Model comparison
GPT-6 Sol vs Phi 3 Mini 4k Instruct
GPT-6 Sol is the stronger model overall, scoring 61.8 to 27.9 on the Noometry Index.
Last verified . 17 shared benchmarks.
MicrosoftSummary
- They share 17 benchmarks with published results for both. GPT-6 Sol 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 math, where GPT-6 Sol leads 87.2 to 26.6.
- Phi 3 Mini 4k Instruct has downloadable open weights; the other is API-only.
Side by side
| GPT-6 Sol | Phi 3 Mini 4k Instruct | |
|---|---|---|
| Provider | OpenAI | Microsoft |
| Noometry Index | 61.8 | 27.9 |
| Released | 2026-09-22 | 2024-04-23 |
| Weights | Proprietary | Open |
| Context window | 1.05M | — |
| Max output | 128K | — |
| Input $ / M tokens | $2 | — |
| Output $ / M tokens | $10 | — |
| Results tracked | 45 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-6 Sol leads
GPT-6 Sol: 60.1 (#11), Phi 3 Mini 4k Instruct: 26.6 (#323)
| Benchmark | GPT-6 Sol | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Coding | 1447 | 1093 |
| DeepSWE | 68.8% | — |
| FrontierCode | 49.3% | — |
| LMArena WebDev | 1688 | — |
| SciCode | 57.6% | — |
| LiveBench Coding | — | 15.5% |
| ALE-Bench | 2,462 | — |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 54.2% |
Agentic & Tool Use Not comparable
GPT-6 Sol: 37.2 (#36), Phi 3 Mini 4k Instruct: —
| Benchmark | GPT-6 Sol | Phi 3 Mini 4k Instruct |
|---|---|---|
| APEX-Agents | 54.3% | — |
| GDP.pdf | 26.4% | — |
| Vending-Bench 2 | 14,428 | — |
Reasoning GPT-6 Sol leads
GPT-6 Sol: 74.0 (#9), Phi 3 Mini 4k Instruct: 14.1 (#328)
| Benchmark | GPT-6 Sol | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1418 | 1072 |
| ARC-AGI-2 | 89.6% | — |
| NYT Connections (extended) | 90.1% | — |
| ARC-AGI-1 | 95.5% | — |
| CritPt | 30.9% | — |
| Chess Puzzles | — | 0% |
| EBR-Bench | 53.3% | — |
| LiveBench Reasoning | — | 26.8% |
| Mystery Game Puzzles | 56% | — |
| DTBench | 97.3% | — |
| LiveBench Data Analysis | — | 34.7% |
| LMCA | 59.1% | — |
| Adversarial NLI | — | 52.8% |
| BIG-Bench Hard | — | 71.7% |
| Epoch Capabilities Index | 162.72 | — |
| HellaSwag | — | 76.7% |
| LiveBench | — | 22.4% |
| WinoGrande | — | 70.8% |
Math GPT-6 Sol leads
GPT-6 Sol: 87.2 (#7), Phi 3 Mini 4k Instruct: 26.6 (#257)
| Benchmark | GPT-6 Sol | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Math | 1402 | 1111 |
| FrontierMath (Tiers 1-3) | 89.8% | — |
| FrontierMath Tier 4 | 90% | — |
| OTIS Mock AIME 2024-2025 | 100% | — |
| ProofBench | 83% | — |
| LiveBench Math | — | 15.7% |
Knowledge GPT-6 Sol leads
GPT-6 Sol: 64.8 (#15), Phi 3 Mini 4k Instruct: 28.5 (#246)
| Benchmark | GPT-6 Sol | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Expert | 1439 | 1045 |
| GPQA Diamond | 94.3% | — |
| SimpleQA Verified | 60.7% | — |
| Vectara Hallucination Rate | 6.5% | — |
| ARC (AI2) Challenge | — | 84.9% |
| MMLU | — | 68.8% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 64% |
Multimodal Not comparable
GPT-6 Sol: 47.6 (#10), Phi 3 Mini 4k Instruct: —
| Benchmark | GPT-6 Sol | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Vision | 1245 | — |
| Blueprint-Bench 2 | 36.9% | — |
| Furniture Assembly | 58.3% | — |
Multilingual GPT-6 Sol leads
GPT-6 Sol: 50.5 (#118), Phi 3 Mini 4k Instruct: 26.3 (#280)
| Benchmark | GPT-6 Sol | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Non-English | 1385 | 1021 |
| LMArena Chinese | 1405 | 1021 |
| LMArena French | 1410 | 1076 |
| LMArena German | 1390 | 1044 |
| LMArena Japanese | 1385 | 935 |
| LMArena Korean | 1341 | 905 |
| LMArena Russian | 1401 | 1022 |
| LMArena Spanish | 1384 | 1085 |
Instruction Following GPT-6 Sol leads
GPT-6 Sol: 74.5 (#94), Phi 3 Mini 4k Instruct: 47.7 (#303)
| Benchmark | GPT-6 Sol | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Instruction Following | 1412 | 1053 |
| LiveBench Instruction Following | — | 39.1% |
Long Context GPT-6 Sol leads
GPT-6 Sol: 43.1 (#108), Phi 3 Mini 4k Instruct: 31.7 (#276)
| Benchmark | GPT-6 Sol | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Longer Query | 1411 | 1044 |
Writing & Preference GPT-6 Sol leads
GPT-6 Sol: 71.9 (#18), Phi 3 Mini 4k Instruct: 27.6 (#300)
| Benchmark | GPT-6 Sol | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Text | 1395 | 1073 |
| LMArena Creative Writing | 1378 | 1037 |
| LMArena Multi-Turn | 1412 | 1018 |
| EQ-Bench Creative Writing | 2125 | — |
| LiveBench Language | — | 9.2% |
Frequently asked questions
Is GPT-6 Sol better than Phi 3 Mini 4k Instruct?
GPT-6 Sol is the stronger model overall, scoring 61.8 to 27.9 on the Noometry Index.
Is GPT-6 Sol or Phi 3 Mini 4k Instruct better for coding?
GPT-6 Sol scores higher on coding benchmarks: 60.1 versus 26.6 in the Noometry coding category.
How many benchmarks do GPT-6 Sol and Phi 3 Mini 4k Instruct share?
17 benchmarks have published results for both models. GPT-6 Sol has 45 scored results on Noometry and Phi 3 Mini 4k Instruct has 35.