Model comparison
Grok-3 mini vs Phi-2
Grok-3 mini has enough public results to be ranked (#141); Phi-2 does not yet, so treat this comparison as directional.
Last verified . 1 shared benchmarks.
MicrosoftSummary
- They share 1 benchmark with published results for both.
- Phi-2 has downloadable open weights; the other is API-only.
Side by side
| Grok-3 mini | Phi-2 | |
|---|---|---|
| Provider | xAI | Microsoft |
| Noometry Index | 41.2 | — |
| Released | 2025-04-09 | 2023-12-12 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 35 | 11 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Grok-3 mini: 40.8 (#131), Phi-2: —
| Benchmark | Grok-3 mini | Phi-2 |
|---|---|---|
| Aider Polyglot | 49.3% | — |
| WeirdML | 42.6% | — |
| LMArena Coding | 1379 | — |
| HumanEval+ | — | 45.1% |
| MBPP+ | — | 54.2% |
Reasoning Not comparable
Grok-3 mini: 13.6 (#334), Phi-2: —
| Benchmark | Grok-3 mini | Phi-2 |
|---|---|---|
| Epoch Capabilities Index | 140.35 | 107.94 |
| ARC-AGI-2 | 0.4% | — |
| Kagi LLM Benchmark | 61.3% | — |
| ARC-AGI-1 | 16.5% | — |
| LMArena Hard Prompts | 1375 | — |
| Adversarial NLI | — | 42.5% |
| BIG-Bench Hard | — | 59.4% |
| HellaSwag | — | 53.6% |
| WinoGrande | — | 54.7% |
Math Not comparable
Grok-3 mini: 42.1 (#85), Phi-2: —
| Benchmark | Grok-3 mini | Phi-2 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 77.8% | — |
| Omni-MATH | 31.8% | — |
| LMArena Math | 1386 | — |
| MATH Level 5 | 90.9% | — |
| FrontierMath (Feb 2025 set) | 5.9% | — |
Knowledge Not comparable
Grok-3 mini: 46.4 (#81), Phi-2: —
| Benchmark | Grok-3 mini | Phi-2 |
|---|---|---|
| GPQA Diamond | 76.3% | — |
| MMLU-Pro | 79.9% | — |
| Confabulations | 10.8% | — |
| GPQA (HELM) | 67.5% | — |
| LMArena Expert | 1395 | — |
| ARC (AI2) Challenge | — | 75.9% |
| MMLU | — | 58.4% |
| OpenBookQA | — | 73.6% |
| TriviaQA | — | 45.2% |
Multilingual Not comparable
Grok-3 mini: 48.1 (#145), Phi-2: —
| Benchmark | Grok-3 mini | Phi-2 |
|---|---|---|
| LMArena Non-English | 1352 | — |
| LMArena Chinese | 1387 | — |
| LMArena French | 1357 | — |
| LMArena German | 1349 | — |
| LMArena Japanese | 1342 | — |
| LMArena Korean | 1335 | — |
| LMArena Russian | 1353 | — |
| LMArena Spanish | 1381 | — |
Instruction Following Not comparable
Grok-3 mini: 78.5 (#9), Phi-2: —
| Benchmark | Grok-3 mini | Phi-2 |
|---|---|---|
| IFEval | 95.1% | — |
| LMArena Instruction Following | 1357 | — |
Long Context Not comparable
Grok-3 mini: 41.0 (#147), Phi-2: —
| Benchmark | Grok-3 mini | Phi-2 |
|---|---|---|
| Fiction.LiveBench | 66.7% | — |
| LMArena Longer Query | 1372 | — |
Writing & Preference Not comparable
Grok-3 mini: 52.5 (#169), Phi-2: —
| Benchmark | Grok-3 mini | Phi-2 |
|---|---|---|
| LMArena Text | 1370 | — |
| LMArena Creative Writing | 1342 | — |
| Short-Story Creative Writing | 73.5% | — |
| WildBench | 65.1% | — |
| LMArena Multi-Turn | 1355 | — |
Frequently asked questions
Is Grok-3 mini better than Phi-2?
Grok-3 mini has enough public results to be ranked (#141); Phi-2 does not yet, so treat this comparison as directional.
How many benchmarks do Grok-3 mini and Phi-2 share?
1 benchmark has published results for both models. Grok-3 mini has 35 scored results on Noometry and Phi-2 has 11.