Model comparison
Grok 4.6 vs Phi-3.5-mini
Grok 4.6 has enough public results to be ranked (#19); Phi-3.5-mini does not yet, so treat this comparison as directional.
Last verified . 0 shared benchmarks.
MicrosoftSummary
- The widest gap is in coding, where Grok 4.6 leads 58.0 to 34.0.
- Phi-3.5-mini has downloadable open weights; the other is API-only.
Side by side
| Grok 4.6 | Phi-3.5-mini | |
|---|---|---|
| Provider | xAI | Microsoft |
| Noometry Index | 56.8 | 36.4 |
| Released | 2026-08-12 | 2024-08-16 |
| Weights | Proprietary | Open |
| Context window | 500K | — |
| Max output | 500K | — |
| Input $ / M tokens | $2 | — |
| Output $ / M tokens | $6 | — |
| Results tracked | 49 | 5 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4.6 leads
Grok 4.6: 58.0 (#14), Phi-3.5-mini: 34.0 (#231)
| Benchmark | Grok 4.6 | Phi-3.5-mini |
|---|---|---|
| DeepSWE | 67.5% | — |
| FrontierCode | 48% | — |
| CursorBench | 41.4% | — |
| LMArena WebDev | 1620 | — |
| FrontierSWE | 25.3% | — |
| SciCode | 56.5% | — |
| WeirdML | 67.3% | — |
| BigCodeBench Instruct | — | 32.8% |
| LMArena Coding | 1464 | — |
| BigCodeBench Complete | — | 38.5% |
| ALE-Bench | 1,508 | — |
Agentic & Tool Use Not comparable
Grok 4.6: 39.4 (#25), Phi-3.5-mini: —
| Benchmark | Grok 4.6 | Phi-3.5-mini |
|---|---|---|
| APEX-Agents | 65.3% | — |
| GDP.pdf | 17.2% | — |
| Vending-Bench 2 | 9,047 | — |
Reasoning Not comparable
Grok 4.6: 61.3 (#18), Phi-3.5-mini: —
| Benchmark | Grok 4.6 | Phi-3.5-mini |
|---|---|---|
| ARC-AGI-2 | 67.1% | — |
| SimpleBench | 75.9% | — |
| NYT Connections (extended) | 80% | — |
| ARC-AGI-1 | 87.5% | — |
| CritPt | 19.7% | — |
| Chess Puzzles | 40% | — |
| EBR-Bench | 30.5% | — |
| LMArena Hard Prompts | 1445 | — |
| Mystery Game Puzzles | 34% | — |
| DTBench | 97.3% | — |
| LMCA | 48.5% | — |
| Epoch Capabilities Index | 156.48 | — |
| PIQA | — | 81% |
Math Not comparable
Grok 4.6: 66.8 (#19), Phi-3.5-mini: —
| Benchmark | Grok 4.6 | Phi-3.5-mini |
|---|---|---|
| FrontierMath (Tiers 1-3) | 66% | — |
| FrontierMath Tier 4 | 31.7% | — |
| OTIS Mock AIME 2024-2025 | 99.2% | — |
| ProofBench | 51% | — |
| LMArena Math | 1416 | — |
| GSM8K | — | 86.2% |
Knowledge Not comparable
Grok 4.6: 63.3 (#18), Phi-3.5-mini: —
| Benchmark | Grok 4.6 | Phi-3.5-mini |
|---|---|---|
| GPQA Diamond | 94% | — |
| SimpleQA Verified | 49.3% | — |
| LMArena Expert | 1463 | — |
| BoolQ | — | 78% |
Multimodal Not comparable
Grok 4.6: 43.9 (#18), Phi-3.5-mini: —
| Benchmark | Grok 4.6 | Phi-3.5-mini |
|---|---|---|
| LMArena Vision | 1265 | — |
| Blueprint-Bench 2 | 33.2% | — |
| Furniture Assembly | 40% | — |
| LMArena Document | 1452 | — |
Multilingual Not comparable
Grok 4.6: 53.3 (#67), Phi-3.5-mini: —
| Benchmark | Grok 4.6 | Phi-3.5-mini |
|---|---|---|
| LMArena Non-English | 1422 | — |
| LMArena Chinese | 1479 | — |
| LMArena French | 1458 | — |
| LMArena German | 1425 | — |
| LMArena Japanese | 1383 | — |
| LMArena Korean | 1395 | — |
| LMArena Russian | 1427 | — |
| LMArena Spanish | 1408 | — |
Instruction Following Not comparable
Grok 4.6: 75.6 (#59), Phi-3.5-mini: —
| Benchmark | Grok 4.6 | Phi-3.5-mini |
|---|---|---|
| LMArena Instruction Following | 1431 | — |
Long Context Not comparable
Grok 4.6: 44.4 (#62), Phi-3.5-mini: —
| Benchmark | Grok 4.6 | Phi-3.5-mini |
|---|---|---|
| LMArena Longer Query | 1453 | — |
Writing & Preference Not comparable
Grok 4.6: 62.5 (#77), Phi-3.5-mini: —
| Benchmark | Grok 4.6 | Phi-3.5-mini |
|---|---|---|
| LMArena Text | 1427 | — |
| LMArena Creative Writing | 1430 | — |
| LMArena Multi-Turn | 1422 | — |
Frequently asked questions
Is Grok 4.6 better than Phi-3.5-mini?
Grok 4.6 has enough public results to be ranked (#19); Phi-3.5-mini does not yet, so treat this comparison as directional.
Is Grok 4.6 or Phi-3.5-mini better for coding?
Grok 4.6 scores higher on coding benchmarks: 58.0 versus 34.0 in the Noometry coding category.
How many benchmarks do Grok 4.6 and Phi-3.5-mini share?
0 benchmarks have published results for both models. Grok 4.6 has 49 scored results on Noometry and Phi-3.5-mini has 5.