Model comparison
GPT-5.6 Terra vs Phi 3 Small 8k Instruct
GPT-5.6 Terra is the stronger model overall, scoring 59.2 to 29.3 on the Noometry Index.
Last verified . 17 shared benchmarks.
MicrosoftSummary
- They share 17 benchmarks with published results for both. GPT-5.6 Terra 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 math, where GPT-5.6 Terra leads 81.6 to 27.6.
- Phi 3 Small 8k Instruct has downloadable open weights; the other is API-only.
Side by side
| GPT-5.6 Terra | Phi 3 Small 8k Instruct | |
|---|---|---|
| Provider | OpenAI | Microsoft |
| Noometry Index | 59.2 | 29.3 |
| Released | 2026-07-09 | 2024-04-23 |
| Weights | Proprietary | Open |
| Context window | 1.05M | — |
| Max output | 128K | — |
| Input $ / M tokens | $2 | — |
| Output $ / M tokens | $12 | — |
| Results tracked | 52 | 32 |
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: 57.7 (#19), Phi 3 Small 8k Instruct: 27.9 (#318)
| Benchmark | GPT-5.6 Terra | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Coding | 1484 | 1101 |
| DeepSWE | 69.6% | — |
| FrontierCode | 41.3% | — |
| CursorBench | 41.3% | — |
| LMArena WebDev | 1522 | — |
| SciCode | 55% | — |
| WeirdML | 78.3% | — |
| LiveBench Coding | — | 20.3% |
| ALE-Bench | 1,951 | — |
Agentic & Tool Use Not comparable
GPT-5.6 Terra: 40.1 (#25), Phi 3 Small 8k Instruct: —
| Benchmark | GPT-5.6 Terra | Phi 3 Small 8k Instruct |
|---|---|---|
| APEX-Agents | 58.2% | — |
| BALROG | 53.2% | — |
| GDP.pdf | 24.7% | — |
| Vending-Bench 2 | 7,343 | — |
Reasoning GPT-5.6 Terra leads
GPT-5.6 Terra: 60.7 (#21), Phi 3 Small 8k Instruct: 14.8 (#323)
| Benchmark | GPT-5.6 Terra | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1468 | 1100 |
| 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% | — |
| LiveBench Reasoning | — | 15.9% |
| Mystery Game Puzzles | 35% | — |
| DTBench | 93.3% | — |
| LiveBench Data Analysis | — | 30.3% |
| LMCA | 55% | — |
| Surface Evolver Bench | 83.8% | — |
| Adversarial NLI | — | 58.1% |
| BIG-Bench Hard | — | 79.1% |
| Epoch Capabilities Index | 159.62 | — |
| HellaSwag | — | 77% |
| LiveBench | — | 24% |
| WinoGrande | — | 81.5% |
Math GPT-5.6 Terra leads
GPT-5.6 Terra: 81.6 (#12), Phi 3 Small 8k Instruct: 27.6 (#248)
| Benchmark | GPT-5.6 Terra | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Math | 1466 | 1151 |
| FrontierMath (Tiers 1-3) | 86% | — |
| FrontierMath Tier 4 | 70.7% | — |
| OTIS Mock AIME 2024-2025 | 99.7% | — |
| ProofBench | 74% | — |
| LiveBench Math | — | 17.6% |
Knowledge GPT-5.6 Terra leads
GPT-5.6 Terra: 61.2 (#30), Phi 3 Small 8k Instruct: 29.1 (#240)
| Benchmark | GPT-5.6 Terra | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Expert | 1492 | 1067 |
| GPQA Diamond | 93.3% | — |
| SimpleQA Verified | 43.2% | — |
| ARC (AI2) Challenge | — | 90.7% |
| MMLU | — | 75.7% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 58.1% |
Multimodal Not comparable
GPT-5.6 Terra: 47.3 (#11), Phi 3 Small 8k Instruct: —
| Benchmark | GPT-5.6 Terra | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Vision | 1271 | — |
| Blueprint-Bench 2 | 30.8% | — |
| Furniture Assembly | 54.2% | — |
| LMArena Document | 1472 | — |
Multilingual GPT-5.6 Terra leads
GPT-5.6 Terra: 54.4 (#44), Phi 3 Small 8k Instruct: 28.5 (#272)
| Benchmark | GPT-5.6 Terra | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Non-English | 1439 | 1058 |
| LMArena Chinese | 1513 | 1061 |
| LMArena French | 1471 | 1135 |
| LMArena German | 1460 | 1080 |
| LMArena Japanese | 1457 | 966 |
| LMArena Korean | 1425 | 894 |
| LMArena Russian | 1450 | 1111 |
| LMArena Spanish | 1448 | 1111 |
Instruction Following GPT-5.6 Terra leads
GPT-5.6 Terra: 76.4 (#40), Phi 3 Small 8k Instruct: 51.9 (#292)
| Benchmark | GPT-5.6 Terra | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Instruction Following | 1454 | 1087 |
| LiveBench Instruction Following | — | 47.2% |
Long Context GPT-5.6 Terra leads
GPT-5.6 Terra: 44.4 (#68), Phi 3 Small 8k Instruct: 33.0 (#267)
| Benchmark | GPT-5.6 Terra | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Longer Query | 1451 | 1088 |
Writing & Preference GPT-5.6 Terra leads
GPT-5.6 Terra: 70.2 (#23), Phi 3 Small 8k Instruct: 31.1 (#284)
| Benchmark | GPT-5.6 Terra | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Text | 1447 | 1110 |
| LMArena Creative Writing | 1410 | 1083 |
| LMArena Multi-Turn | 1449 | 1068 |
| EQ-Bench Creative Writing | 1855 | — |
| EQ-Bench 4 | 1234 | — |
| LiveBench Language | — | 12.9% |
Frequently asked questions
Is GPT-5.6 Terra better than Phi 3 Small 8k Instruct?
GPT-5.6 Terra is the stronger model overall, scoring 59.2 to 29.3 on the Noometry Index.
Is GPT-5.6 Terra or Phi 3 Small 8k Instruct better for coding?
GPT-5.6 Terra scores higher on coding benchmarks: 57.7 versus 27.9 in the Noometry coding category.
How many benchmarks do GPT-5.6 Terra and Phi 3 Small 8k Instruct share?
17 benchmarks have published results for both models. GPT-5.6 Terra has 52 scored results on Noometry and Phi 3 Small 8k Instruct has 32.