Model comparison
Grok 4.20 (Non-Reasoning) vs Phi 3 Small 8k Instruct
Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.5 to 28.8 on the Noometry Index.
Last verified . 17 shared benchmarks.
MicrosoftSummary
- They share 17 benchmarks with published results for both. Grok 4.20 (Non-Reasoning) scores higher in 8 categories and Phi 3 Small 8k Instruct in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.20 (Non-Reasoning) leads 52.2 to 14.2.
- Phi 3 Small 8k Instruct has downloadable open weights; the other is API-only.
Side by side
| Grok 4.20 (Non-Reasoning) | Phi 3 Small 8k Instruct | |
|---|---|---|
| Provider | xAI | Microsoft |
| Noometry Index | 48.5 | 28.8 |
| Released | 2026-02-17 | 2024-04-23 |
| Weights | Proprietary | Open |
| Context window | 1M | — |
| Max output | 30K | — |
| Input $ / M tokens | $1.25 | — |
| Output $ / M tokens | $2.50 | — |
| Results tracked | 46 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 41.8 (#104), Phi 3 Small 8k Instruct: 27.4 (#313)
| Benchmark | Grok 4.20 (Non-Reasoning) | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Coding | 1458 | 1102 |
| LMArena WebDev | 1374 | — |
| WeirdML | 52.3% | — |
| LiveBench Coding | — | 20.3% |
| ALE-Bench | 1,150 | — |
Agentic & Tool Use Not comparable
Grok 4.20 (Non-Reasoning): 34.3 (#43), Phi 3 Small 8k Instruct: —
| Benchmark | Grok 4.20 (Non-Reasoning) | Phi 3 Small 8k Instruct |
|---|---|---|
| Terminal-Bench | 57.3% | — |
| τ²-bench Banking | 18% | — |
| LMArena Search | 1189 | — |
| Vending-Bench 2 | 4,663 | — |
Reasoning Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 52.2 (#30), Phi 3 Small 8k Instruct: 14.2 (#319)
| Benchmark | Grok 4.20 (Non-Reasoning) | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1451 | 1100 |
| ARC-AGI-2 | 65.1% | — |
| Kagi LLM Benchmark | 75% | — |
| NYT Connections (extended) | 85.4% | — |
| ARC-AGI-1 | 89.5% | — |
| Chess Puzzles | 24% | — |
| Thematic Generalization | 63.8% | — |
| LiveBench Reasoning | — | 15.9% |
| DTBench | 90.1% | — |
| LiveBench Data Analysis | — | 30.3% |
| LMCA | 38.7% | — |
| Adversarial NLI | — | 58.1% |
| BIG-Bench Hard | — | 79.1% |
| Epoch Capabilities Index | 152.01 | — |
| ForecastBench | 61.4 | — |
| HellaSwag | — | 77% |
| LiveBench | — | 24% |
| WinoGrande | — | 81.5% |
Math Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 48.0 (#54), Phi 3 Small 8k Instruct: 25.4 (#247)
| Benchmark | Grok 4.20 (Non-Reasoning) | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Math | 1455 | 1151 |
| FrontierMath (Tiers 1-3) | 44.9% | — |
| FrontierMath Tier 4 | 17.1% | — |
| OTIS Mock AIME 2024-2025 | 92.2% | — |
| ProofBench | 14% | — |
| LiveBench Math | — | 17.6% |
Knowledge Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 52.8 (#54), Phi 3 Small 8k Instruct: 28.5 (#237)
| Benchmark | Grok 4.20 (Non-Reasoning) | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Expert | 1440 | 1067 |
| GPQA Diamond | 89.3% | — |
| SimpleQA Verified | 30.2% | — |
| ARC (AI2) Challenge | — | 90.7% |
| MMLU | — | 75.7% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 58.1% |
Multimodal Not comparable
Grok 4.20 (Non-Reasoning): 33.2 (#88), Phi 3 Small 8k Instruct: —
| Benchmark | Grok 4.20 (Non-Reasoning) | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Vision | 1263 | — |
| Blueprint-Bench 2 | 0% | — |
| LMArena Document | 1416 | — |
Multilingual Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 54.7 (#38), Phi 3 Small 8k Instruct: 28.6 (#267)
| Benchmark | Grok 4.20 (Non-Reasoning) | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Non-English | 1440 | 1058 |
| LMArena Chinese | 1481 | 1061 |
| LMArena French | 1477 | 1134 |
| LMArena German | 1463 | 1080 |
| LMArena Japanese | 1450 | 966 |
| LMArena Korean | 1417 | 894 |
| LMArena Russian | 1457 | 1111 |
| LMArena Spanish | 1442 | 1111 |
Instruction Following Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 75.0 (#79), Phi 3 Small 8k Instruct: 52.2 (#287)
| Benchmark | Grok 4.20 (Non-Reasoning) | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Instruction Following | 1420 | 1087 |
| LiveBench Instruction Following | — | 47.2% |
Long Context Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 45.4 (#33), Phi 3 Small 8k Instruct: 33.0 (#262)
| Benchmark | Grok 4.20 (Non-Reasoning) | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Longer Query | 1436 | 1088 |
| CL-bench | 22.2% | — |
| CL-bench Life | 11.9% | — |
Writing & Preference Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 65.9 (#42), Phi 3 Small 8k Instruct: 31.3 (#279)
| Benchmark | Grok 4.20 (Non-Reasoning) | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Text | 1451 | 1110 |
| LMArena Creative Writing | 1439 | 1083 |
| LMArena Multi-Turn | 1456 | 1068 |
| EQ-Bench Creative Writing | 1574 | — |
| LiveBench Language | — | 12.9% |
Frequently asked questions
Is Grok 4.20 (Non-Reasoning) better than Phi 3 Small 8k Instruct?
Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.5 to 28.8 on the Noometry Index.
Is Grok 4.20 (Non-Reasoning) or Phi 3 Small 8k Instruct better for coding?
Grok 4.20 (Non-Reasoning) scores higher on coding benchmarks: 41.8 versus 27.4 in the Noometry coding category.
How many benchmarks do Grok 4.20 (Non-Reasoning) and Phi 3 Small 8k Instruct share?
17 benchmarks have published results for both models. Grok 4.20 (Non-Reasoning) has 46 scored results on Noometry and Phi 3 Small 8k Instruct has 32.