Model comparison
Grok-3 mini vs Phi-4 Mini
Grok-3 mini is the stronger model overall, scoring 41.2 to 30.9 on the Noometry Index.
Last verified . 0 shared benchmarks.
MicrosoftSummary
- The widest gap is in knowledge, where Grok-3 mini leads 46.4 to 25.3.
- Phi-4 Mini has downloadable open weights; the other is API-only.
Side by side
| Grok-3 mini | Phi-4 Mini | |
|---|---|---|
| Provider | xAI | Microsoft |
| Noometry Index | 41.2 | 30.9 |
| Released | 2025-04-09 | 2024-12-11 |
| Weights | Proprietary | Open |
| Context window | — | 128K |
| Max output | — | 4K |
| Input $ / M tokens | — | $0.075 |
| Output $ / M tokens | — | $0.30 |
| Results tracked | 35 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok-3 mini leads
Grok-3 mini: 40.8 (#131), Phi-4 Mini: 28.1 (#317)
| Benchmark | Grok-3 mini | Phi-4 Mini |
|---|---|---|
| Aider Polyglot | 49.3% | — |
| SciCode | — | 10.8% |
| WeirdML | 42.6% | — |
| LMArena Coding | 1379 | — |
Reasoning Phi-4 Mini leads
Grok-3 mini: 13.6 (#334), Phi-4 Mini: 22.4 (#195)
| Benchmark | Grok-3 mini | Phi-4 Mini |
|---|---|---|
| ARC-AGI-2 | 0.4% | — |
| Kagi LLM Benchmark | 61.3% | — |
| ARC-AGI-1 | 16.5% | — |
| CritPt | — | 0% |
| LMArena Hard Prompts | 1375 | — |
| Epoch Capabilities Index | 140.35 | — |
Math Not comparable
Grok-3 mini: 42.1 (#85), Phi-4 Mini: —
| Benchmark | Grok-3 mini | Phi-4 Mini |
|---|---|---|
| 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 Grok-3 mini leads
Grok-3 mini: 46.4 (#81), Phi-4 Mini: 25.3 (#262)
| Benchmark | Grok-3 mini | Phi-4 Mini |
|---|---|---|
| GPQA Diamond | 76.3% | — |
| MMLU-Pro | 79.9% | — |
| Confabulations | 10.8% | — |
| Vectara Hallucination Rate | — | 23.5% |
| GPQA (HELM) | 67.5% | — |
| LMArena Expert | 1395 | — |
Multilingual Not comparable
Grok-3 mini: 48.1 (#145), Phi-4 Mini: —
| Benchmark | Grok-3 mini | Phi-4 Mini |
|---|---|---|
| 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-4 Mini: —
| Benchmark | Grok-3 mini | Phi-4 Mini |
|---|---|---|
| IFEval | 95.1% | — |
| LMArena Instruction Following | 1357 | — |
Long Context Not comparable
Grok-3 mini: 41.0 (#147), Phi-4 Mini: —
| Benchmark | Grok-3 mini | Phi-4 Mini |
|---|---|---|
| Fiction.LiveBench | 66.7% | — |
| LMArena Longer Query | 1372 | — |
Writing & Preference Not comparable
Grok-3 mini: 52.5 (#169), Phi-4 Mini: —
| Benchmark | Grok-3 mini | Phi-4 Mini |
|---|---|---|
| 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-4 Mini?
Grok-3 mini is the stronger model overall, scoring 41.2 to 30.9 on the Noometry Index.
Is Grok-3 mini or Phi-4 Mini better for coding?
Grok-3 mini scores higher on coding benchmarks: 40.8 versus 28.1 in the Noometry coding category.
How many benchmarks do Grok-3 mini and Phi-4 Mini share?
0 benchmarks have published results for both models. Grok-3 mini has 35 scored results on Noometry and Phi-4 Mini has 3.