Model comparison
GPT-5.6 Terra vs Phi-3.5-mini
GPT-5.6 Terra has enough public results to be ranked (#15); Phi-3.5-mini does not yet, so treat this comparison as directional.
Last verified . 0 shared benchmarks.
MicrosoftSummary
- The widest gap is in coding, where GPT-5.6 Terra leads 57.1 to 34.0.
- Phi-3.5-mini has downloadable open weights; the other is API-only.
Side by side
| GPT-5.6 Terra | Phi-3.5-mini | |
|---|---|---|
| Provider | OpenAI | Microsoft |
| Noometry Index | 59.1 | 36.4 |
| Released | 2026-07-09 | 2024-08-16 |
| Weights | Proprietary | Open |
| Context window | 1.05M | — |
| Max output | 128K | — |
| Input $ / M tokens | $2 | — |
| Output $ / M tokens | $12 | — |
| Results tracked | 52 | 5 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.6 Terra leads
GPT-5.6 Terra: 57.1 (#16), Phi-3.5-mini: 34.0 (#231)
| Benchmark | GPT-5.6 Terra | Phi-3.5-mini |
|---|---|---|
| DeepSWE | 69.6% | — |
| FrontierCode | 41.3% | — |
| CursorBench | 41.3% | — |
| LMArena WebDev | 1520 | — |
| SciCode | 55% | — |
| WeirdML | 78.3% | — |
| BigCodeBench Instruct | — | 32.8% |
| LMArena Coding | 1484 | — |
| BigCodeBench Complete | — | 38.5% |
| ALE-Bench | 1,951 | — |
Agentic & Tool Use Not comparable
GPT-5.6 Terra: 40.2 (#23), Phi-3.5-mini: —
| Benchmark | GPT-5.6 Terra | Phi-3.5-mini |
|---|---|---|
| APEX-Agents | 58.2% | — |
| BALROG | 53.2% | — |
| GDP.pdf | 24.7% | — |
| Vending-Bench 2 | 7,343 | — |
Reasoning Not comparable
GPT-5.6 Terra: 60.6 (#19), Phi-3.5-mini: —
| Benchmark | GPT-5.6 Terra | Phi-3.5-mini |
|---|---|---|
| ARC-AGI-2 | 83.9% | — |
| SimpleBench | 48.9% | — |
| Kagi LLM Benchmark | 51.3% | — |
| NYT Connections (extended) | 78.4% | — |
| ARC-AGI-1 | 96.5% | — |
| CritPt | 30% | — |
| Chess Puzzles | 54% | — |
| LMArena Hard Prompts | 1467 | — |
| Mystery Game Puzzles | 35% | — |
| DTBench | 93.3% | — |
| LMCA | 55% | — |
| Surface Evolver Bench | 83.8% | — |
| Epoch Capabilities Index | 159.31 | — |
| PIQA | — | 81% |
Math Not comparable
GPT-5.6 Terra: 81.5 (#10), Phi-3.5-mini: —
| Benchmark | GPT-5.6 Terra | Phi-3.5-mini |
|---|---|---|
| FrontierMath (Tiers 1-3) | 86% | — |
| FrontierMath Tier 4 | 70.7% | — |
| OTIS Mock AIME 2024-2025 | 99.7% | — |
| ProofBench | 74% | — |
| LMArena Math | 1463 | — |
| GSM8K | — | 86.2% |
Knowledge Not comparable
GPT-5.6 Terra: 61.3 (#27), Phi-3.5-mini: —
| Benchmark | GPT-5.6 Terra | Phi-3.5-mini |
|---|---|---|
| GPQA Diamond | 93.3% | — |
| SimpleQA Verified | 43.2% | — |
| LMArena Expert | 1492 | — |
| BoolQ | — | 78% |
Multimodal Not comparable
GPT-5.6 Terra: 47.5 (#10), Phi-3.5-mini: —
| Benchmark | GPT-5.6 Terra | Phi-3.5-mini |
|---|---|---|
| LMArena Vision | 1271 | — |
| Blueprint-Bench 2 | 30.8% | — |
| Furniture Assembly | 54.2% | — |
| LMArena Document | 1472 | — |
Multilingual Not comparable
GPT-5.6 Terra: 54.5 (#42), Phi-3.5-mini: —
| Benchmark | GPT-5.6 Terra | Phi-3.5-mini |
|---|---|---|
| LMArena Non-English | 1439 | — |
| LMArena Chinese | 1514 | — |
| LMArena French | 1476 | — |
| LMArena German | 1462 | — |
| LMArena Japanese | 1446 | — |
| LMArena Korean | 1420 | — |
| LMArena Russian | 1450 | — |
| LMArena Spanish | 1455 | — |
Instruction Following Not comparable
GPT-5.6 Terra: 76.6 (#38), Phi-3.5-mini: —
| Benchmark | GPT-5.6 Terra | Phi-3.5-mini |
|---|---|---|
| LMArena Instruction Following | 1453 | — |
Long Context Not comparable
GPT-5.6 Terra: 44.4 (#64), Phi-3.5-mini: —
| Benchmark | GPT-5.6 Terra | Phi-3.5-mini |
|---|---|---|
| LMArena Longer Query | 1452 | — |
Writing & Preference Not comparable
GPT-5.6 Terra: 70.4 (#21), Phi-3.5-mini: —
| Benchmark | GPT-5.6 Terra | Phi-3.5-mini |
|---|---|---|
| LMArena Text | 1446 | — |
| LMArena Creative Writing | 1411 | — |
| EQ-Bench Creative Writing | 1855 | — |
| EQ-Bench 4 | 1234 | — |
| LMArena Multi-Turn | 1451 | — |
Frequently asked questions
Is GPT-5.6 Terra better than Phi-3.5-mini?
GPT-5.6 Terra has enough public results to be ranked (#15); Phi-3.5-mini does not yet, so treat this comparison as directional.
Is GPT-5.6 Terra or Phi-3.5-mini better for coding?
GPT-5.6 Terra scores higher on coding benchmarks: 57.1 versus 34.0 in the Noometry coding category.
How many benchmarks do GPT-5.6 Terra and Phi-3.5-mini share?
0 benchmarks have published results for both models. GPT-5.6 Terra has 52 scored results on Noometry and Phi-3.5-mini has 5.