# GPT-5.4 Pro vs GPT-6 Sol

> GPT-5.4 Pro is the stronger model overall, scoring 58.8 to 49.2 on the Noometry Index. GPT-6 Sol costs 17× less per token, which makes it the better buy when GPT-5.4 Pro's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gpt-5-4-pro-vs-gpt-6-sol
- Last updated: 2026-10-10
- Shared benchmarks: 1

## Summary

- They share 1 benchmark with published results for both. GPT-5.4 Pro scores higher in 3 categories and GPT-6 Sol in 1 category; 4 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5.4 Pro leads 72.0 to 35.8.
- GPT-6 Sol is cheaper at $2 / $10 per million input/output tokens, against $30 / $180 for GPT-5.4 Pro.

## Snapshot

| | GPT-5.4 Pro | GPT-6 Sol |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 58.8 | 49.2 |
| Rank | 16 | 46 |
| Context | 1.05M | 1.05M |
| Input $/M | $30 | $2 |
| Output $/M | $180 | $10 |
| Weights | Proprietary | Proprietary |

## Coding

- GPT-5.4 Pro: 42.6 (#89)
- GPT-6 Sol: 59.6 (#11)

| Benchmark | GPT-5.4 Pro | GPT-6 Sol |
|---|---|---|
| DeepSWE | — | 68.8% |
| FrontierCode | — | 49.3% |
| LMArena WebDev | — | 1692 |
| WeirdML | 57.4% | — |
| LMArena Coding | — | 1453 |

## Agentic & Tool Use

- GPT-5.4 Pro: —
- GPT-6 Sol: 33.5 (#49)

| Benchmark | GPT-5.4 Pro | GPT-6 Sol |
|---|---|---|
| GDP.pdf | — | 28% |

## Reasoning

- GPT-5.4 Pro: 71.0 (#10)
- GPT-6 Sol: 49.3 (#34)

| Benchmark | GPT-5.4 Pro | GPT-6 Sol |
|---|---|---|
| ARC-AGI-2 | 83.3% | — |
| SimpleBench | 74.1% | — |
| NYT Connections (extended) | — | 90.1% |
| ARC-AGI-1 | 94.5% | — |
| CritPt | 30% | — |
| Chess Puzzles | 58.6% | — |
| EnigmaEval | 23.8% | — |
| EBR-Bench | — | 53.3% |
| LMArena Hard Prompts | — | 1420 |
| Epoch Capabilities Index | 159.12 | — |

## Math

- GPT-5.4 Pro: 72.0 (#17)
- GPT-6 Sol: 35.8 (#135)

| Benchmark | GPT-5.4 Pro | GPT-6 Sol |
|---|---|---|
| FrontierMath (Tiers 1-3) | 82.5% | — |
| FrontierMath Tier 4 | 58.5% | — |
| LMArena Math | — | 1404 |
| FrontierMath (Feb 2025 set) | 50% | — |
| FrontierMath Tier 4 (v1) | 37.5% | — |

## Knowledge

- GPT-5.4 Pro: 68.3 (#6)
- GPT-6 Sol: 43.0 (#87)

| Benchmark | GPT-5.4 Pro | GPT-6 Sol |
|---|---|---|
| Vectara Hallucination Rate | 8.3% | 6.5% |
| GPQA Diamond | 94.6% | — |
| Humanity's Last Exam | 44.3% | — |
| SimpleQA Verified | 46.3% | — |
| LMArena Expert | — | 1449 |

## Multimodal

- GPT-5.4 Pro: —
- GPT-6 Sol: 47.6 (#9)

| Benchmark | GPT-5.4 Pro | GPT-6 Sol |
|---|---|---|
| Furniture Assembly | — | 58.3% |

## Multilingual

- GPT-5.4 Pro: —
- GPT-6 Sol: 51.0 (#113)

| Benchmark | GPT-5.4 Pro | GPT-6 Sol |
|---|---|---|
| LMArena Non-English | — | 1389 |
| LMArena Chinese | — | 1416 |
| LMArena Russian | — | 1407 |
| LMArena Spanish | — | 1377 |

## Instruction Following

- GPT-5.4 Pro: —
- GPT-6 Sol: 74.4 (#97)

| Benchmark | GPT-5.4 Pro | GPT-6 Sol |
|---|---|---|
| LMArena Instruction Following | — | 1406 |

## Long Context

- GPT-5.4 Pro: —
- GPT-6 Sol: 43.2 (#100)

| Benchmark | GPT-5.4 Pro | GPT-6 Sol |
|---|---|---|
| LMArena Longer Query | — | 1415 |

## Writing & Preference

- GPT-5.4 Pro: —
- GPT-6 Sol: 72.3 (#15)

| Benchmark | GPT-5.4 Pro | GPT-6 Sol |
|---|---|---|
| LMArena Text | — | 1396 |
| LMArena Creative Writing | — | 1392 |
| EQ-Bench Creative Writing | — | 2125 |
| LMArena Multi-Turn | — | 1405 |

## FAQ

### Is GPT-5.4 Pro better than GPT-6 Sol?

GPT-5.4 Pro is the stronger model overall, scoring 58.8 to 49.2 on the Noometry Index. GPT-6 Sol costs 17× less per token, which makes it the better buy when GPT-5.4 Pro's lead doesn't matter for your workload.

### Which is cheaper, GPT-5.4 Pro or GPT-6 Sol?

GPT-6 Sol is cheaper. It lists at $2 per million input tokens and $10 per million output tokens; GPT-5.4 Pro lists at $30 and $180.

### Is GPT-5.4 Pro or GPT-6 Sol better for coding?

GPT-6 Sol scores higher on coding benchmarks: 59.6 versus 42.6 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-6 Sol share?

1 benchmark has published results for both models. GPT-5.4 Pro has 16 scored results on Noometry and GPT-6 Sol has 22.