# GPT-4 vs GPT-6.1 Sol

> GPT-6.1 Sol is the stronger model overall, scoring 65.6 to 29.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-4-vs-gpt-6-1-sol
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. GPT-4 scores higher in 0 categories and GPT-6.1 Sol in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-6.1 Sol leads 93.7 to 10.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 1.1% for GPT-4 and 100% for GPT-6.1 Sol.
- GPT-6.1 Sol is cheaper at $2 / $10 per million input/output tokens, against $30 / $60 for GPT-4.
- GPT-6.1 Sol accepts more context: 1.05M tokens versus 8K.

## Snapshot

| | GPT-4 | GPT-6.1 Sol |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 29.1 | 65.6 |
| Rank | 316 | 6 |
| Context | 8K | 1.05M |
| Input $/M | $30 | $2 |
| Output $/M | $60 | $10 |
| Weights | Proprietary | Proprietary |

## Coding

- GPT-4: 31.6 (#283)
- GPT-6.1 Sol: 63.2 (#8)

| Benchmark | GPT-4 | GPT-6.1 Sol |
|---|---|---|
| LMArena Coding | 1254 | 1487 |
| DeepSWE | — | 75.2% |
| FrontierCode | — | 50.2% |
| LMArena WebDev | — | 1755 |
| SciCode | — | 55.8% |
| WeirdML | 12.4% | — |
| BigCodeBench Instruct | 46% | — |
| BigCodeBench Complete | 57.2% | — |
| HumanEval+ | 79.3% | — |

## Agentic & Tool Use

- GPT-4: —
- GPT-6.1 Sol: 39.6 (#26)

| Benchmark | GPT-4 | GPT-6.1 Sol |
|---|---|---|
| APEX-Agents | — | 60% |
| GDP.pdf | — | 32% |
| METR Time Horizons | 36.1% | — |

## Reasoning

- GPT-4: 17.8 (#289)
- GPT-6.1 Sol: 81.9 (#2)

| Benchmark | GPT-4 | GPT-6.1 Sol |
|---|---|---|
| Chess Puzzles | 4% | 61% |
| LMArena Hard Prompts | 1241 | 1466 |
| Mystery Game Puzzles | 12% | 80% |
| Epoch Capabilities Index | 125.89 | 166.09 |
| ARC-AGI-2 | — | 94.2% |
| NYT Connections (extended) | — | 95.5% |
| ARC-AGI-1 | — | 98.5% |
| CritPt | — | 31.7% |
| EBR-Bench | — | 54.3% |
| DTBench | 62.7% | — |
| LMCA | 17.1% | — |
| BIG-Bench Hard | 75.1% | — |
| ForecastBench | 57.8 | — |
| HellaSwag | 95.3% | — |
| WinoGrande | 87.5% | — |

## Math

- GPT-4: 10.8 (#309)
- GPT-6.1 Sol: 93.7 (#1)

| Benchmark | GPT-4 | GPT-6.1 Sol |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.1% | 100% |
| LMArena Math | 1269 | 1464 |
| FrontierMath (Tiers 1-3) | — | 93.7% |
| FrontierMath Tier 4 | — | 100% |
| ProofBench | — | 99% |
| MATH Level 5 | 23% | — |
| GSM8K | 92% | — |

## Knowledge

- GPT-4: 18.4 (#282)
- GPT-6.1 Sol: 71.8 (#4)

| Benchmark | GPT-4 | GPT-6.1 Sol |
|---|---|---|
| GPQA Diamond | 35.7% | 95.4% |
| LMArena Expert | 1211 | 1502 |
| SimpleQA Verified | — | 73.9% |
| MMLU | 86.4% | — |
| TriviaQA | 84.8% | — |

## Multimodal

- GPT-4: —
- GPT-6.1 Sol: 52.7 (#5)

| Benchmark | GPT-4 | GPT-6.1 Sol |
|---|---|---|
| LMArena Vision | — | 1288 |
| Furniture Assembly | — | 80% |

## Multilingual

- GPT-4: 40.6 (#215)
- GPT-6.1 Sol: 54.3 (#46)

| Benchmark | GPT-4 | GPT-6.1 Sol |
|---|---|---|
| LMArena Non-English | 1246 | 1438 |
| LMArena Chinese | 1242 | 1477 |
| LMArena Russian | 1251 | 1455 |
| LMArena French | 1283 | — |
| LMArena German | 1251 | — |
| LMArena Japanese | 1209 | — |
| LMArena Korean | 1184 | — |
| LMArena Spanish | 1261 | — |

## Instruction Following

- GPT-4: 65.3 (#222)
- GPT-6.1 Sol: 77.0 (#29)

| Benchmark | GPT-4 | GPT-6.1 Sol |
|---|---|---|
| LMArena Instruction Following | 1241 | 1468 |

## Long Context

- GPT-4: 37.7 (#212)
- GPT-6.1 Sol: 44.9 (#54)

| Benchmark | GPT-4 | GPT-6.1 Sol |
|---|---|---|
| LMArena Longer Query | 1244 | 1465 |

## Writing & Preference

- GPT-4: 34.9 (#268)
- GPT-6.1 Sol: 63.6 (#63)

| Benchmark | GPT-4 | GPT-6.1 Sol |
|---|---|---|
| LMArena Text | 1263 | 1447 |
| LMArena Creative Writing | 1244 | 1432 |
| LMArena Multi-Turn | 1257 | 1449 |
| EQ-Bench Creative Writing | 752 | — |

## FAQ

### Is GPT-4 better than GPT-6.1 Sol?

GPT-6.1 Sol is the stronger model overall, scoring 65.6 to 29.1 on the Noometry Index.

### Which is cheaper, GPT-4 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-4 lists at $30 and $60.

### Is GPT-4 or GPT-6.1 Sol better for coding?

GPT-6.1 Sol scores higher on coding benchmarks: 63.2 versus 31.6 in the Noometry coding category.

### Which has the bigger context window?

GPT-6.1 Sol does, with 1.05M tokens against 8K.

### How many benchmarks do GPT-4 and GPT-6.1 Sol share?

17 benchmarks have published results for both models. GPT-4 has 38 scored results on Noometry and GPT-6.1 Sol has 34.