# Claude 3 Haiku vs Sonar

> Sonar is the stronger model overall, scoring 37.8 to 25.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-3-haiku-vs-sonar
- Last updated: 2026-10-10
- Shared benchmarks: 0

## Summary

- The widest gap is in writing & preference, where Sonar leads 52.6 to 29.8.

## Snapshot

| | Claude 3 Haiku | Sonar |
|---|---|---|
| Provider | Anthropic | Perplexity |
| Noometry Index | 25.7 | 37.8 |
| Rank | 333 | 184 |
| Context | — | 128K |
| Input $/M | — | $1 |
| Output $/M | — | $1 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude 3 Haiku: 26.1 (#320)
- Sonar: 35.1 (#217)

| Benchmark | Claude 3 Haiku | Sonar |
|---|---|---|
| WeirdML | 9.8% | — |
| BigCodeBench Instruct | 39.4% | — |
| LiveBench Coding | — | 35.1% |
| LMArena Coding | 1199 | — |
| BigCodeBench Complete | 50.1% | — |
| CadEval | 12% | — |
| HumanEval+ | 68.9% | — |
| MBPP+ | 68.8% | — |

## Reasoning

- Claude 3 Haiku: 15.7 (#303)
- Sonar: 20.3 (#221)

| Benchmark | Claude 3 Haiku | Sonar |
|---|---|---|
| Kagi LLM Benchmark | 34.2% | — |
| LiveBench Reasoning | — | 46.3% |
| LMArena Hard Prompts | 1174 | — |
| DTBench | 50.1% | — |
| LiveBench Data Analysis | — | 37.9% |
| LMCA | 8.8% | — |
| Epoch Capabilities Index | 118.3 | — |
| ForecastBench | 53.2 | — |
| LiveBench | — | 46.9% |
| WinoGrande | 74.2% | — |

## Math

- Claude 3 Haiku: 9.2 (#313)
- Sonar: 31.3 (#197)

| Benchmark | Claude 3 Haiku | Sonar |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.8% | — |
| LiveBench Math | — | 41.6% |
| LMArena Math | 1188 | — |
| MATH Level 5 | 14.9% | — |

## Knowledge

- Claude 3 Haiku: 17.3 (#280)
- Sonar: —

| Benchmark | Claude 3 Haiku | Sonar |
|---|---|---|
| GPQA Diamond | 36.3% | — |
| Confabulations | 34.2% | — |
| LMArena Expert | 1148 | — |
| MMLU | 73.8% | — |

## Multimodal

- Claude 3 Haiku: 23.1 (#123)
- Sonar: —

| Benchmark | Claude 3 Haiku | Sonar |
|---|---|---|
| LMArena Vision | 950 | — |
| ScienceQA | 72% | — |

## Multilingual

- Claude 3 Haiku: 36.1 (#238)
- Sonar: —

| Benchmark | Claude 3 Haiku | Sonar |
|---|---|---|
| LMArena Non-English | 1178 | — |
| LMArena Chinese | 1155 | — |
| LMArena French | 1194 | — |
| LMArena German | 1174 | — |
| LMArena Japanese | 1102 | — |
| LMArena Korean | 1108 | — |
| LMArena Russian | 1204 | — |
| LMArena Spanish | 1165 | — |

## Instruction Following

- Claude 3 Haiku: 61.5 (#242)
- Sonar: 71.5 (#146)

| Benchmark | Claude 3 Haiku | Sonar |
|---|---|---|
| LiveBench Instruction Following | — | 76.2% |
| LMArena Instruction Following | 1174 | — |

## Long Context

- Claude 3 Haiku: 36.1 (#232)
- Sonar: —

| Benchmark | Claude 3 Haiku | Sonar |
|---|---|---|
| LMArena Longer Query | 1191 | — |

## Writing & Preference

- Claude 3 Haiku: 29.8 (#286)
- Sonar: 52.6 (#166)

| Benchmark | Claude 3 Haiku | Sonar |
|---|---|---|
| LMArena Text | 1195 | — |
| LMArena Creative Writing | 1157 | — |
| EQ-Bench Creative Writing | 717 | — |
| LMArena Multi-Turn | 1190 | — |
| LiveBench Language | — | 44.1% |

## FAQ

### Is Claude 3 Haiku better than Sonar?

Sonar is the stronger model overall, scoring 37.8 to 25.7 on the Noometry Index.

### Is Claude 3 Haiku or Sonar better for coding?

Sonar scores higher on coding benchmarks: 35.1 versus 26.1 in the Noometry coding category.

### How many benchmarks do Claude 3 Haiku and Sonar share?

0 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and Sonar has 7.