Model comparison
GPT-5.6 Terra vs o4-mini
GPT-5.6 Terra is the stronger model overall, scoring 59.2 to 41.6 on the Noometry Index. o4-mini costs 2.3× less per token, which makes it the better buy when GPT-5.6 Terra's lead doesn't matter for your workload.
Last verified . 35 shared benchmarks.
Summary
- They share 35 benchmarks with published results for both. GPT-5.6 Terra scores higher in 9 categories and o4-mini in 1 category; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5.6 Terra leads 81.6 to 40.8.
- The biggest single-benchmark swing is ARC-AGI-2: 83.9% for GPT-5.6 Terra and 6.1% for o4-mini.
- o4-mini is cheaper at $1.10 / $4.40 per million input/output tokens, against $2 / $12 for GPT-5.6 Terra.
- GPT-5.6 Terra accepts more context: 1.05M tokens versus 200K.
Side by side
| GPT-5.6 Terra | o4-mini | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 59.2 | 41.6 |
| Released | 2026-07-09 | 2025-04-16 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 200K |
| Max output | 128K | 100K |
| Input $ / M tokens | $2 | $1.10 |
| Output $ / M tokens | $12 | $4.40 |
| Results tracked | 52 | 60 |
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), o4-mini: 40.9 (#127)
| Benchmark | GPT-5.6 Terra | o4-mini |
|---|---|---|
| WeirdML | 78.3% | 52.6% |
| LMArena Coding | 1484 | 1368 |
| ALE-Bench | 1,951 | 826.17 |
| DeepSWE | 69.6% | — |
| FrontierCode | 41.3% | — |
| SWE-bench Verified (bash only) | — | 45% |
| Aider Polyglot | — | 72% |
| CursorBench | 41.3% | — |
| LMArena WebDev | 1522 | — |
| SciCode | 55% | — |
| GSO | — | 3.6% |
| CadEval | — | 62% |
| AlgoTune | — | 1.72 |
Agentic & Tool Use GPT-5.6 Terra leads
GPT-5.6 Terra: 40.1 (#25), o4-mini: 32.6 (#61)
| Benchmark | GPT-5.6 Terra | o4-mini |
|---|---|---|
| APEX-Agents | 58.2% | — |
| Berkeley Function Calling Leaderboard | — | 53.2% |
| GDPval | — | 25.3% |
| BALROG | 53.2% | — |
| GDP.pdf | 24.7% | — |
| METR Time Horizons | — | 63.9% |
| Vending-Bench 2 | 7,343 | — |
Reasoning GPT-5.6 Terra leads
GPT-5.6 Terra: 60.7 (#21), o4-mini: 24.6 (#162)
| Benchmark | GPT-5.6 Terra | o4-mini |
|---|---|---|
| ARC-AGI-2 | 83.9% | 6.1% |
| SimpleBench | 48.9% | 38.7% |
| Kagi LLM Benchmark | 51.3% | 67.6% |
| ARC-AGI-1 | 96.5% | 58.7% |
| CritPt | 30% | 0.6% |
| Chess Puzzles | 54% | 26% |
| LMArena Hard Prompts | 1468 | 1351 |
| Mystery Game Puzzles | 35% | 5% |
| DTBench | 93.3% | 77.6% |
| LMCA | 55% | 26.5% |
| Epoch Capabilities Index | 159.62 | 145.64 |
| NYT Connections (extended) | 78.4% | — |
| EnigmaEval | — | 9.2% |
| Surface Evolver Bench | 83.8% | — |
| ForecastBench | — | 61.8 |
Math GPT-5.6 Terra leads
GPT-5.6 Terra: 81.6 (#12), o4-mini: 40.8 (#89)
| Benchmark | GPT-5.6 Terra | o4-mini |
|---|---|---|
| FrontierMath (Tiers 1-3) | 86% | 36.1% |
| FrontierMath Tier 4 | 70.7% | 4.9% |
| OTIS Mock AIME 2024-2025 | 99.7% | 81.7% |
