Model comparison
Grok 4.3 vs Phi 3 Mini 4k Instruct
Grok 4.3 is the stronger model overall, scoring 43.6 to 27.4 on the Noometry Index.
Last verified . 18 shared benchmarks.
MicrosoftSummary
- They share 18 benchmarks with published results for both. Grok 4.3 scores higher in 8 categories and Phi 3 Mini 4k Instruct in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Grok 4.3 leads 58.6 to 27.7.
- The biggest single-benchmark swing is Chess Puzzles: 25% for Grok 4.3 and 0% for Phi 3 Mini 4k Instruct.
- Phi 3 Mini 4k Instruct has downloadable open weights; the other is API-only.
Side by side
| Grok 4.3 | Phi 3 Mini 4k Instruct | |
|---|---|---|
| Provider | xAI | Microsoft |
| Noometry Index | 43.6 | 27.4 |
| Released | 2026-04-17 | 2024-04-23 |
| Weights | Proprietary | Open |
| Context window | 1M | — |
| Max output | 30K | — |
| Input $ / M tokens | $1.25 | — |
| Output $ / M tokens | $2.50 | — |
| Results tracked | 40 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4.3 leads
Grok 4.3: 41.3 (#117), Phi 3 Mini 4k Instruct: 26.1 (#319)
| Benchmark | Grok 4.3 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Coding | 1415 | 1093 |
| LMArena WebDev | 1357 | — |
| SciCode | 47.3% | — |
| WeirdML | 49.9% | — |
| LiveBench Coding | — | 15.5% |
| ALE-Bench | 944.17 | — |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 54.2% |
Agentic & Tool Use Not comparable
Grok 4.3: 27.6 (#93), Phi 3 Mini 4k Instruct: —
| Benchmark | Grok 4.3 | Phi 3 Mini 4k Instruct |
|---|---|---|
| GDP.pdf | 8% | — |
| LMArena Search | 1165 | — |
| Vending-Bench 2 | 35.26 | — |
Reasoning Grok 4.3 leads
Grok 4.3: 34.9 (#60), Phi 3 Mini 4k Instruct: 13.6 (#326)
| Benchmark | Grok 4.3 | Phi 3 Mini 4k Instruct |
|---|---|---|
| Chess Puzzles | 25% | 0% |
| LMArena Hard Prompts | 1397 | 1072 |
| NYT Connections (extended) | 55.2% | — |
| CritPt | 8% | — |
| LiveBench Reasoning | — | 26.8% |
| DTBench | 90.7% | — |
| LiveBench Data Analysis | — | 34.7% |
| LMCA | 38.3% | — |
| Adversarial NLI | — | 52.8% |
| BIG-Bench Hard | — | 71.7% |
| Epoch Capabilities Index | 149.13 | — |
| ForecastBench | 60.3 | — |
| HellaSwag | — | 76.7% |
| LiveBench | — | 22.4% |
| WinoGrande | — | 70.8% |
Math Grok 4.3 leads
Grok 4.3: 45.8 (#60), Phi 3 Mini 4k Instruct: 24.5 (#258)
| Benchmark | Grok 4.3 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Math | 1388 | 1111 |
| FrontierMath (Tiers 1-3) | 42.8% | — |
| FrontierMath Tier 4 | 14.6% | — |
| OTIS Mock AIME 2024-2025 | 93.3% | — |
| ProofBench | 11% | — |
| LiveBench Math | — | 15.7% |
Knowledge Grok 4.3 leads
Grok 4.3: 52.5 (#57), Phi 3 Mini 4k Instruct: 27.9 (#241)
| Benchmark | Grok 4.3 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Expert | 1385 | 1045 |
| GPQA Diamond | 88.8% | — |
| SimpleQA Verified | 33.2% | — |
| ARC (AI2) Challenge | — | 84.9% |
| MMLU | — | 68.8% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 64% |
Multimodal Not comparable
Grok 4.3: 31.6 (#96), Phi 3 Mini 4k Instruct: —
| Benchmark | Grok 4.3 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Vision | 1231 | — |
| Blueprint-Bench 2 | 0% | — |
Multilingual Grok 4.3 leads
Grok 4.3: 50.7 (#114), Phi 3 Mini 4k Instruct: 26.5 (#275)
| Benchmark | Grok 4.3 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Non-English | 1385 | 1021 |
| LMArena Chinese | 1423 | 1021 |
| LMArena French | 1412 | 1075 |
| LMArena German | 1395 | 1044 |
| LMArena Japanese | 1379 | 935 |
| LMArena Korean | 1357 | 905 |
| LMArena Russian | 1399 | 1022 |
| LMArena Spanish | 1402 | 1084 |
Instruction Following Grok 4.3 leads
Grok 4.3: 72.3 (#135), Phi 3 Mini 4k Instruct: 48.0 (#298)
| Benchmark | Grok 4.3 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Instruction Following | 1366 | 1053 |
| LiveBench Instruction Following | — | 39.1% |
Long Context Grok 4.3 leads
Grok 4.3: 42.5 (#118), Phi 3 Mini 4k Instruct: 31.7 (#271)
| Benchmark | Grok 4.3 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Longer Query | 1393 | 1044 |
Writing & Preference Grok 4.3 leads
Grok 4.3: 58.6 (#112), Phi 3 Mini 4k Instruct: 27.7 (#295)
| Benchmark | Grok 4.3 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Text | 1397 | 1073 |
| LMArena Creative Writing | 1380 | 1037 |
| LMArena Multi-Turn | 1406 | 1018 |
| EQ-Bench 4 | 1075 | — |
| LiveBench Language | — | 9.2% |
Frequently asked questions
Is Grok 4.3 better than Phi 3 Mini 4k Instruct?
Grok 4.3 is the stronger model overall, scoring 43.6 to 27.4 on the Noometry Index.
Is Grok 4.3 or Phi 3 Mini 4k Instruct better for coding?
Grok 4.3 scores higher on coding benchmarks: 41.3 versus 26.1 in the Noometry coding category.
How many benchmarks do Grok 4.3 and Phi 3 Mini 4k Instruct share?
18 benchmarks have published results for both models. Grok 4.3 has 40 scored results on Noometry and Phi 3 Mini 4k Instruct has 35.