Model comparison
GPT-6 Sol vs Phi 3 Mini 128k Instruct
GPT-6 Sol is the stronger model overall, scoring 61.8 to 29.7 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 128k 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 31.6.
- Phi 3 Mini 128k Instruct has downloadable open weights; the other is API-only.
Side by side
| GPT-6 Sol | Phi 3 Mini 128k Instruct | |
|---|---|---|
| Provider | OpenAI | Microsoft |
| Noometry Index | 61.8 | 29.7 |
| 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 | 19 |
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 128k Instruct: 28.8 (#312)
| Benchmark | GPT-6 Sol | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Coding | 1447 | 1039 |
| DeepSWE | 68.8% | — |
| FrontierCode | 49.3% | — |
| LMArena WebDev | 1688 | — |
| SciCode | 57.6% | — |
| BigCodeBench Instruct | — | 29.6% |
| BigCodeBench Complete | — | 40.6% |
| ALE-Bench | 2,462 | — |
Agentic & Tool Use Not comparable
GPT-6 Sol: 37.2 (#36), Phi 3 Mini 128k Instruct: —
| Benchmark | GPT-6 Sol | Phi 3 Mini 128k 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 128k Instruct: 19.6 (#256)
| Benchmark | GPT-6 Sol | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1418 | 1028 |
| ARC-AGI-2 | 89.6% | — |
| NYT Connections (extended) | 90.1% | — |
| ARC-AGI-1 | 95.5% | — |
| CritPt | 30.9% | — |
| EBR-Bench | 53.3% | — |
| Mystery Game Puzzles | 56% | — |
| DTBench | 97.3% | — |
| LMCA | 59.1% | — |
| Epoch Capabilities Index | 162.72 | — |
Math GPT-6 Sol leads
GPT-6 Sol: 87.2 (#7), Phi 3 Mini 128k Instruct: 31.6 (#222)
| Benchmark | GPT-6 Sol | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Math | 1402 | 1089 |
| FrontierMath (Tiers 1-3) | 89.8% | — |
| FrontierMath Tier 4 | 90% | — |
| OTIS Mock AIME 2024-2025 | 100% | — |
| ProofBench | 83% | — |
Knowledge GPT-6 Sol leads
GPT-6 Sol: 64.8 (#15), Phi 3 Mini 128k Instruct: 26.8 (#254)
| Benchmark | GPT-6 Sol | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Expert | 1439 | 984 |
| GPQA Diamond | 94.3% | — |
| SimpleQA Verified | 60.7% | — |
| Vectara Hallucination Rate | 6.5% | — |
Multimodal Not comparable
GPT-6 Sol: 47.6 (#10), Phi 3 Mini 128k Instruct: —
| Benchmark | GPT-6 Sol | Phi 3 Mini 128k 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 128k Instruct: 25.2 (#285)
| Benchmark | GPT-6 Sol | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Non-English | 1385 | 1000 |
| LMArena Chinese | 1405 | 1016 |
| LMArena French | 1410 | 1039 |
| LMArena German | 1390 | 1006 |
| LMArena Japanese | 1385 | 899 |
| LMArena Korean | 1341 | 856 |
| LMArena Russian | 1401 | 1004 |
| LMArena Spanish | 1384 | 1059 |
Instruction Following GPT-6 Sol leads
GPT-6 Sol: 74.5 (#94), Phi 3 Mini 128k Instruct: 51.8 (#294)
| Benchmark | GPT-6 Sol | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Instruction Following | 1412 | 1023 |
Long Context GPT-6 Sol leads
GPT-6 Sol: 43.1 (#108), Phi 3 Mini 128k Instruct: 30.4 (#289)
| Benchmark | GPT-6 Sol | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Longer Query | 1411 | 996 |
Writing & Preference GPT-6 Sol leads
GPT-6 Sol: 71.9 (#18), Phi 3 Mini 128k Instruct: 27.1 (#301)
| Benchmark | GPT-6 Sol | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Text | 1395 | 1050 |
| LMArena Creative Writing | 1378 | 1024 |
| LMArena Multi-Turn | 1412 | 989 |
| EQ-Bench Creative Writing | 2125 | — |
Frequently asked questions
Is GPT-6 Sol better than Phi 3 Mini 128k Instruct?
GPT-6 Sol is the stronger model overall, scoring 61.8 to 29.7 on the Noometry Index.
Is GPT-6 Sol or Phi 3 Mini 128k Instruct better for coding?
GPT-6 Sol scores higher on coding benchmarks: 60.1 versus 28.8 in the Noometry coding category.
How many benchmarks do GPT-6 Sol and Phi 3 Mini 128k Instruct share?
17 benchmarks have published results for both models. GPT-6 Sol has 45 scored results on Noometry and Phi 3 Mini 128k Instruct has 19.