# GPT-5 Pro vs GPT-6.1 Sol

> GPT-6.1 Sol is the stronger model overall, scoring 65.6 to 46.4 on the Noometry Index.

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

## Summary

- They share 5 benchmarks with published results for both. GPT-5 Pro scores higher in 0 categories and GPT-6.1 Sol in 4 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-6.1 Sol leads 93.7 to 48.5.
- The biggest single-benchmark swing is FrontierMath Tier 4: 19.5% for GPT-5 Pro and 100% for GPT-6.1 Sol.
- GPT-6.1 Sol is cheaper at $2 / $10 per million input/output tokens, against $15 / $120 for GPT-5 Pro.
- GPT-6.1 Sol accepts more context: 1.05M tokens versus 400K.

## Snapshot

| | GPT-5 Pro | GPT-6.1 Sol |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 46.4 | 65.6 |
| Rank | 64 | 6 |
| Context | 400K | 1.05M |
| Input $/M | $15 | $2 |
| Output $/M | $120 | $10 |
| Weights | Proprietary | Proprietary |

## Coding

- GPT-5 Pro: 44.0 (#80)
- GPT-6.1 Sol: 63.2 (#8)

| Benchmark | GPT-5 Pro | GPT-6.1 Sol |
|---|---|---|
| DeepSWE | — | 75.2% |
| FrontierCode | — | 50.2% |
| LMArena WebDev | — | 1755 |
| SciCode | — | 55.8% |
| WeirdML | 60.4% | — |
| LMArena Coding | — | 1487 |
| AlgoTune | 1.31 | — |

## Agentic & Tool Use

- GPT-5 Pro: —
- GPT-6.1 Sol: 39.6 (#26)

| Benchmark | GPT-5 Pro | GPT-6.1 Sol |
|---|---|---|
| APEX-Agents | — | 60% |
| GDP.pdf | — | 32% |

## Reasoning

- GPT-5 Pro: 38.9 (#62)
- GPT-6.1 Sol: 81.9 (#2)

| Benchmark | GPT-5 Pro | GPT-6.1 Sol |
|---|---|---|
| ARC-AGI-2 | 18.3% | 94.2% |
| ARC-AGI-1 | 70.2% | 98.5% |
| Epoch Capabilities Index | 150.28 | 166.09 |
| SimpleBench | 61.6% | — |
| Kagi LLM Benchmark | 76.8% | — |
| NYT Connections (extended) | — | 95.5% |
| CritPt | — | 31.7% |
| Chess Puzzles | — | 61% |
| EnigmaEval | 18.8% | — |
| EBR-Bench | — | 54.3% |
| LMArena Hard Prompts | — | 1466 |
| Mystery Game Puzzles | — | 80% |

## Math

- GPT-5 Pro: 48.5 (#63)
- GPT-6.1 Sol: 93.7 (#1)

| Benchmark | GPT-5 Pro | GPT-6.1 Sol |
|---|---|---|
| FrontierMath (Tiers 1-3) | 55.8% | 93.7% |
| FrontierMath Tier 4 | 19.5% | 100% |
| OTIS Mock AIME 2024-2025 | — | 100% |
| ProofBench | — | 99% |
| LMArena Math | — | 1464 |
| FrontierMath Tier 4 (v1) | 14.6% | — |

## Knowledge

- GPT-5 Pro: 56.7 (#42)
- GPT-6.1 Sol: 71.8 (#4)

| Benchmark | GPT-5 Pro | GPT-6.1 Sol |
|---|---|---|
| GPQA Diamond | — | 95.4% |
| Humanity's Last Exam | 31.6% | — |
| SimpleQA Verified | — | 73.9% |
| LMArena Expert | — | 1502 |

## Multimodal

- GPT-5 Pro: —
- GPT-6.1 Sol: 52.7 (#5)

| Benchmark | GPT-5 Pro | GPT-6.1 Sol |
|---|---|---|
| LMArena Vision | — | 1288 |
| Furniture Assembly | — | 80% |

## Multilingual

- GPT-5 Pro: —
- GPT-6.1 Sol: 54.3 (#46)

| Benchmark | GPT-5 Pro | GPT-6.1 Sol |
|---|---|---|
| LMArena Non-English | — | 1438 |
| LMArena Chinese | — | 1477 |
| LMArena Russian | — | 1455 |

## Instruction Following

- GPT-5 Pro: —
- GPT-6.1 Sol: 77.0 (#29)

| Benchmark | GPT-5 Pro | GPT-6.1 Sol |
|---|---|---|
| LMArena Instruction Following | — | 1468 |

## Long Context

- GPT-5 Pro: —
- GPT-6.1 Sol: 44.9 (#54)

| Benchmark | GPT-5 Pro | GPT-6.1 Sol |
|---|---|---|
| LMArena Longer Query | — | 1465 |

## Writing & Preference

- GPT-5 Pro: —
- GPT-6.1 Sol: 63.6 (#63)

| Benchmark | GPT-5 Pro | GPT-6.1 Sol |
|---|---|---|
| LMArena Text | — | 1447 |
| LMArena Creative Writing | — | 1432 |
| LMArena Multi-Turn | — | 1449 |

## FAQ

### Is GPT-5 Pro better than GPT-6.1 Sol?

GPT-6.1 Sol is the stronger model overall, scoring 65.6 to 46.4 on the Noometry Index.

### Which is cheaper, GPT-5 Pro or GPT-6.1 Sol?

GPT-6.1 Sol is cheaper. It lists at $2 per million input tokens and $10 per million output tokens; GPT-5 Pro lists at $15 and $120.

### Is GPT-5 Pro or GPT-6.1 Sol better for coding?

GPT-6.1 Sol scores higher on coding benchmarks: 63.2 versus 44.0 in the Noometry coding category.

### Which has the bigger context window?

GPT-6.1 Sol does, with 1.05M tokens against 400K.

### How many benchmarks do GPT-5 Pro and GPT-6.1 Sol share?

5 benchmarks have published results for both models. GPT-5 Pro has 12 scored results on Noometry and GPT-6.1 Sol has 34.