Model comparison
Grok 3 vs Phi 3 Medium 4k Instruct
Grok 3 is the stronger model overall, scoring 39.6 to 32.4 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 Medium 4k Instruct in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Grok 3 leads 52.5 to 30.8.
- Phi 3 Medium 4k Instruct has downloadable open weights; the other is API-only.
Side by side
| Grok 3 | Phi 3 Medium 4k Instruct | |
|---|---|---|
| Provider | xAI | Microsoft |
| Noometry Index | 39.6 | 32.4 |
| Released | 2025-04-09 | — |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 40 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 3 leads
Grok 3: 41.5 (#113), Phi 3 Medium 4k Instruct: 32.3 (#263)
| Benchmark | Grok 3 | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Coding | 1432 | 1130 |
| Aider Polyglot | 53.3% | — |
| WeirdML | 37.2% | — |
Agentic & Tool Use Not comparable
Grok 3: 30.2 (#69), Phi 3 Medium 4k Instruct: —
| Benchmark | Grok 3 | Phi 3 Medium 4k Instruct |
|---|---|---|
| BALROG | 29.5% | — |
Reasoning Phi 3 Medium 4k Instruct leads
Grok 3: 13.8 (#322), Phi 3 Medium 4k Instruct: 20.8 (#214)
| Benchmark | Grok 3 | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1433 | 1127 |
| ARC-AGI-2 | 0% | — |
| SimpleBench | 36.1% | — |
| Kagi LLM Benchmark | 61.3% | — |
| ARC-AGI-1 | 5.5% | — |
| Epoch Capabilities Index | 138.34 | — |
Math Grok 3 leads
Grok 3: 36.2 (#122), Phi 3 Medium 4k Instruct: 30.9 (#202)
| Benchmark | Grok 3 | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Math | 1390 | 1173 |
| 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: 46.0 (#76), Phi 3 Medium 4k Instruct: 29.6 (#226)
| Benchmark | Grok 3 | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Expert | 1420 | 1108 |
| 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: 52.5 (#81), Phi 3 Medium 4k Instruct: 30.8 (#258)
| Benchmark | Grok 3 | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Non-English | 1411 | 1094 |
| LMArena Chinese | 1448 | 1108 |
| LMArena French | 1460 | 1109 |
| LMArena German | 1431 | 1101 |
| LMArena Japanese | 1389 | 1042 |
| LMArena Korean | 1374 | 954 |
| LMArena Russian | 1416 | 1145 |
| LMArena Spanish | 1417 | 1095 |
Instruction Following Grok 3 leads
Grok 3: 75.2 (#69), Phi 3 Medium 4k Instruct: 57.8 (#263)
| Benchmark | Grok 3 | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Instruction Following | 1409 | 1114 |
| IFEval | 88.4% | — |
Long Context Grok 3 leads
Grok 3: 38.7 (#187), Phi 3 Medium 4k Instruct: 33.9 (#250)
| Benchmark | Grok 3 | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Longer Query | 1439 | 1120 |
| Fiction.LiveBench | 58.3% | — |
Writing & Preference Grok 3 leads
Grok 3: 56.0 (#136), Phi 3 Medium 4k Instruct: 34.3 (#267)
| Benchmark | Grok 3 | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Text | 1426 | 1138 |
| LMArena Creative Writing | 1414 | 1106 |
| LMArena Multi-Turn | 1424 | 1088 |
| Short-Story Creative Writing | 76.4% | — |
| EQ-Bench Creative Writing | 1186 | — |
| WildBench | 84.9% | — |
Frequently asked questions
Is Grok 3 better than Phi 3 Medium 4k Instruct?
Grok 3 is the stronger model overall, scoring 39.6 to 32.4 on the Noometry Index.
Is Grok 3 or Phi 3 Medium 4k Instruct better for coding?
Grok 3 scores higher on coding benchmarks: 41.5 versus 32.3 in the Noometry coding category.
How many benchmarks do Grok 3 and Phi 3 Medium 4k Instruct share?
17 benchmarks have published results for both models. Grok 3 has 40 scored results on Noometry and Phi 3 Medium 4k Instruct has 17.