Model comparison
GPT-5.4 Pro vs GPT-5.6 Terra
GPT-5.4 Pro and GPT-5.6 Terra score almost the same on the Noometry Index (58.9 vs 59.2), so choose on price, context window or the category you care about most.
Last verified . 11 shared benchmarks.
Summary
- They share 11 benchmarks with published results for both. GPT-5.4 Pro scores higher in 2 categories and GPT-5.6 Terra in 2 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in coding, where GPT-5.6 Terra leads 57.7 to 43.2.
- The biggest single-benchmark swing is SimpleBench: 74.1% for GPT-5.4 Pro and 48.9% for GPT-5.6 Terra.
- GPT-5.6 Terra is cheaper at $2 / $12 per million input/output tokens, against $30 / $180 for GPT-5.4 Pro.
Side by side
| GPT-5.4 Pro | GPT-5.6 Terra | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 58.9 | 59.2 |
| Released | 2026-03-05 | 2026-07-09 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 1.05M |
| Max output | 128K | 128K |
| Input $ / M tokens | $30 | $2 |
| Output $ / M tokens | $180 | $12 |
| Results tracked | 16 | 52 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.6 Terra leads
GPT-5.4 Pro: 43.2 (#90), GPT-5.6 Terra: 57.7 (#19)
| Benchmark | GPT-5.4 Pro | GPT-5.6 Terra |
|---|---|---|
| WeirdML | 57.4% | 78.3% |
| DeepSWE | — | 69.6% |
| FrontierCode | — | 41.3% |
| CursorBench | — | 41.3% |
| LMArena WebDev | — | 1522 |
| SciCode | — | 55% |
| LMArena Coding | — | 1484 |
| ALE-Bench | — | 1,951 |
Agentic & Tool Use Not comparable
GPT-5.4 Pro: —, GPT-5.6 Terra: 40.1 (#25)
| Benchmark | GPT-5.4 Pro | GPT-5.6 Terra |
|---|---|---|
| APEX-Agents | — | 58.2% |
| BALROG | — | 53.2% |
| GDP.pdf | — | 24.7% |
| Vending-Bench 2 | — | 7,343 |
Reasoning GPT-5.4 Pro leads
GPT-5.4 Pro: 70.7 (#13), GPT-5.6 Terra: 60.7 (#21)
| Benchmark | GPT-5.4 Pro | GPT-5.6 Terra |
|---|---|---|
| ARC-AGI-2 | 83.3% | 83.9% |
| SimpleBench | 74.1% | 48.9% |
| ARC-AGI-1 | 94.5% | 96.5% |
| CritPt | 30% | 30% |
| Chess Puzzles | 58.6% | 54% |
| Epoch Capabilities Index | 158.93 | 159.62 |
| Kagi LLM Benchmark | — | 51.3% |
| NYT Connections (extended) | — | 78.4% |
| EnigmaEval | 23.8% | — |
| LMArena Hard Prompts | — | 1468 |
| Mystery Game Puzzles | — | 35% |
| DTBench | — | 93.3% |
| LMCA | — | 55% |
| Surface Evolver Bench | — | 83.8% |
Math GPT-5.6 Terra leads
GPT-5.4 Pro: 72.4 (#22), GPT-5.6 Terra: 81.6 (#12)
| Benchmark | GPT-5.4 Pro | GPT-5.6 Terra |
|---|---|---|
| FrontierMath (Tiers 1-3) | 82.5% | 86% |
| FrontierMath Tier 4 | 58.5% | 70.7% |
| OTIS Mock AIME 2024-2025 | — | 99.7% |
| ProofBench | — | 74% |
| LMArena Math | — | 1466 |
| FrontierMath (Feb 2025 set) | 50% | — |
| FrontierMath Tier 4 (v1) | 37.5% | — |
Knowledge GPT-5.4 Pro leads
GPT-5.4 Pro: 68.3 (#7), GPT-5.6 Terra: 61.2 (#30)
| Benchmark | GPT-5.4 Pro | GPT-5.6 Terra |
|---|---|---|
| GPQA Diamond | 94.6% | 93.3% |
| SimpleQA Verified | 46.3% | 43.2% |
| Humanity's Last Exam | 44.3% | — |
| Vectara Hallucination Rate | 8.3% | — |
| LMArena Expert | — | 1492 |
Multimodal Not comparable
GPT-5.4 Pro: —, GPT-5.6 Terra: 47.3 (#11)
| Benchmark | GPT-5.4 Pro | GPT-5.6 Terra |
|---|---|---|
| LMArena Vision | — | 1271 |
| Blueprint-Bench 2 | — | 30.8% |
| Furniture Assembly | — | 54.2% |
| LMArena Document | — | 1472 |
Multilingual Not comparable
GPT-5.4 Pro: —, GPT-5.6 Terra: 54.4 (#44)
| Benchmark | GPT-5.4 Pro | GPT-5.6 Terra |
|---|---|---|
| LMArena Non-English | — | 1439 |
| LMArena Chinese | — | 1513 |
| LMArena French | — | 1471 |
| LMArena German | — | 1460 |
| LMArena Japanese | — | 1457 |
| LMArena Korean | — | 1425 |
| LMArena Russian | — | 1450 |
| LMArena Spanish | — | 1448 |
Instruction Following Not comparable
GPT-5.4 Pro: —, GPT-5.6 Terra: 76.4 (#40)
| Benchmark | GPT-5.4 Pro | GPT-5.6 Terra |
|---|---|---|
| LMArena Instruction Following | — | 1454 |
Long Context Not comparable
GPT-5.4 Pro: —, GPT-5.6 Terra: 44.4 (#68)
| Benchmark | GPT-5.4 Pro | GPT-5.6 Terra |
|---|---|---|
| LMArena Longer Query | — | 1451 |
Writing & Preference Not comparable
GPT-5.4 Pro: —, GPT-5.6 Terra: 70.2 (#23)
| Benchmark | GPT-5.4 Pro | GPT-5.6 Terra |
|---|---|---|
| LMArena Text | — | 1447 |
| LMArena Creative Writing | — | 1410 |
| EQ-Bench Creative Writing | — | 1855 |
| EQ-Bench 4 | — | 1234 |
| LMArena Multi-Turn | — | 1449 |
Frequently asked questions
Is GPT-5.4 Pro better than GPT-5.6 Terra?
GPT-5.4 Pro and GPT-5.6 Terra score almost the same on the Noometry Index (58.9 vs 59.2), so choose on price, context window or the category you care about most.
Which is cheaper, GPT-5.4 Pro or GPT-5.6 Terra?
GPT-5.6 Terra is cheaper. It lists at $2 per million input tokens and $12 per million output tokens; GPT-5.4 Pro lists at $30 and $180.
Is GPT-5.4 Pro or GPT-5.6 Terra better for coding?
GPT-5.6 Terra scores higher on coding benchmarks: 57.7 versus 43.2 in the Noometry coding category.
Which has the bigger context window?
Both accept 1.05M tokens.
How many benchmarks do GPT-5.4 Pro and GPT-5.6 Terra share?
11 benchmarks have published results for both models. GPT-5.4 Pro has 16 scored results on Noometry and GPT-5.6 Terra has 52.