Model comparison
GPT-5.6 Sol vs gpt-oss-120b
GPT-5.6 Sol is the stronger model overall, scoring 64.4 to 36.0 on the Noometry Index. gpt-oss-120b costs 114× less per token, which makes it the better buy when GPT-5.6 Sol'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 Sol 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 Sol leads 74.7 to 19.5.
- The biggest single-benchmark swing is Surface Evolver Bench: 93.1% for GPT-5.6 Sol and 25% for gpt-oss-120b.
- gpt-oss-120b is cheaper at $0.037 / $0.17 per million input/output tokens, against $4 / $20 for GPT-5.6 Sol.
- GPT-5.6 Sol 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 Sol | gpt-oss-120b | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 64.4 | 36.0 |
| Released | 2026-07-09 | 2025-08-05 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 131K |
| Max output | 128K | 41K |
| Input $ / M tokens | $4 | $0.037 |
| Output $ / M tokens | $20 | $0.17 |
| Results tracked | 64 | 48 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.6 Sol leads
GPT-5.6 Sol: 61.1 (#7), gpt-oss-120b: 33.2 (#251)
| Benchmark | GPT-5.6 Sol | gpt-oss-120b |
|---|---|---|
| SciCode | 57.1% | 36% |
| WeirdML | 89.4% | 48.2% |
| LMArena Coding | 1493 | 1380 |
| ALE-Bench | 2,177 | 575.62 |
| DeepSWE | 72.7% | — |
| FrontierCode | 47.5% | — |
| SWE-bench Verified (bash only) | — | 26% |
| Aider Polyglot | — | 41.8% |
| CursorBench | 41.7% | — |
| LMArena WebDev | 1619 | — |
| FrontierSWE | 32.2% | — |
| MirrorCode | 20% | — |
| AlgoTune | — | 1.41 |
Agentic & Tool Use GPT-5.6 Sol leads
GPT-5.6 Sol: 50.2 (#7), gpt-oss-120b: 12.1 (#145)
| Benchmark | GPT-5.6 Sol | gpt-oss-120b |
|---|---|---|
| APEX-Agents | 51.4% | 4.4% |
| Vending-Bench 2 | 9,619 | -21.53 |
| Terminal-Bench | — | 18.7% |
| OSWorld 2.0 | 27.3% | — |
| τ²-bench Banking | 46.9% | — |
| PostTrainBench | 36.2% | — |
| BALROG | 60% | — |
| GBAEval | 52.6% | — |
| GDP.pdf | 30.7% | — |
| LMArena Search | 1257 | — |
| METR Time Horizons | — | 56.6% |
Reasoning GPT-5.6 Sol leads
GPT-5.6 Sol: 74.7 (#6), gpt-oss-120b: 19.5 (#236)
| Benchmark | GPT-5.6 Sol | gpt-oss-120b |
|---|---|---|
| SimpleBench | 71.7% | 22.1% |
| Kagi LLM Benchmark | 67% | 58.6% |
| CritPt | 32.3% | 1.1% |
| Chess Puzzles | 64% | 20% |
| LMArena Hard Prompts | 1481 | 1364 |
| Mystery Game Puzzles | 58% | 2% |
| DTBench | 96% | 76.3% |
| LMCA | 59.2% | 22.1% |
| Surface Evolver Bench | 93.1% | 25% |
| Epoch Capabilities Index | 161.99 | 139.94 |
| ARC-AGI-2 | 92.5% | — |
| NYT Connections (extended) | 93.8% | — |
| ARC-AGI-1 | 97.5% | — |
| EnigmaEval | 37.1% | — |
| EBR-Bench | 44.8% | — |
| Bench to the Future 3 | 0.14 | — |
Math GPT-5.6 Sol leads
GPT-5.6 Sol: 85.5 (#7), gpt-oss-120b: 50.6 (#43)
| Benchmark | GPT-5.6 Sol | gpt-oss-120b |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 100% | 88.9% |
| LMArena Math | 1472 | 1388 |
