Model comparison
Grok-2 (Dec 2024) vs phi-3-medium 14B
Grok-2 (Dec 2024) is the stronger model overall, scoring 33.4 to 29.1 on the Noometry Index.
Last verified . 3 shared benchmarks.
MicrosoftSummary
- They share 3 benchmarks with published results for both. Grok-2 (Dec 2024) scores higher in 1 category and phi-3-medium 14B in 2 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Grok-2 (Dec 2024) leads 29.8 to 9.1.
- The biggest single-benchmark swing is MATH Level 5: 63.5% for Grok-2 (Dec 2024) and 17.6% for phi-3-medium 14B.
- phi-3-medium 14B has downloadable open weights; the other is API-only.
Side by side
| Grok-2 (Dec 2024) | phi-3-medium 14B | |
|---|---|---|
| Provider | xAI | Microsoft |
| Noometry Index | 33.4 | 29.1 |
| Released | 2024-08-13 | 2024-04-23 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 34 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding phi-3-medium 14B leads
Grok-2 (Dec 2024): 32.9 (#254), phi-3-medium 14B: 36.3 (#198)
| Benchmark | Grok-2 (Dec 2024) | phi-3-medium 14B |
|---|---|---|
| WeirdML | 22.2% | — |
| BigCodeBench Instruct | — | 37.6% |
| LiveBench Coding | 46.4% | — |
| LMArena Coding | 1288 | — |
| BigCodeBench Complete | — | 48.7% |
Reasoning Not comparable
Grok-2 (Dec 2024): 16.4 (#294), phi-3-medium 14B: —
| Benchmark | Grok-2 (Dec 2024) | phi-3-medium 14B |
|---|---|---|
| Epoch Capabilities Index | 130.48 | 121.18 |
| SimpleBench | 22.7% | — |
| LiveBench Reasoning | 54.8% | — |
| LMArena Hard Prompts | 1272 | — |
| DTBench | 65.2% | — |
| LiveBench Data Analysis | 54.5% | — |
| Adversarial NLI | — | 55.8% |
| BIG-Bench Hard | — | 81.4% |
| HellaSwag | — | 82.4% |
| LiveBench | 54.3% | — |
| WinoGrande | — | 81.5% |
Math phi-3-medium 14B leads
Grok-2 (Dec 2024): 19.6 (#278), phi-3-medium 14B: 25.2 (#249)
| Benchmark | Grok-2 (Dec 2024) | phi-3-medium 14B |
|---|---|---|
| MATH Level 5 | 63.5% | 17.6% |
| OTIS Mock AIME 2024-2025 | 11.5% | — |
| LiveBench Math | 54.9% | — |
| LMArena Math | 1283 | — |
| FrontierMath (Feb 2025 set) | 0.7% | — |
Knowledge Grok-2 (Dec 2024) leads
Grok-2 (Dec 2024): 29.8 (#225), phi-3-medium 14B: 9.1 (#301)
| Benchmark | Grok-2 (Dec 2024) | phi-3-medium 14B |
|---|---|---|
| GPQA Diamond | 53.8% | 27.6% |
| Confabulations | 20.1% | — |
| LMArena Expert | 1254 | — |
| ARC (AI2) Challenge | — | 91.6% |
| MMLU | — | 78% |
| OpenBookQA | — | 87.4% |
| TriviaQA | — | 73.9% |
Multilingual Not comparable
Grok-2 (Dec 2024): 43.3 (#183), phi-3-medium 14B: —
| Benchmark | Grok-2 (Dec 2024) | phi-3-medium 14B |
|---|---|---|
| LMArena Non-English | 1282 | — |
| LMArena Chinese | 1289 | — |
| LMArena French | 1317 | — |
| LMArena German | 1287 | — |
| LMArena Japanese | 1244 | — |
| LMArena Korean | 1237 | — |
| LMArena Russian | 1286 | — |
| LMArena Spanish | 1281 | — |
Instruction Following Not comparable
Grok-2 (Dec 2024): 67.1 (#197), phi-3-medium 14B: —
| Benchmark | Grok-2 (Dec 2024) | phi-3-medium 14B |
|---|---|---|
| LiveBench Instruction Following | 69.6% | — |
| LMArena Instruction Following | 1270 | — |
Long Context Not comparable
Grok-2 (Dec 2024): 38.7 (#186), phi-3-medium 14B: —
| Benchmark | Grok-2 (Dec 2024) | phi-3-medium 14B |
|---|---|---|
| LMArena Longer Query | 1276 | — |
Writing & Preference Not comparable
Grok-2 (Dec 2024): 48.8 (#192), phi-3-medium 14B: —
| Benchmark | Grok-2 (Dec 2024) | phi-3-medium 14B |
|---|---|---|
| LMArena Text | 1305 | — |
| LMArena Creative Writing | 1284 | — |
| Short-Story Creative Writing | 63.6% | — |
| LMArena Multi-Turn | 1290 | — |
| LiveBench Language | 45.6% | — |
Frequently asked questions
Is Grok-2 (Dec 2024) better than phi-3-medium 14B?
Grok-2 (Dec 2024) is the stronger model overall, scoring 33.4 to 29.1 on the Noometry Index.
Is Grok-2 (Dec 2024) or phi-3-medium 14B better for coding?
phi-3-medium 14B scores higher on coding benchmarks: 36.3 versus 32.9 in the Noometry coding category.
How many benchmarks do Grok-2 (Dec 2024) and phi-3-medium 14B share?
3 benchmarks have published results for both models. Grok-2 (Dec 2024) has 34 scored results on Noometry and phi-3-medium 14B has 13.