Model comparison
GPT-5.4 mini vs GPT-5.6 Sol
GPT-5.6 Sol is the stronger model overall, scoring 65.0 to 45.0 on the Noometry Index. GPT-5.4 mini costs 4.7× less per token, which makes it the better buy when GPT-5.6 Sol's lead doesn't matter for your workload.
Last verified . 41 shared benchmarks.
Summary
- They share 41 benchmarks with published results for both. GPT-5.4 mini scores higher in 0 categories and GPT-5.6 Sol in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-5.6 Sol leads 74.8 to 30.4.
- The biggest single-benchmark swing is ARC-AGI-2: 18.9% for GPT-5.4 mini and 92.5% for GPT-5.6 Sol.
- GPT-5.4 mini is cheaper at $0.75 / $4.50 per million input/output tokens, against $4 / $20 for GPT-5.6 Sol.
- GPT-5.6 Sol accepts more context: 1.05M tokens versus 400K.
Side by side
| GPT-5.4 mini | GPT-5.6 Sol | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 45.0 | 65.0 |
| Released | 2026-03-17 | 2026-07-09 |
| Weights | Proprietary | Proprietary |
| Context window | 400K | 1.05M |
| Max output | 128K | 128K |
| Input $ / M tokens | $0.75 | $4 |
| Output $ / M tokens | $4.50 | $20 |
| Results tracked | 46 | 65 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.6 Sol leads
GPT-5.4 mini: 45.2 (#72), GPT-5.6 Sol: 65.1 (#7)
| Benchmark | GPT-5.4 mini | GPT-5.6 Sol |
|---|---|---|
| FrontierCode | 27% | 47.5% |
| LMArena WebDev | 1397 | 1618 |
| SciCode | 49.9% | 57.1% |
| WeirdML | 60.3% | 89.4% |
| LMArena Coding | 1438 | 1498 |
| ALE-Bench | 1,189 | 2,177 |
| DeepSWE | — | 72.7% |
| CursorBench | — | 41.7% |
| FrontierSWE | — | 32.2% |
| GSO | — | 76.5% |
| MirrorCode | — | 20% |
Agentic & Tool Use GPT-5.6 Sol leads
GPT-5.4 mini: 29.9 (#81), GPT-5.6 Sol: 50.3 (#7)
| Benchmark | GPT-5.4 mini | GPT-5.6 Sol |
|---|---|---|
| APEX-Agents | — | 51.4% |
| OSWorld 2.0 | — | 27.3% |
| τ²-bench Banking | — | 46.9% |
| DeepResearch Bench | 36.3% | — |
| PostTrainBench | — | 36.2% |
| BALROG | — | 60% |
| GBAEval | — | 52.6% |
| GDP.pdf | — | 30.7% |
| LMArena Search | — | 1257 |
| Vending-Bench 2 | — | 9,619 |
Reasoning GPT-5.6 Sol leads
GPT-5.4 mini: 30.4 (#85), GPT-5.6 Sol: 74.8 (#8)
| Benchmark | GPT-5.4 mini | GPT-5.6 Sol |
|---|---|---|
| ARC-AGI-2 | 18.9% | 92.5% |
| Kagi LLM Benchmark | 37.9% | 67% |
| NYT Connections (extended) | 61.8% | 93.8% |
| ARC-AGI-1 | 63.7% | 97.5% |
| CritPt | 10% | 32.3% |
| Chess Puzzles | 24% | 64% |
| LMArena Hard Prompts | 1424 | 1484 |
| Mystery Game Puzzles | 11% | 58% |
| DTBench | 80% | 96% |
| LMCA | 40.8% | 59.2% |
| Epoch Capabilities Index | 148.84 | 161.66 |
| SimpleBench | — | 71.7% |
| EnigmaEval | — | 37.1% |
| Thematic Generalization | 61.7% | — |
| EBR-Bench | — | 44.8% |
| Surface Evolver Bench | — | 93.1% |
| Bench to the Future 3 | — | 0.14 |
| ForecastBench | 57 | — |
Math GPT-5.6 Sol leads
GPT-5.4 mini: 45.5 (#75), GPT-5.6 Sol: 85.6 (#9)
