Model comparison
Grok 4.7 vs Phi-3.5-MoE
Grok 4.7 has enough public results to be ranked (#37); Phi-3.5-MoE does not yet, so treat this comparison as directional.
Last verified . 0 shared benchmarks.
MicrosoftSummary
- Phi-3.5-MoE has downloadable open weights; the other is API-only.
Side by side
| Grok 4.7 | Phi-3.5-MoE | |
|---|---|---|
| Provider | xAI | Microsoft |
| Noometry Index | 53.1 | — |
| Released | 2026-09-21 | 2024-08-17 |
| Weights | Proprietary | Open |
| Context window | 500K | — |
| Max output | 500K | — |
| Input $ / M tokens | $2 | — |
| Output $ / M tokens | $6 | — |
| Results tracked | 39 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Grok 4.7: 58.0 (#18), Phi-3.5-MoE: —
| Benchmark | Grok 4.7 | Phi-3.5-MoE |
|---|---|---|
| FrontierCode | 47.6% | — |
| CursorBench | 46.3% | — |
| LMArena WebDev | 1639 | — |
| FrontierSWE | 29.5% | — |
| SciCode | 57.8% | — |
| LMArena Coding | 1427 | — |
Agentic & Tool Use Not comparable
Grok 4.7: 36.7 (#37), Phi-3.5-MoE: —
| Benchmark | Grok 4.7 | Phi-3.5-MoE |
|---|---|---|
| APEX-Agents | 54.6% | — |
| GDP.pdf | 22.8% | — |
| Vending-Bench 2 | 10,537 | — |
Reasoning Not comparable
Grok 4.7: 49.1 (#40), Phi-3.5-MoE: —
| Benchmark | Grok 4.7 | Phi-3.5-MoE |
|---|---|---|
| NYT Connections (extended) | 76.8% | — |
| CritPt | 18% | — |
| Chess Puzzles | 38% | — |
| LMArena Hard Prompts | 1413 | — |
| Mystery Game Puzzles | 29% | — |
| DTBench | 96% | — |
| LMCA | 49.4% | — |
| Epoch Capabilities Index | 153.53 | — |
| PIQA | — | 88.6% |
Math Not comparable
Grok 4.7: 57.8 (#39), Phi-3.5-MoE: —
| Benchmark | Grok 4.7 | Phi-3.5-MoE |
|---|---|---|
| FrontierMath (Tiers 1-3) | 53% | — |
| FrontierMath Tier 4 | 17.1% | — |
| OTIS Mock AIME 2024-2025 | 98.1% | — |
| ProofBench | 34% | — |
| LMArena Math | 1407 | — |
| GSM8K | — | 88.7% |
Knowledge Not comparable
Grok 4.7: 62.8 (#22), Phi-3.5-MoE: —
| Benchmark | Grok 4.7 | Phi-3.5-MoE |
|---|---|---|
| GPQA Diamond | 92.7% | — |
| SimpleQA Verified | 56% | — |
| LMArena Expert | 1422 | — |
| BoolQ | — | 84.6% |
Multimodal Not comparable
Grok 4.7: 35.5 (#87), Phi-3.5-MoE: —
| Benchmark | Grok 4.7 | Phi-3.5-MoE |
|---|---|---|
| LMArena Vision | 1228 | — |
| Blueprint-Bench 2 | 32.5% | — |
| Furniture Assembly | 20.8% | — |
Multilingual Not comparable
Grok 4.7: 50.8 (#116), Phi-3.5-MoE: —
| Benchmark | Grok 4.7 | Phi-3.5-MoE |
|---|---|---|
| LMArena Non-English | 1389 | — |
| LMArena Chinese | 1455 | — |
| LMArena French | 1455 | — |
| LMArena Russian | 1397 | — |
| LMArena Spanish | 1400 | — |
Instruction Following Not comparable
Grok 4.7: 74.1 (#105), Phi-3.5-MoE: —
| Benchmark | Grok 4.7 | Phi-3.5-MoE |
|---|---|---|
| LMArena Instruction Following | 1404 | — |
Long Context Not comparable
Grok 4.7: 43.1 (#104), Phi-3.5-MoE: —
| Benchmark | Grok 4.7 | Phi-3.5-MoE |
|---|---|---|
| LMArena Longer Query | 1413 | — |
Writing & Preference Not comparable
Grok 4.7: 70.0 (#24), Phi-3.5-MoE: —
| Benchmark | Grok 4.7 | Phi-3.5-MoE |
|---|---|---|
| LMArena Text | 1399 | — |
| LMArena Creative Writing | 1391 | — |
| EQ-Bench Creative Writing | 2007 | — |
| LMArena Multi-Turn | 1393 | — |
Frequently asked questions
Is Grok 4.7 better than Phi-3.5-MoE?
Grok 4.7 has enough public results to be ranked (#37); Phi-3.5-MoE does not yet, so treat this comparison as directional.
How many benchmarks do Grok 4.7 and Phi-3.5-MoE share?
0 benchmarks have published results for both models. Grok 4.7 has 39 scored results on Noometry and Phi-3.5-MoE has 3.