# GPT-6 Sol vs Magistral Small

> GPT-6 Sol is the stronger model overall, scoring 49.2 to 29.9 on the Noometry Index. Magistral Small costs 5.3× less per token, which makes it the better buy when GPT-6 Sol's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gpt-6-sol-vs-magistral-small
- Last updated: 2026-10-10
- Shared benchmarks: 0

## Summary

- The widest gap is in reasoning, where GPT-6 Sol leads 49.3 to 6.9.
- Magistral Small is cheaper at $0.50 / $1.50 per million input/output tokens, against $2 / $10 for GPT-6 Sol.
- GPT-6 Sol accepts more context: 1.05M tokens versus 128K.
- Magistral Small has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-6 Sol | Magistral Small |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 49.2 | 29.9 |
| Rank | 46 | 289 |
| Context | 1.05M | 128K |
| Input $/M | $2 | $0.50 |
| Output $/M | $10 | $1.50 |
| Weights | Proprietary | Open |

## Coding

- GPT-6 Sol: 59.6 (#11)
- Magistral Small: 37.8 (#172)

| Benchmark | GPT-6 Sol | Magistral Small |
|---|---|---|
| DeepSWE | 68.8% | — |
| FrontierCode | 49.3% | — |
| LMArena WebDev | 1692 | — |
| SciCode | — | 35.2% |
| LMArena Coding | 1453 | — |

## Agentic & Tool Use

- GPT-6 Sol: 33.5 (#49)
- Magistral Small: —

| Benchmark | GPT-6 Sol | Magistral Small |
|---|---|---|
| GDP.pdf | 28% | — |

## Reasoning

- GPT-6 Sol: 49.3 (#34)
- Magistral Small: 6.9 (#345)

| Benchmark | GPT-6 Sol | Magistral Small |
|---|---|---|
| ARC-AGI-2 | — | 0% |
| Kagi LLM Benchmark | — | 6.3% |
| NYT Connections (extended) | 90.1% | — |
| ARC-AGI-1 | — | 5% |
| CritPt | — | 0.3% |
| Chess Puzzles | — | 3% |
| EBR-Bench | 53.3% | — |
| LMArena Hard Prompts | 1420 | — |
| DTBench | — | 61.3% |
| Epoch Capabilities Index | — | 133.19 |

## Math

- GPT-6 Sol: 35.8 (#135)
- Magistral Small: 24.9 (#253)

| Benchmark | GPT-6 Sol | Magistral Small |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 30% |
| LMArena Math | 1404 | — |

## Knowledge

- GPT-6 Sol: 43.0 (#87)
- Magistral Small: 30.9 (#215)

| Benchmark | GPT-6 Sol | Magistral Small |
|---|---|---|
| GPQA Diamond | — | 56.1% |
| Vectara Hallucination Rate | 6.5% | — |
| LMArena Expert | 1449 | — |

## Multimodal

- GPT-6 Sol: 47.6 (#9)
- Magistral Small: —

| Benchmark | GPT-6 Sol | Magistral Small |
|---|---|---|
| Furniture Assembly | 58.3% | — |

## Multilingual

- GPT-6 Sol: 51.0 (#113)
- Magistral Small: —

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

## Instruction Following

- GPT-6 Sol: 74.4 (#97)
- Magistral Small: —

| Benchmark | GPT-6 Sol | Magistral Small |
|---|---|---|
| LMArena Instruction Following | 1406 | — |

## Long Context

- GPT-6 Sol: 43.2 (#100)
- Magistral Small: —

| Benchmark | GPT-6 Sol | Magistral Small |
|---|---|---|
| LMArena Longer Query | 1415 | — |

## Writing & Preference

- GPT-6 Sol: 72.3 (#15)
- Magistral Small: —

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

## FAQ

### Is GPT-6 Sol better than Magistral Small?

GPT-6 Sol is the stronger model overall, scoring 49.2 to 29.9 on the Noometry Index. Magistral Small costs 5.3× less per token, which makes it the better buy when GPT-6 Sol's lead doesn't matter for your workload.

### Which is cheaper, GPT-6 Sol or Magistral Small?

Magistral Small is cheaper. It lists at $0.50 per million input tokens and $1.50 per million output tokens; GPT-6 Sol lists at $2 and $10.

### Is GPT-6 Sol or Magistral Small better for coding?

GPT-6 Sol scores higher on coding benchmarks: 59.6 versus 37.8 in the Noometry coding category.

### Which has the bigger context window?

GPT-6 Sol does, with 1.05M tokens against 128K.

### How many benchmarks do GPT-6 Sol and Magistral Small share?

0 benchmarks have published results for both models. GPT-6 Sol has 22 scored results on Noometry and Magistral Small has 10.