# o1-mini vs Sonar

> Sonar is the stronger model overall, scoring 37.8 to 33.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/o1-mini-vs-sonar
- Last updated: 2026-10-10
- Shared benchmarks: 7

## Summary

- They share 7 benchmarks with published results for both. o1-mini scores higher in 1 category and Sonar in 4 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Sonar leads 20.3 to 8.9.
- The biggest single-benchmark swing is LiveBench Reasoning: 72.3% for o1-mini and 46.3% for Sonar.

## Snapshot

| | o1-mini | Sonar |
|---|---|---|
| Provider | OpenAI | Perplexity |
| Noometry Index | 33.7 | 37.8 |
| Rank | 230 | 184 |
| Context | — | 128K |
| Input $/M | — | $1 |
| Output $/M | — | $1 |
| Weights | Proprietary | Proprietary |

## Coding

- o1-mini: 35.1 (#218)
- Sonar: 35.1 (#217)

| Benchmark | o1-mini | Sonar |
|---|---|---|
| LiveBench Coding | 48% | 35.1% |
| Aider Polyglot | 32.9% | — |
| WeirdML | 36.3% | — |
| LMArena Coding | 1362 | — |
| HumanEval+ | 89% | — |
| MBPP+ | 78.8% | — |

## Agentic & Tool Use

- o1-mini: 24.3 (#112)
- Sonar: —

| Benchmark | o1-mini | Sonar |
|---|---|---|
| Cybench | 10% | — |

## Reasoning

- o1-mini: 8.9 (#340)
- Sonar: 20.3 (#221)

| Benchmark | o1-mini | Sonar |
|---|---|---|
| LiveBench Reasoning | 72.3% | 46.3% |
| LiveBench Data Analysis | 57.9% | 37.9% |
| LiveBench | 57.8% | 46.9% |
| ARC-AGI-2 | 0.8% | — |
| SimpleBench | 18.1% | — |
| ARC-AGI-1 | 14% | — |
| LMArena Hard Prompts | 1333 | — |
| Epoch Capabilities Index | 135.82 | — |

## Math

- o1-mini: 33.7 (#168)
- Sonar: 31.3 (#197)

| Benchmark | o1-mini | Sonar |
|---|---|---|
| LiveBench Math | 62% | 41.6% |
| OTIS Mock AIME 2024-2025 | 46.9% | — |
| LMArena Math | 1358 | — |
| MATH Level 5 | 89.2% | — |
| FrontierMath (Feb 2025 set) | 1.7% | — |

## Knowledge

- o1-mini: 34.8 (#180)
- Sonar: —

| Benchmark | o1-mini | Sonar |
|---|---|---|
| GPQA Diamond | 62.4% | — |
| Confabulations | 18.6% | — |
| LMArena Expert | 1316 | — |

## Multilingual

- o1-mini: 43.8 (#177)
- Sonar: —

| Benchmark | o1-mini | Sonar |
|---|---|---|
| LMArena Non-English | 1289 | — |
| LMArena Chinese | 1314 | — |
| LMArena French | 1292 | — |
| LMArena German | 1278 | — |
| LMArena Japanese | 1245 | — |
| LMArena Korean | 1223 | — |
| LMArena Russian | 1283 | — |
| LMArena Spanish | 1302 | — |

## Instruction Following

- o1-mini: 67.0 (#200)
- Sonar: 71.5 (#146)

| Benchmark | o1-mini | Sonar |
|---|---|---|
| LiveBench Instruction Following | 65.4% | 76.2% |
| LMArena Instruction Following | 1304 | — |

## Long Context

- o1-mini: 40.1 (#156)
- Sonar: —

| Benchmark | o1-mini | Sonar |
|---|---|---|
| LMArena Longer Query | 1321 | — |

## Writing & Preference

- o1-mini: 48.6 (#196)
- Sonar: 52.6 (#166)

| Benchmark | o1-mini | Sonar |
|---|---|---|
| LiveBench Language | 40.9% | 44.1% |
| LMArena Text | 1317 | — |
| LMArena Creative Writing | 1244 | — |
| Short-Story Creative Writing | 64.9% | — |
| LMArena Multi-Turn | 1314 | — |

## FAQ

### Is o1-mini better than Sonar?

Sonar is the stronger model overall, scoring 37.8 to 33.7 on the Noometry Index.

### Is o1-mini or Sonar better for coding?

They score almost the same on coding (35.1 vs 35.1); test both on your own repository before choosing.

### How many benchmarks do o1-mini and Sonar share?

7 benchmarks have published results for both models. o1-mini has 39 scored results on Noometry and Sonar has 7.