# Claude 3 Haiku vs Claude Sonnet 5

> Claude Sonnet 5 is the stronger model overall, scoring 54.5 to 25.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-3-haiku-vs-claude-sonnet-5
- Last updated: 2026-10-10
- Shared benchmarks: 26

## Summary

- They share 26 benchmarks with published results for both. Claude 3 Haiku scores higher in 0 categories and Claude Sonnet 5 in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Sonnet 5 leads 66.1 to 9.2.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 1.8% for Claude 3 Haiku and 94.7% for Claude Sonnet 5.

## Snapshot

| | Claude 3 Haiku | Claude Sonnet 5 |
|---|---|---|
| Provider | Anthropic | Anthropic |
| Noometry Index | 25.7 | 54.5 |
| Rank | 333 | 26 |
| Context | — | 1M |
| Input $/M | — | $2 |
| Output $/M | — | $10 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude 3 Haiku: 26.1 (#320)
- Claude Sonnet 5: 55.5 (#20)

| Benchmark | Claude 3 Haiku | Claude Sonnet 5 |
|---|---|---|
| WeirdML | 9.8% | 68.8% |
| LMArena Coding | 1199 | 1483 |
| DeepSWE | — | 53.8% |
| FrontierCode | — | 42.7% |
| CursorBench | — | 34.1% |
| LMArena WebDev | — | 1540 |
| SciCode | — | 53.6% |
| GSO | — | 37.3% |
| BigCodeBench Instruct | 39.4% | — |
| BigCodeBench Complete | 50.1% | — |
| CadEval | 12% | — |
| ALE-Bench | — | 1,463 |
| HumanEval+ | 68.9% | — |
| MBPP+ | 68.8% | — |

## Agentic & Tool Use

- Claude 3 Haiku: —
- Claude Sonnet 5: 42.7 (#16)

| Benchmark | Claude 3 Haiku | Claude Sonnet 5 |
|---|---|---|
| APEX-Agents | — | 54.5% |
| GBAEval | — | 65.3% |
| LMArena Search | — | 1194 |
| Vending-Bench 2 | — | 6,378 |

## Reasoning

- Claude 3 Haiku: 15.7 (#303)
- Claude Sonnet 5: 48.2 (#37)

| Benchmark | Claude 3 Haiku | Claude Sonnet 5 |
|---|---|---|
| LMArena Hard Prompts | 1174 | 1461 |
| DTBench | 50.1% | 92.5% |
| LMCA | 8.8% | 50% |
| Epoch Capabilities Index | 118.3 | 156.34 |
| ForecastBench | 53.2 | 61.1 |
| SimpleBench | — | 60.6% |
| Kagi LLM Benchmark | 34.2% | — |
| NYT Connections (extended) | — | 75.1% |
| CritPt | — | 16.9% |
| Chess Puzzles | — | 35% |
| Mystery Game Puzzles | — | 35% |
| Surface Evolver Bench | — | 60% |
| Bench to the Future 3 | — | 0.14 |
| WinoGrande | 74.2% | — |

## Math

- Claude 3 Haiku: 9.2 (#313)
- Claude Sonnet 5: 66.1 (#21)

| Benchmark | Claude 3 Haiku | Claude Sonnet 5 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.8% | 94.7% |
| LMArena Math | 1188 | 1467 |
| FrontierMath (Tiers 1-3) | — | 65.6% |
| FrontierMath Tier 4 | — | 29.3% |
| ProofBench | — | 77% |
| MATH Level 5 | 14.9% | — |

## Knowledge

- Claude 3 Haiku: 17.3 (#280)
- Claude Sonnet 5: 55.7 (#42)

| Benchmark | Claude 3 Haiku | Claude Sonnet 5 |
|---|---|---|
| GPQA Diamond | 36.3% | 90.5% |
| LMArena Expert | 1148 | 1491 |
| SimpleQA Verified | — | 33.7% |
| Confabulations | 34.2% | — |
| MMLU | 73.8% | — |

## Multimodal

- Claude 3 Haiku: 23.1 (#123)
- Claude Sonnet 5: 42.4 (#26)

| Benchmark | Claude 3 Haiku | Claude Sonnet 5 |
|---|---|---|
| LMArena Vision | 950 | 1275 |
| Blueprint-Bench 2 | — | 24.9% |
| LMArena Document | — | 1466 |
| ScienceQA | 72% | — |

## Multilingual

- Claude 3 Haiku: 36.1 (#238)
- Claude Sonnet 5: 54.0 (#55)

| Benchmark | Claude 3 Haiku | Claude Sonnet 5 |
|---|---|---|
| LMArena Non-English | 1178 | 1431 |
| LMArena Chinese | 1155 | 1475 |
| LMArena French | 1194 | 1457 |
| LMArena German | 1174 | 1448 |
| LMArena Japanese | 1102 | 1422 |
| LMArena Korean | 1108 | 1411 |
| LMArena Russian | 1204 | 1452 |
| LMArena Spanish | 1165 | 1436 |

## Instruction Following

- Claude 3 Haiku: 61.5 (#242)
- Claude Sonnet 5: 76.6 (#39)

| Benchmark | Claude 3 Haiku | Claude Sonnet 5 |
|---|---|---|
| LMArena Instruction Following | 1174 | 1453 |

## Long Context

- Claude 3 Haiku: 36.1 (#232)
- Claude Sonnet 5: 44.8 (#53)

| Benchmark | Claude 3 Haiku | Claude Sonnet 5 |
|---|---|---|
| LMArena Longer Query | 1191 | 1464 |

## Writing & Preference

- Claude 3 Haiku: 29.8 (#286)
- Claude Sonnet 5: 69.4 (#24)

| Benchmark | Claude 3 Haiku | Claude Sonnet 5 |
|---|---|---|
| LMArena Text | 1195 | 1443 |
| LMArena Creative Writing | 1157 | 1416 |
| EQ-Bench Creative Writing | 717 | 1794 |
| LMArena Multi-Turn | 1190 | 1454 |
| EQ-Bench 4 | — | 1236 |

## FAQ

### Is Claude 3 Haiku better than Claude Sonnet 5?

Claude Sonnet 5 is the stronger model overall, scoring 54.5 to 25.7 on the Noometry Index.

### Is Claude 3 Haiku or Claude Sonnet 5 better for coding?

Claude Sonnet 5 scores higher on coding benchmarks: 55.5 versus 26.1 in the Noometry coding category.

### How many benchmarks do Claude 3 Haiku and Claude Sonnet 5 share?

26 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and Claude Sonnet 5 has 51.