Model comparison
Kimi K2.5 Instant vs phi-3-medium 14B
Kimi K2.5 Instant is the stronger model overall, scoring 42.9 to 29.1 on the Noometry Index.
Last verified . 0 shared benchmarks.
MicrosoftSummary
- The widest gap is in knowledge, where Kimi K2.5 Instant leads 39.5 to 9.1.
Side by side
| Kimi K2.5 Instant | phi-3-medium 14B | |
|---|---|---|
| Provider | Moonshot AI | Microsoft |
| Noometry Index | 42.9 | 29.1 |
| Released | — | 2024-04-23 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 18 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2.5 Instant leads
Kimi K2.5 Instant: 42.3 (#95), phi-3-medium 14B: 36.3 (#198)
| Benchmark | Kimi K2.5 Instant | phi-3-medium 14B |
|---|---|---|
| LMArena WebDev | 1404 | — |
| BigCodeBench Instruct | — | 37.6% |
| LMArena Coding | 1483 | — |
| BigCodeBench Complete | — | 48.7% |
Reasoning Not comparable
Kimi K2.5 Instant: 28.5 (#88), phi-3-medium 14B: —
| Benchmark | Kimi K2.5 Instant | phi-3-medium 14B |
|---|---|---|
| LMArena Hard Prompts | 1443 | — |
| Adversarial NLI | — | 55.8% |
| BIG-Bench Hard | — | 81.4% |
| Epoch Capabilities Index | — | 121.18 |
| HellaSwag | — | 82.4% |
| WinoGrande | — | 81.5% |
Math Kimi K2.5 Instant leads
Kimi K2.5 Instant: 36.6 (#105), phi-3-medium 14B: 25.2 (#249)
| Benchmark | Kimi K2.5 Instant | phi-3-medium 14B |
|---|---|---|
| LMArena Math | 1443 | — |
| MATH Level 5 | — | 17.6% |
Knowledge Kimi K2.5 Instant leads
Kimi K2.5 Instant: 39.5 (#121), phi-3-medium 14B: 9.1 (#301)
| Benchmark | Kimi K2.5 Instant | phi-3-medium 14B |
|---|---|---|
| GPQA Diamond | — | 27.6% |
| LMArena Expert | 1438 | — |
| ARC (AI2) Challenge | — | 91.6% |
| MMLU | — | 78% |
| OpenBookQA | — | 87.4% |
| TriviaQA | — | 73.9% |
Multimodal Not comparable
Kimi K2.5 Instant: 39.5 (#47), phi-3-medium 14B: —
| Benchmark | Kimi K2.5 Instant | phi-3-medium 14B |
|---|---|---|
| LMArena Vision | 1254 | — |
Multilingual Not comparable
Kimi K2.5 Instant: 52.2 (#89), phi-3-medium 14B: —
| Benchmark | Kimi K2.5 Instant | phi-3-medium 14B |
|---|---|---|
| LMArena Non-English | 1406 | — |
| LMArena Chinese | 1450 | — |
| LMArena French | 1403 | — |
| LMArena German | 1413 | — |
| LMArena Korean | 1378 | — |
| LMArena Russian | 1404 | — |
| LMArena Spanish | 1448 | — |
Instruction Following Not comparable
Kimi K2.5 Instant: 75.5 (#61), phi-3-medium 14B: —
| Benchmark | Kimi K2.5 Instant | phi-3-medium 14B |
|---|---|---|
| LMArena Instruction Following | 1430 | — |
Long Context Not comparable
Kimi K2.5 Instant: 43.8 (#82), phi-3-medium 14B: —
| Benchmark | Kimi K2.5 Instant | phi-3-medium 14B |
|---|---|---|
| LMArena Longer Query | 1435 | — |
Writing & Preference Not comparable
Kimi K2.5 Instant: 60.8 (#91), phi-3-medium 14B: —
| Benchmark | Kimi K2.5 Instant | phi-3-medium 14B |
|---|---|---|
| LMArena Text | 1420 | — |
| LMArena Creative Writing | 1379 | — |
| LMArena Multi-Turn | 1427 | — |
Frequently asked questions
Is Kimi K2.5 Instant better than phi-3-medium 14B?
Kimi K2.5 Instant is the stronger model overall, scoring 42.9 to 29.1 on the Noometry Index.
Is Kimi K2.5 Instant or phi-3-medium 14B better for coding?
Kimi K2.5 Instant scores higher on coding benchmarks: 42.3 versus 36.3 in the Noometry coding category.
How many benchmarks do Kimi K2.5 Instant and phi-3-medium 14B share?
0 benchmarks have published results for both models. Kimi K2.5 Instant has 18 scored results on Noometry and phi-3-medium 14B has 13.