| Benchmark | GPT-5.4 mini | GPT-5.6 Sol |
|---|---|---|
| FrontierMath (Tiers 1-3) | 51.2% | 89.1% |
| FrontierMath Tier 4 | 9.8% | 82.9% |
| OTIS Mock AIME 2024-2025 | 88.9% | 100% |
| ProofBench | 21% | 83% |
| LMArena Math | 1419 | 1474 |
| FrontierMath (Feb 2025 set) | 28.3% | — |
| FrontierMath Erdős | — | 0% |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge GPT-5.6 Sol leads
GPT-5.4 mini: 51.5 (#67), GPT-5.6 Sol: 64.3 (#18)
| Benchmark | GPT-5.4 mini | GPT-5.6 Sol |
|---|---|---|
| GPQA Diamond | 86.9% | 93.5% |
| SimpleQA Verified | 29.4% | 69.7% |
| Vectara Hallucination Rate | 5.5% | 12.4% |
| LMArena Expert | 1435 | 1516 |
Multimodal GPT-5.6 Sol leads
GPT-5.4 mini: 39.7 (#56), GPT-5.6 Sol: 48.6 (#9)
| Benchmark | GPT-5.4 mini | GPT-5.6 Sol |
|---|---|---|
| LMArena Vision | 1245 | 1281 |
| Blueprint-Bench 2 | — | 33.6% |
| Furniture Assembly | — | 56.7% |
| LMArena Document | — | 1483 |
Multilingual GPT-5.6 Sol leads
GPT-5.4 mini: 51.9 (#96), GPT-5.6 Sol: 55.3 (#32)
| Benchmark | GPT-5.4 mini | GPT-5.6 Sol |
|---|---|---|
| LMArena Non-English | 1405 | 1452 |
| LMArena Chinese | 1446 | 1527 |
| LMArena French | 1440 | 1477 |
| LMArena German | 1409 | 1476 |
| LMArena Japanese | 1374 | 1471 |
| LMArena Korean | 1368 | 1442 |
| LMArena Russian | 1417 | 1468 |
| LMArena Spanish | 1405 | 1441 |
Instruction Following GPT-5.6 Sol leads
GPT-5.4 mini: 74.1 (#102), GPT-5.6 Sol: 77.7 (#16)
| Benchmark | GPT-5.4 mini | GPT-5.6 Sol |
|---|---|---|
| LMArena Instruction Following | 1405 | 1482 |
Long Context GPT-5.6 Sol leads
GPT-5.4 mini: 43.0 (#112), GPT-5.6 Sol: 45.4 (#42)
| Benchmark | GPT-5.4 mini | GPT-5.6 Sol |
|---|---|---|
| LMArena Longer Query | 1407 | 1480 |
Writing & Preference GPT-5.6 Sol leads
GPT-5.4 mini: 64.0 (#58), GPT-5.6 Sol: 73.3 (#12)
| Benchmark | GPT-5.4 mini | GPT-5.6 Sol |
|---|---|---|
| LMArena Text | 1412 | 1457 |
| LMArena Creative Writing | 1370 | 1448 |
| EQ-Bench Creative Writing | 1665 | 1972 |
| LMArena Multi-Turn | 1429 | 1460 |
| EQ-Bench 4 | — | 1250 |
Frequently asked questions
Is GPT-5.4 mini better than GPT-5.6 Sol?
GPT-5.6 Sol is the stronger model overall, scoring 65.0 to 45.0 on the Noometry Index. GPT-5.4 mini costs 4.7× 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-5.4 mini or GPT-5.6 Sol?
GPT-5.4 mini is cheaper. It lists at $0.75 per million input tokens and $4.50 per million output tokens; GPT-5.6 Sol lists at $4 and $20.
Is GPT-5.4 mini or GPT-5.6 Sol better for coding?
GPT-5.6 Sol scores higher on coding benchmarks: 65.1 versus 45.2 in the Noometry coding category.
Which has the bigger context window?
GPT-5.6 Sol does, with 1.05M tokens against 400K.
How many benchmarks do GPT-5.4 mini and GPT-5.6 Sol share?
41 benchmarks have published results for both models. GPT-5.4 mini has 46 scored results on Noometry and GPT-5.6 Sol has 65.