# GPT-5.4 mini vs GPT-5.6 Sol

> GPT-5.6 Sol is the stronger model overall, scoring 64.4 to 44.8 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.

- Canonical page: https://noometry.com/compare/gpt-5-4-mini-vs-gpt-5-6-sol
- Last updated: 2026-10-10
- Shared benchmarks: 41

## 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 74.7 to 30.3.
- 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.

## Snapshot

| | GPT-5.4 mini | GPT-5.6 Sol |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 44.8 | 64.4 |
| Rank | 69 | 6 |
| Context | 400K | 1.05M |
| Input $/M | $0.75 | $4 |
| Output $/M | $4.50 | $20 |
| Weights | Proprietary | Proprietary |

## Coding

- GPT-5.4 mini: 45.0 (#67)
- GPT-5.6 Sol: 61.1 (#7)

| Benchmark | GPT-5.4 mini | GPT-5.6 Sol |
|---|---|---|
| FrontierCode | 27% | 47.5% |
| LMArena WebDev | 1397 | 1619 |
| SciCode | 49.9% | 57.1% |
| WeirdML | 60.3% | 89.4% |
| LMArena Coding | 1438 | 1493 |
| ALE-Bench | 1,189 | 2,177 |
| DeepSWE | — | 72.7% |
| CursorBench | — | 41.7% |
| FrontierSWE | — | 32.2% |
| MirrorCode | — | 20% |

## Agentic & Tool Use

- GPT-5.4 mini: 29.6 (#74)
- GPT-5.6 Sol: 50.2 (#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-5.4 mini: 30.3 (#77)
- GPT-5.6 Sol: 74.7 (#6)

| 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 | 1481 |
| Mystery Game Puzzles | 11% | 58% |
| DTBench | 80% | 96% |
| LMCA | 40.8% | 59.2% |
| Epoch Capabilities Index | 148.83 | 161.99 |
| 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-5.4 mini: 45.4 (#63)
- GPT-5.6 Sol: 85.5 (#7)

| 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 | 1418 | 1472 |
| FrontierMath (Feb 2025 set) | 28.3% | — |
| FrontierMath Erdős | — | 0% |
| FrontierMath Tier 4 (v1) | 2.1% | — |

## Knowledge

- GPT-5.4 mini: 51.4 (#62)
- GPT-5.6 Sol: 64.3 (#16)

| 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 | 1434 | 1517 |

## Multimodal

- GPT-5.4 mini: 39.0 (#51)
- GPT-5.6 Sol: 48.9 (#8)

| 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-5.4 mini: 52.1 (#94)
- GPT-5.6 Sol: 55.4 (#32)

| Benchmark | GPT-5.4 mini | GPT-5.6 Sol |
|---|---|---|
| LMArena Non-English | 1405 | 1450 |
| LMArena Chinese | 1446 | 1523 |
| LMArena French | 1440 | 1475 |
| LMArena German | 1407 | 1476 |
| LMArena Japanese | 1375 | 1475 |
| LMArena Korean | 1369 | 1434 |
| LMArena Russian | 1417 | 1466 |
| LMArena Spanish | 1403 | 1449 |

## Instruction Following

- GPT-5.4 mini: 74.3 (#99)
- GPT-5.6 Sol: 77.8 (#16)

| Benchmark | GPT-5.4 mini | GPT-5.6 Sol |
|---|---|---|
| LMArena Instruction Following | 1405 | 1480 |

## Long Context

- GPT-5.4 mini: 42.9 (#107)
- GPT-5.6 Sol: 45.3 (#42)

| Benchmark | GPT-5.4 mini | GPT-5.6 Sol |
|---|---|---|
| LMArena Longer Query | 1407 | 1479 |

## Writing & Preference

- GPT-5.4 mini: 64.2 (#56)
- GPT-5.6 Sol: 73.5 (#12)

| Benchmark | GPT-5.4 mini | GPT-5.6 Sol |
|---|---|---|
| LMArena Text | 1411 | 1456 |
| LMArena Creative Writing | 1370 | 1450 |
| EQ-Bench Creative Writing | 1665 | 1972 |
| LMArena Multi-Turn | 1429 | 1456 |
| EQ-Bench 4 | — | 1250 |

## FAQ

### Is GPT-5.4 mini better than GPT-5.6 Sol?

GPT-5.6 Sol is the stronger model overall, scoring 64.4 to 44.8 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: 61.1 versus 45.0 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 64.