# Claude 2 vs Sonar

> Sonar is the stronger model overall, scoring 37.8 to 24.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-2-vs-sonar
- Last updated: 2026-10-10
- Shared benchmarks: 0

## Summary

- The widest gap is in math, where Sonar leads 31.3 to 8.7.

## Snapshot

| | Claude 2 | Sonar |
|---|---|---|
| Provider | Anthropic | Perplexity |
| Noometry Index | 24.7 | 37.8 |
| Rank | 342 | 184 |
| Context | — | 128K |
| Input $/M | — | $1 |
| Output $/M | — | $1 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude 2: —
- Sonar: 35.1 (#217)

| Benchmark | Claude 2 | Sonar |
|---|---|---|
| LiveBench Coding | — | 35.1% |
| HumanEval+ | 61.6% | — |

## Reasoning

- Claude 2: 20.8 (#213)
- Sonar: 20.3 (#221)

| Benchmark | Claude 2 | Sonar |
|---|---|---|
| LiveBench Reasoning | — | 46.3% |
| DTBench | 51.9% | — |
| LiveBench Data Analysis | — | 37.9% |
| Epoch Capabilities Index | 120.08 | — |
| LiveBench | — | 46.9% |

## Math

- Claude 2: 8.7 (#314)
- Sonar: 31.3 (#197)

| Benchmark | Claude 2 | Sonar |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.5% | — |
| LiveBench Math | — | 41.6% |
| MATH Level 5 | 11.7% | — |

## Knowledge

- Claude 2: 17.0 (#282)
- Sonar: —

| Benchmark | Claude 2 | Sonar |
|---|---|---|
| GPQA Diamond | 34.7% | — |
| MMLU | 78.5% | — |
| TriviaQA | 87.5% | — |

## Instruction Following

- Claude 2: —
- Sonar: 71.5 (#146)

| Benchmark | Claude 2 | Sonar |
|---|---|---|
| LiveBench Instruction Following | — | 76.2% |

## Writing & Preference

- Claude 2: —
- Sonar: 52.6 (#166)

| Benchmark | Claude 2 | Sonar |
|---|---|---|
| LiveBench Language | — | 44.1% |

## FAQ

### Is Claude 2 better than Sonar?

Sonar is the stronger model overall, scoring 37.8 to 24.7 on the Noometry Index.

### How many benchmarks do Claude 2 and Sonar share?

0 benchmarks have published results for both models. Claude 2 has 8 scored results on Noometry and Sonar has 7.