Model comparison
Grok 3 vs Phi 3 Mini 128k Instruct
Grok 3 is the stronger model overall, scoring 39.9 to 29.7 on the Noometry Index.
Last verified . 17 shared benchmarks.
MicrosoftSummary
- They share 17 benchmarks with published results for both. Grok 3 scores higher in 7 categories and Phi 3 Mini 128k Instruct in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Grok 3 leads 55.8 to 27.1.
- Phi 3 Mini 128k Instruct has downloadable open weights; the other is API-only.
Side by side
| Grok 3 | Phi 3 Mini 128k Instruct | |
|---|---|---|
| Provider | xAI | Microsoft |
| Noometry Index | 39.9 | 29.7 |
| Released | 2025-04-09 | 2024-04-23 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 40 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 3 leads
Grok 3: 41.9 (#115), Phi 3 Mini 128k Instruct: 28.8 (#312)
| Benchmark | Grok 3 | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Coding | 1432 | 1039 |
| Aider Polyglot | 53.3% | — |
| WeirdML | 37.2% | — |
| BigCodeBench Instruct | — | 29.6% |
| BigCodeBench Complete | — | 40.6% |
Agentic & Tool Use Not comparable
Grok 3: 30.5 (#76), Phi 3 Mini 128k Instruct: —
| Benchmark | Grok 3 | Phi 3 Mini 128k Instruct |
|---|---|---|
| BALROG | 29.5% | — |
Reasoning Phi 3 Mini 128k Instruct leads
Grok 3: 13.7 (#333), Phi 3 Mini 128k Instruct: 19.6 (#256)
| Benchmark | Grok 3 | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1434 | 1028 |
| ARC-AGI-2 | 0% | — |
| SimpleBench | 36.1% | — |
| Kagi LLM Benchmark | 61.3% | — |
| ARC-AGI-1 | 5.5% | — |
| Epoch Capabilities Index | 138.33 | — |
Math Grok 3 leads
Grok 3: 38.0 (#145), Phi 3 Mini 128k Instruct: 31.6 (#222)
| Benchmark | Grok 3 | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Math | 1391 | 1089 |
| OTIS Mock AIME 2024-2025 | 55.6% | — |
| Omni-MATH | 46.4% | — |
| MATH Level 5 | 88.7% | — |
| FrontierMath (Feb 2025 set) | 3.8% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Grok 3 leads
Grok 3: 46.2 (#82), Phi 3 Mini 128k Instruct: 26.8 (#254)
| Benchmark | Grok 3 | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Expert | 1421 | 984 |
| GPQA Diamond | 75.8% | — |
| MMLU-Pro | 78.8% | — |
| Confabulations | 14.2% | — |
| Vectara Hallucination Rate | 5.8% | — |
| GPQA (HELM) | 65% | — |
Multilingual Grok 3 leads
Grok 3: 52.3 (#87), Phi 3 Mini 128k Instruct: 25.2 (#285)
| Benchmark | Grok 3 | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Non-English | 1410 | 1000 |
| LMArena Chinese | 1448 | 1016 |
| LMArena French | 1460 | 1039 |
| LMArena German | 1431 | 1006 |
| LMArena Japanese | 1387 | 899 |
| LMArena Korean | 1373 | 856 |
| LMArena Russian | 1416 | 1004 |
| LMArena Spanish | 1417 | 1059 |
Instruction Following Grok 3 leads
Grok 3: 75.0 (#73), Phi 3 Mini 128k Instruct: 51.8 (#294)
| Benchmark | Grok 3 | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Instruction Following | 1409 | 1023 |
| IFEval | 88.4% | — |
Long Context Grok 3 leads
Grok 3: 38.7 (#192), Phi 3 Mini 128k Instruct: 30.4 (#289)
| Benchmark | Grok 3 | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Longer Query | 1439 | 996 |
| Fiction.LiveBench | 58.3% | — |
Writing & Preference Grok 3 leads
Grok 3: 55.8 (#141), Phi 3 Mini 128k Instruct: 27.1 (#301)
| Benchmark | Grok 3 | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Text | 1426 | 1050 |
| LMArena Creative Writing | 1414 | 1024 |
| LMArena Multi-Turn | 1425 | 989 |
| Short-Story Creative Writing | 76.4% | — |
| EQ-Bench Creative Writing | 1186 | — |
| WildBench | 84.9% | — |
Frequently asked questions
Is Grok 3 better than Phi 3 Mini 128k Instruct?
Grok 3 is the stronger model overall, scoring 39.9 to 29.7 on the Noometry Index.
Is Grok 3 or Phi 3 Mini 128k Instruct better for coding?
Grok 3 scores higher on coding benchmarks: 41.9 versus 28.8 in the Noometry coding category.
How many benchmarks do Grok 3 and Phi 3 Mini 128k Instruct share?
17 benchmarks have published results for both models. Grok 3 has 40 scored results on Noometry and Phi 3 Mini 128k Instruct has 19.