| FrontierMath (Tiers 1-3) | 89.1% | — |
| FrontierMath Tier 4 | 82.9% | — |
| ProofBench | 83% | — |
| Omni-MATH | — | 68.8% |
| FrontierMath Erdős | 0% | — |
Knowledge GPT-5.6 Sol leads
GPT-5.6 Sol: 64.3 (#16), gpt-oss-120b: 42.3 (#89)
| Benchmark | GPT-5.6 Sol | gpt-oss-120b |
|---|---|---|
| GPQA Diamond | 93.5% | 75.8% |
| Vectara Hallucination Rate | 12.4% | 14.2% |
| LMArena Expert | 1517 | 1356 |
| SimpleQA Verified | 69.7% | — |
| MMLU-Pro | — | 79.5% |
| Confabulations | — | 15.7% |
| GPQA (HELM) | — | 68.4% |
Multimodal Not comparable
GPT-5.6 Sol: 48.9 (#8), gpt-oss-120b: —
| Benchmark | GPT-5.6 Sol | gpt-oss-120b |
|---|---|---|
| LMArena Vision | 1281 | — |
| Blueprint-Bench 2 | 33.6% | — |
| Furniture Assembly | 56.7% | — |
| LMArena Document | 1483 | — |
Multilingual GPT-5.6 Sol leads
GPT-5.6 Sol: 55.4 (#32), gpt-oss-120b: 48.2 (#142)
| Benchmark | GPT-5.6 Sol | gpt-oss-120b |
|---|---|---|
| LMArena Non-English | 1450 | 1350 |
| LMArena Chinese | 1523 | 1384 |
| LMArena French | 1475 | 1370 |
| LMArena German | 1476 | 1355 |
| LMArena Japanese | 1475 | 1332 |
| LMArena Korean | 1434 | 1283 |
| LMArena Russian | 1466 | 1343 |
| LMArena Spanish | 1449 | 1388 |
Instruction Following GPT-5.6 Sol leads
GPT-5.6 Sol: 77.8 (#16), gpt-oss-120b: 69.5 (#168)
| Benchmark | GPT-5.6 Sol | gpt-oss-120b |
|---|---|---|
| LMArena Instruction Following | 1480 | 1318 |
| IFEval | — | 83.6% |
Long Context GPT-5.6 Sol leads
GPT-5.6 Sol: 45.3 (#42), gpt-oss-120b: 31.4 (#273)
| Benchmark | GPT-5.6 Sol | gpt-oss-120b |
|---|---|---|
| LMArena Longer Query | 1479 | 1319 |
| Fiction.LiveBench | — | 44.4% |
Writing & Preference GPT-5.6 Sol leads
GPT-5.6 Sol: 73.5 (#12), gpt-oss-120b: 46.7 (#213)
| Benchmark | GPT-5.6 Sol | gpt-oss-120b |
|---|---|---|
| LMArena Text | 1456 | 1366 |
| LMArena Creative Writing | 1450 | 1274 |
| EQ-Bench Creative Writing | 1972 | 961 |
| LMArena Multi-Turn | 1456 | 1340 |
| Short-Story Creative Writing | — | 77.1% |
| WildBench | — | 84.5% |
| EQ-Bench 4 | 1250 | — |
Frequently asked questions
Is GPT-5.6 Sol better than gpt-oss-120b?
GPT-5.6 Sol is the stronger model overall, scoring 64.4 to 36.0 on the Noometry Index. gpt-oss-120b costs 114× less per token, which makes it the better buy when GPT-5.6 Sol's lead doesn't matter for your workload.
Which is cheaper, GPT-5.6 Sol 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 Sol lists at $4 and $20.
Is GPT-5.6 Sol or gpt-oss-120b better for coding?
GPT-5.6 Sol scores higher on coding benchmarks: 61.1 versus 33.2 in the Noometry coding category.
Which has the bigger context window?
GPT-5.6 Sol does, with 1.05M tokens against 131K.
How many benchmarks do GPT-5.6 Sol and gpt-oss-120b share?
35 benchmarks have published results for both models. GPT-5.6 Sol has 64 scored results on Noometry and gpt-oss-120b has 48.