Model comparison
Grok Build 0.1 vs Phi-2
Grok Build 0.1 has enough public results to be ranked (#216); Phi-2 does not yet, so treat this comparison as directional.
Last verified . 0 shared benchmarks.
MicrosoftSummary
- Phi-2 has downloadable open weights; the other is API-only.
Side by side
| Grok Build 0.1 | Phi-2 | |
|---|---|---|
| Provider | xAI | Microsoft |
| Noometry Index | 36.4 | — |
| Released | 2026-04-16 | 2023-12-12 |
| Weights | Proprietary | Open |
| Context window | 256K | — |
| Max output | 256K | — |
| Input $ / M tokens | $1 | — |
| Output $ / M tokens | $2 | — |
| Results tracked | 3 | 11 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Grok Build 0.1: 43.1 (#91), Phi-2: —
| Benchmark | Grok Build 0.1 | Phi-2 |
|---|---|---|
| SciCode | 50.2% | — |
| HumanEval+ | — | 45.1% |
| MBPP+ | — | 54.2% |
Agentic & Tool Use Not comparable
Grok Build 0.1: 22.7 (#129), Phi-2: —
| Benchmark | Grok Build 0.1 | Phi-2 |
|---|---|---|
| GBAEval | 2.4% | — |
Reasoning Not comparable
Grok Build 0.1: 32.2 (#77), Phi-2: —
| Benchmark | Grok Build 0.1 | Phi-2 |
|---|---|---|
| CritPt | 9.1% | — |
| Adversarial NLI | — | 42.5% |
| BIG-Bench Hard | — | 59.4% |
| Epoch Capabilities Index | — | 107.94 |
| HellaSwag | — | 53.6% |
| WinoGrande | — | 54.7% |
Knowledge Not comparable
Grok Build 0.1: —, Phi-2: —
| Benchmark | Grok Build 0.1 | Phi-2 |
|---|---|---|
| ARC (AI2) Challenge | — | 75.9% |
| MMLU | — | 58.4% |
| OpenBookQA | — | 73.6% |
| TriviaQA | — | 45.2% |
Frequently asked questions
Is Grok Build 0.1 better than Phi-2?
Grok Build 0.1 has enough public results to be ranked (#216); Phi-2 does not yet, so treat this comparison as directional.
How many benchmarks do Grok Build 0.1 and Phi-2 share?
0 benchmarks have published results for both models. Grok Build 0.1 has 3 scored results on Noometry and Phi-2 has 11.