| LMArena Math | 1466 | 1389 |
| ProofBench | 74% | — |
| Omni-MATH | — | 72% |
| MATH Level 5 | — | 97.8% |
| FrontierMath (Feb 2025 set) | — | 24.8% |
| FrontierMath Tier 4 (v1) | — | 6.3% |
Knowledge GPT-5.6 Terra leads
GPT-5.6 Terra: 61.2 (#30), o4-mini: 43.6 (#91)
| Benchmark | GPT-5.6 Terra | o4-mini |
|---|---|---|
| GPQA Diamond | 93.3% | 79.6% |
| SimpleQA Verified | 43.2% | 19.6% |
| LMArena Expert | 1492 | 1343 |
| Humanity's Last Exam | — | 18.1% |
| MMLU-Pro | — | 82% |
| Confabulations | — | 15.8% |
| Vectara Hallucination Rate | — | 18.6% |
| GPQA (HELM) | — | 73.5% |
Multimodal GPT-5.6 Terra leads
GPT-5.6 Terra: 47.3 (#11), o4-mini: 40.2 (#49)
| Benchmark | GPT-5.6 Terra | o4-mini |
|---|---|---|
| LMArena Vision | 1271 | 1194 |
| GeoBench | — | 64% |
| VPCT | — | 57.5% |
| 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), o4-mini: 47.0 (#154)
| Benchmark | GPT-5.6 Terra | o4-mini |
|---|---|---|
| LMArena Non-English | 1439 | 1337 |
| LMArena Chinese | 1513 | 1354 |
| LMArena French | 1471 | 1364 |
| LMArena German | 1460 | 1336 |
| LMArena Japanese | 1457 | 1308 |
| LMArena Korean | 1425 | 1312 |
| LMArena Russian | 1450 | 1334 |
| LMArena Spanish | 1448 | 1347 |
Instruction Following GPT-5.6 Terra leads
GPT-5.6 Terra: 76.4 (#40), o4-mini: 75.2 (#68)
| Benchmark | GPT-5.6 Terra | o4-mini |
|---|---|---|
| LMArena Instruction Following | 1454 | 1321 |
| IFEval | — | 92.8% |
Long Context o4-mini leads
GPT-5.6 Terra: 44.4 (#68), o4-mini: 45.5 (#33)
| Benchmark | GPT-5.6 Terra | o4-mini |
|---|---|---|
| LMArena Longer Query | 1451 | 1315 |
| Fiction.LiveBench | — | 77.8% |
Writing & Preference GPT-5.6 Terra leads
GPT-5.6 Terra: 70.2 (#23), o4-mini: 54.0 (#152)
| Benchmark | GPT-5.6 Terra | o4-mini |
|---|---|---|
| LMArena Text | 1447 | 1353 |
| LMArena Creative Writing | 1410 | 1294 |
| LMArena Multi-Turn | 1449 | 1350 |
| Short-Story Creative Writing | — | 75% |
| EQ-Bench Creative Writing | 1855 | — |
| WildBench | — | 85.4% |
| EQ-Bench 4 | 1234 | — |
Frequently asked questions
Is GPT-5.6 Terra better than o4-mini?
GPT-5.6 Terra is the stronger model overall, scoring 59.2 to 41.6 on the Noometry Index. o4-mini costs 2.3× less per token, which makes it the better buy when GPT-5.6 Terra's lead doesn't matter for your workload.
Which is cheaper, GPT-5.6 Terra or o4-mini?
o4-mini is cheaper. It lists at $1.10 per million input tokens and $4.40 per million output tokens; GPT-5.6 Terra lists at $2 and $12.
Is GPT-5.6 Terra or o4-mini better for coding?
GPT-5.6 Terra scores higher on coding benchmarks: 57.7 versus 40.9 in the Noometry coding category.
Which has the bigger context window?
GPT-5.6 Terra does, with 1.05M tokens against 200K.
How many benchmarks do GPT-5.6 Terra and o4-mini share?
35 benchmarks have published results for both models. GPT-5.6 Terra has 52 scored results on Noometry and o4-mini has 60.