Model comparison
Grok 4 vs Phi 3 Mini 128k Instruct
Grok 4 is the stronger model overall, scoring 48.1 to 29.7 on the Noometry Index.
Last verified . 17 shared benchmarks.
MicrosoftSummary
- They share 17 benchmarks with published results for both. Grok 4 scores higher in 8 categories and Phi 3 Mini 128k Instruct in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in long context, where Grok 4 leads 63.1 to 30.4.
- Phi 3 Mini 128k Instruct has downloadable open weights; the other is API-only.
Side by side
| Grok 4 | Phi 3 Mini 128k Instruct | |
|---|---|---|
| Provider | xAI | Microsoft |
| Noometry Index | 48.1 | 29.7 |
| Released | 2025-07-09 | 2024-04-23 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 48 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4 leads
Grok 4: 50.3 (#46), Phi 3 Mini 128k Instruct: 28.8 (#312)
| Benchmark | Grok 4 | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Coding | 1408 | 1039 |
| Aider Polyglot | 79.6% | — |
| WeirdML | 45.7% | — |
| BigCodeBench Instruct | — | 29.6% |
| BigCodeBench Complete | — | 40.6% |
Agentic & Tool Use Not comparable
Grok 4: 32.3 (#68), Phi 3 Mini 128k Instruct: —
| Benchmark | Grok 4 | Phi 3 Mini 128k Instruct |
|---|---|---|
| Terminal-Bench | 27.2% | — |
| Berkeley Function Calling Leaderboard | 63% | — |
| GDPval | 21.1% | — |
| Cybench | 43% | — |
| DeepResearch Bench | 47.3% | — |
| BALROG | 43.6% | — |
| LMArena Search | 1142 | — |
| METR Time Horizons | 66.6% | — |
Reasoning Grok 4 leads
Grok 4: 36.7 (#65), Phi 3 Mini 128k Instruct: 19.6 (#256)
| Benchmark | Grok 4 | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1409 | 1028 |
| ARC-AGI-2 | 16% | — |
| SimpleBench | 60.5% | — |
| Kagi LLM Benchmark | 73.6% | — |
| ARC-AGI-1 | 66.7% | — |
| Chess Puzzles | 28% | — |
| Epoch Capabilities Index | 146.44 | — |
| ForecastBench | 60.9 | — |
Math Grok 4 leads
Grok 4: 48.4 (#64), Phi 3 Mini 128k Instruct: 31.6 (#222)
| Benchmark | Grok 4 | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Math | 1422 | 1089 |
| OTIS Mock AIME 2024-2025 | 84% | — |
| Omni-MATH | 60.3% | — |
| FrontierMath (Feb 2025 set) | 19.7% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge Grok 4 leads
Grok 4: 53.8 (#55), Phi 3 Mini 128k Instruct: 26.8 (#254)
| Benchmark | Grok 4 | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Expert | 1415 | 984 |
| GPQA Diamond | 87% | — |
| MMLU-Pro | 85.1% | — |
| Confabulations | 12.4% | — |
| GPQA (HELM) | 72.7% | — |
Multimodal Not comparable
Grok 4: 33.7 (#94), Phi 3 Mini 128k Instruct: —
| Benchmark | Grok 4 | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Vision | 1210 | — |
| GeoBench | 45% | — |
Multilingual Grok 4 leads
Grok 4: 51.8 (#103), Phi 3 Mini 128k Instruct: 25.2 (#285)
| Benchmark | Grok 4 | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Non-English | 1403 | 1000 |
| LMArena Chinese | 1427 | 1016 |
| LMArena French | 1418 | 1039 |
| LMArena German | 1429 | 1006 |
| LMArena Japanese | 1394 | 899 |
| LMArena Korean | 1377 | 856 |
| LMArena Russian | 1410 | 1004 |
| LMArena Spanish | 1420 | 1059 |
Instruction Following Grok 4 leads
Grok 4: 79.2 (#5), Phi 3 Mini 128k Instruct: 51.8 (#294)
| Benchmark | Grok 4 | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Instruction Following | 1387 | 1023 |
| IFEval | 94.9% | — |
Long Context Grok 4 leads
Grok 4: 63.1 (#4), Phi 3 Mini 128k Instruct: 30.4 (#289)
| Benchmark | Grok 4 | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Longer Query | 1409 | 996 |
| Fiction.LiveBench | 94.4% | — |
Writing & Preference Grok 4 leads
Grok 4: 58.5 (#116), Phi 3 Mini 128k Instruct: 27.1 (#301)
| Benchmark | Grok 4 | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Text | 1411 | 1050 |
| LMArena Creative Writing | 1397 | 1024 |
| LMArena Multi-Turn | 1416 | 989 |
| Short-Story Creative Writing | 76.9% | — |
| WildBench | 79.7% | — |
Frequently asked questions
Is Grok 4 better than Phi 3 Mini 128k Instruct?
Grok 4 is the stronger model overall, scoring 48.1 to 29.7 on the Noometry Index.
Is Grok 4 or Phi 3 Mini 128k Instruct better for coding?
Grok 4 scores higher on coding benchmarks: 50.3 versus 28.8 in the Noometry coding category.
How many benchmarks do Grok 4 and Phi 3 Mini 128k Instruct share?
17 benchmarks have published results for both models. Grok 4 has 48 scored results on Noometry and Phi 3 Mini 128k Instruct has 19.