Model comparison
GPT-5.6 Terra vs gpt-oss-120b
GPT-5.6 Terra is the stronger model overall, scoring 59.2 to 36.3 on the Noometry Index. gpt-oss-120b costs 64× less per token, which makes it the better buy when GPT-5.6 Terra's lead doesn't matter for your workload.
Last verified . 34 shared benchmarks.
Summary
- They share 34 benchmarks with published results for both. GPT-5.6 Terra scores higher in 9 categories and gpt-oss-120b in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-5.6 Terra leads 60.7 to 20.0.
- The biggest single-benchmark swing is Surface Evolver Bench: 83.8% for GPT-5.6 Terra and 25% for gpt-oss-120b.
- gpt-oss-120b is cheaper at $0.037 / $0.17 per million input/output tokens, against $2 / $12 for GPT-5.6 Terra.
- GPT-5.6 Terra accepts more context: 1.05M tokens versus 131K.
- gpt-oss-120b has downloadable open weights; the other is API-only.
Side by side
| GPT-5.6 Terra | gpt-oss-120b | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 59.2 | 36.3 |
| Released | 2026-07-09 | 2025-08-05 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 131K |
| Max output | 128K | 41K |
| Input $ / M tokens | $2 | $0.037 |
| Output $ / M tokens | $12 | $0.17 |
| Results tracked | 52 | 48 |
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), gpt-oss-120b: 33.5 (#256)
| Benchmark | GPT-5.6 Terra | gpt-oss-120b |
|---|---|---|
| SciCode | 55% | 36% |
| WeirdML | 78.3% | 48.2% |
| LMArena Coding | 1484 | 1380 |
| ALE-Bench | 1,951 | 575.62 |
| DeepSWE | 69.6% | — |
| FrontierCode | 41.3% | — |
| SWE-bench Verified (bash only) | — | 26% |
| Aider Polyglot | — | 41.8% |
| CursorBench | 41.3% | — |
| LMArena WebDev | 1522 | — |
| AlgoTune | — | 1.41 |
Agentic & Tool Use GPT-5.6 Terra leads
GPT-5.6 Terra: 40.1 (#25), gpt-oss-120b: 12.2 (#153)
| Benchmark | GPT-5.6 Terra | gpt-oss-120b |
|---|---|---|
| APEX-Agents | 58.2% | 4.4% |
| Vending-Bench 2 | 7,343 | -21.53 |
| Terminal-Bench | — | 18.7% |
| BALROG | 53.2% | — |
| GDP.pdf | 24.7% | — |
| METR Time Horizons | — | 56.6% |
Reasoning GPT-5.6 Terra leads
GPT-5.6 Terra: 60.7 (#21), gpt-oss-120b: 20.0 (#245)
| Benchmark | GPT-5.6 Terra | gpt-oss-120b |
|---|---|---|
| SimpleBench | 48.9% | 22.1% |
| Kagi LLM Benchmark | 51.3% | 58.6% |
| CritPt | 30% | 1.1% |
| Chess Puzzles | 54% | 20% |
| LMArena Hard Prompts | 1468 | 1364 |
| Mystery Game Puzzles | 35% | 2% |
| DTBench | 93.3% | 76.3% |
| LMCA | 55% | 22.1% |
| Surface Evolver Bench | 83.8% | 25% |
| Epoch Capabilities Index | 159.62 | 139.93 |
| ARC-AGI-2 | 83.9% | — |
| NYT Connections (extended) | 78.4% | — |
| ARC-AGI-1 | 96.5% | — |
Math GPT-5.6 Terra leads
GPT-5.6 Terra: 81.6 (#12), gpt-oss-120b: 52.5 (#50)
| Benchmark | GPT-5.6 Terra | gpt-oss-120b |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 99.7% | 88.9% |
| LMArena Math | 1466 | 1389 |
| FrontierMath (Tiers 1-3) | 86% | — |
| FrontierMath Tier 4 | 70.7% | — |
| ProofBench | 74% | — |
| Omni-MATH | — | 68.8% |
Knowledge GPT-5.6 Terra leads
GPT-5.6 Terra: 61.2 (#30), gpt-oss-120b: 42.4 (#96)
| Benchmark | GPT-5.6 Terra | gpt-oss-120b |
|---|---|---|
| GPQA Diamond | 93.3% | 75.8% |
| LMArena Expert | 1492 | 1356 |
| SimpleQA Verified | 43.2% | — |
| MMLU-Pro | — | 79.5% |
| Confabulations | — | 15.7% |
| Vectara Hallucination Rate | — | 14.2% |
| GPQA (HELM) | — | 68.4% |
Multimodal Not comparable
GPT-5.6 Terra: 47.3 (#11), gpt-oss-120b: —
| Benchmark | GPT-5.6 Terra | gpt-oss-120b |
|---|---|---|
| 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), gpt-oss-120b: 48.0 (#147)
| Benchmark | GPT-5.6 Terra | gpt-oss-120b |
|---|---|---|
| LMArena Non-English | 1439 | 1351 |
| LMArena Chinese | 1513 | 1385 |
| LMArena French | 1471 | 1369 |
| LMArena German | 1460 | 1353 |
| LMArena Japanese | 1457 | 1331 |
| LMArena Korean | 1425 | 1282 |
| LMArena Russian | 1450 | 1343 |
| LMArena Spanish | 1448 | 1389 |
Instruction Following GPT-5.6 Terra leads
GPT-5.6 Terra: 76.4 (#40), gpt-oss-120b: 69.3 (#173)
| Benchmark | GPT-5.6 Terra | gpt-oss-120b |
|---|---|---|
| LMArena Instruction Following | 1454 | 1318 |
| IFEval | — | 83.6% |
Long Context GPT-5.6 Terra leads
GPT-5.6 Terra: 44.4 (#68), gpt-oss-120b: 31.4 (#278)
| Benchmark | GPT-5.6 Terra | gpt-oss-120b |
|---|---|---|
| LMArena Longer Query | 1451 | 1319 |
| Fiction.LiveBench | — | 44.4% |
Writing & Preference GPT-5.6 Terra leads
GPT-5.6 Terra: 70.2 (#23), gpt-oss-120b: 46.5 (#217)
| Benchmark | GPT-5.6 Terra | gpt-oss-120b |
|---|---|---|
| LMArena Text | 1447 | 1365 |
| LMArena Creative Writing | 1410 | 1275 |
| EQ-Bench Creative Writing | 1855 | 961 |
| LMArena Multi-Turn | 1449 | 1340 |
| Short-Story Creative Writing | — | 77.1% |
| WildBench | — | 84.5% |
| EQ-Bench 4 | 1234 | — |
Frequently asked questions
Is GPT-5.6 Terra better than gpt-oss-120b?
GPT-5.6 Terra is the stronger model overall, scoring 59.2 to 36.3 on the Noometry Index. gpt-oss-120b costs 64× 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 gpt-oss-120b?
gpt-oss-120b is cheaper. It lists at $0.037 per million input tokens and $0.17 per million output tokens; GPT-5.6 Terra lists at $2 and $12.
Is GPT-5.6 Terra or gpt-oss-120b better for coding?
GPT-5.6 Terra scores higher on coding benchmarks: 57.7 versus 33.5 in the Noometry coding category.
Which has the bigger context window?
GPT-5.6 Terra does, with 1.05M tokens against 131K.
How many benchmarks do GPT-5.6 Terra and gpt-oss-120b share?
34 benchmarks have published results for both models. GPT-5.6 Terra has 52 scored results on Noometry and gpt-oss-120b has 48.