---|---|
| GPQA Diamond | 87.9% | 27.6% |
| SimpleQA Verified | 36.5% | — |
| ARC (AI2) Challenge | — | 91.6% |
| MMLU | — | 78% |
| OpenBookQA | — | 87.4% |
| TriviaQA | — | 73.9% |
Frequently asked questions
Is Kimi K2.7 Code better than phi-3-medium 14B?
Kimi K2.7 Code is the stronger model overall, scoring 43.3 to 29.7 on the Noometry Index.
Is Kimi K2.7 Code or phi-3-medium 14B better for coding?
Kimi K2.7 Code scores higher on coding benchmarks: 42.9 versus 36.8 in the Noometry coding category.
How many benchmarks do Kimi K2.7 Code and phi-3-medium 14B share?
2 benchmarks have published results for both models. Kimi K2.7 Code has 19 scored results on Noometry and phi-3-medium 14B has 13.