Model comparison
Grok 4.5 vs Phi 3 Mini 4k Instruct
Grok 4.5 is the stronger model overall, scoring 55.0 to 27.9 on the Noometry Index.
Last verified . 18 shared benchmarks.
MicrosoftSummary
- They share 18 benchmarks with published results for both. Grok 4.5 scores higher in 8 categories and Phi 3 Mini 4k Instruct in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.5 leads 56.1 to 14.1.
- The biggest single-benchmark swing is Chess Puzzles: 36% for Grok 4.5 and 0% for Phi 3 Mini 4k Instruct.
- Phi 3 Mini 4k Instruct has downloadable open weights; the other is API-only.
Side by side
| Grok 4.5 | Phi 3 Mini 4k Instruct | |
|---|---|---|
| Provider | xAI | Microsoft |
| Noometry Index | 55.0 | 27.9 |
| Released | 2026-07-08 | 2024-04-23 |
| Weights | Proprietary | Open |
| Context window | 500K | — |
| Max output | 500K | — |
| Input $ / M tokens | $2 | — |
| Output $ / M tokens | $6 | — |
| Results tracked | 52 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4.5 leads
Grok 4.5: 52.2 (#35), Phi 3 Mini 4k Instruct: 26.6 (#323)
| Benchmark | Grok 4.5 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Coding | 1474 | 1093 |
| DeepSWE | 53.8% | — |
| FrontierCode | 42.4% | — |
| LMArena WebDev | 1553 | — |
| SciCode | 54.1% | — |
| WeirdML | 46.4% | — |
| LiveBench Coding | — | 15.5% |
| ALE-Bench | 1,309 | — |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 54.2% |
Agentic & Tool Use Not comparable
Grok 4.5: 44.4 (#17), Phi 3 Mini 4k Instruct: —
| Benchmark | Grok 4.5 | Phi 3 Mini 4k Instruct |
|---|---|---|
| APEX-Agents | 56.2% | — |
| τ²-bench Banking | 47.9% | — |
| PostTrainBench | 23.4% | — |
| GBAEval | 65.4% | — |
| GDP.pdf | 14% | — |
| LMArena Search | 1213 | — |
| Vending-Bench 2 | 3,887 | — |
Reasoning Grok 4.5 leads
Grok 4.5: 56.1 (#25), Phi 3 Mini 4k Instruct: 14.1 (#328)
| Benchmark | Grok 4.5 | Phi 3 Mini 4k Instruct |
|---|---|---|
| Chess Puzzles | 36% | 0% |
| LMArena Hard Prompts | 1462 | 1072 |
| ARC-AGI-2 | 52.6% | — |
| SimpleBench | 70% | — |
| Kagi LLM Benchmark | 83.5% | — |
| NYT Connections (extended) | 79.9% | — |
| ARC-AGI-1 | 87.2% | — |
| CritPt | 15.4% | — |
| LiveBench Reasoning | — | 26.8% |
| DTBench | 96.5% | — |
| LiveBench Data Analysis | — | 34.7% |
| LMCA | 45.2% | — |
| Surface Evolver Bench | 74.4% | — |
| Adversarial NLI | — | 52.8% |
| BIG-Bench Hard | — | 71.7% |
| Epoch Capabilities Index | 153.92 | — |
| HellaSwag | — | 76.7% |
| LiveBench | — | 22.4% |
| WinoGrande | — | 70.8% |
Math Grok 4.5 leads
Grok 4.5: 60.9 (#35), Phi 3 Mini 4k Instruct: 26.6 (#257)
| Benchmark | Grok 4.5 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Math | 1459 | 1111 |
| FrontierMath (Tiers 1-3) | 57.2% | — |
| FrontierMath Tier 4 | 24.4% | — |
| OTIS Mock AIME 2024-2025 | 97.8% | — |
| ProofBench | 31% | — |
| LiveBench Math | — | 15.7% |
Knowledge Grok 4.5 leads
Grok 4.5: 62.3 (#24), Phi 3 Mini 4k Instruct: 28.5 (#246)
| Benchmark | Grok 4.5 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Expert | 1466 | 1045 |
| GPQA Diamond | 93.4% | — |
| SimpleQA Verified | 48.3% | — |
| ARC (AI2) Challenge | — | 84.9% |
| MMLU | — | 68.8% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 64% |
Multimodal Not comparable
Grok 4.5: 37.6 (#72), Phi 3 Mini 4k Instruct: —
| Benchmark | Grok 4.5 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Vision | 1288 | — |
| Blueprint-Bench 2 | 27.3% | — |
| Furniture Assembly | 22.5% | — |
| LMArena Document | 1452 | — |
Multilingual Grok 4.5 leads
Grok 4.5: 54.4 (#42), Phi 3 Mini 4k Instruct: 26.3 (#280)
| Benchmark | Grok 4.5 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Non-English | 1440 | 1021 |
| LMArena Chinese | 1496 | 1021 |
| LMArena French | 1456 | 1076 |
| LMArena German | 1446 | 1044 |
| LMArena Japanese | 1428 | 935 |
| LMArena Korean | 1404 | 905 |
| LMArena Russian | 1448 | 1022 |
| LMArena Spanish | 1450 | 1085 |
Instruction Following Grok 4.5 leads
Grok 4.5: 76.0 (#48), Phi 3 Mini 4k Instruct: 47.7 (#303)
| Benchmark | Grok 4.5 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Instruction Following | 1446 | 1053 |
| LiveBench Instruction Following | — | 39.1% |
Long Context Grok 4.5 leads
Grok 4.5: 44.8 (#56), Phi 3 Mini 4k Instruct: 31.7 (#276)
| Benchmark | Grok 4.5 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Longer Query | 1463 | 1044 |
Writing & Preference Grok 4.5 leads
Grok 4.5: 65.8 (#42), Phi 3 Mini 4k Instruct: 27.6 (#300)
| Benchmark | Grok 4.5 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Text | 1448 | 1073 |
| LMArena Creative Writing | 1442 | 1037 |
| LMArena Multi-Turn | 1456 | 1018 |
| EQ-Bench Creative Writing | 1579 | — |
| LiveBench Language | — | 9.2% |
Frequently asked questions
Is Grok 4.5 better than Phi 3 Mini 4k Instruct?
Grok 4.5 is the stronger model overall, scoring 55.0 to 27.9 on the Noometry Index.
Is Grok 4.5 or Phi 3 Mini 4k Instruct better for coding?
Grok 4.5 scores higher on coding benchmarks: 52.2 versus 26.6 in the Noometry coding category.
How many benchmarks do Grok 4.5 and Phi 3 Mini 4k Instruct share?
18 benchmarks have published results for both models. Grok 4.5 has 52 scored results on Noometry and Phi 3 Mini 4k Instruct has 35.