# Claude 3 Haiku vs GPT-6 Sol

> GPT-6 Sol is the stronger model overall, scoring 49.2 to 25.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-3-haiku-vs-gpt-6-sol
- Last updated: 2026-10-10
- Shared benchmarks: 14

## Summary

- They share 14 benchmarks with published results for both. Claude 3 Haiku scores higher in 0 categories and GPT-6 Sol in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GPT-6 Sol leads 72.3 to 29.8.

## Snapshot

| | Claude 3 Haiku | GPT-6 Sol |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 25.7 | 49.2 |
| Rank | 333 | 46 |
| Context | — | 1.05M |
| Input $/M | — | $2 |
| Output $/M | — | $10 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude 3 Haiku: 26.1 (#320)
- GPT-6 Sol: 59.6 (#11)

| Benchmark | Claude 3 Haiku | GPT-6 Sol |
|---|---|---|
| LMArena Coding | 1199 | 1453 |
| DeepSWE | — | 68.8% |
| FrontierCode | — | 49.3% |
| LMArena WebDev | — | 1692 |
| WeirdML | 9.8% | — |
| BigCodeBench Instruct | 39.4% | — |
| BigCodeBench Complete | 50.1% | — |
| CadEval | 12% | — |
| HumanEval+ | 68.9% | — |
| MBPP+ | 68.8% | — |

## Agentic & Tool Use

- Claude 3 Haiku: —
- GPT-6 Sol: 33.5 (#49)

| Benchmark | Claude 3 Haiku | GPT-6 Sol |
|---|---|---|
| GDP.pdf | — | 28% |

## Reasoning

- Claude 3 Haiku: 15.7 (#303)
- GPT-6 Sol: 49.3 (#34)

| Benchmark | Claude 3 Haiku | GPT-6 Sol |
|---|---|---|
| LMArena Hard Prompts | 1174 | 1420 |
| Kagi LLM Benchmark | 34.2% | — |
| NYT Connections (extended) | — | 90.1% |
| EBR-Bench | — | 53.3% |
| DTBench | 50.1% | — |
| LMCA | 8.8% | — |
| Epoch Capabilities Index | 118.3 | — |
| ForecastBench | 53.2 | — |
| WinoGrande | 74.2% | — |

## Math

- Claude 3 Haiku: 9.2 (#313)
- GPT-6 Sol: 35.8 (#135)

| Benchmark | Claude 3 Haiku | GPT-6 Sol |
|---|---|---|
| LMArena Math | 1188 | 1404 |
| OTIS Mock AIME 2024-2025 | 1.8% | — |
| MATH Level 5 | 14.9% | — |

## Knowledge

- Claude 3 Haiku: 17.3 (#280)
- GPT-6 Sol: 43.0 (#87)

| Benchmark | Claude 3 Haiku | GPT-6 Sol |
|---|---|---|
| LMArena Expert | 1148 | 1449 |
| GPQA Diamond | 36.3% | — |
| Confabulations | 34.2% | — |
| Vectara Hallucination Rate | — | 6.5% |
| MMLU | 73.8% | — |

## Multimodal

- Claude 3 Haiku: 23.1 (#123)
- GPT-6 Sol: 47.6 (#9)

| Benchmark | Claude 3 Haiku | GPT-6 Sol |
|---|---|---|
| LMArena Vision | 950 | — |
| Furniture Assembly | — | 58.3% |
| ScienceQA | 72% | — |

## Multilingual

- Claude 3 Haiku: 36.1 (#238)
- GPT-6 Sol: 51.0 (#113)

| Benchmark | Claude 3 Haiku | GPT-6 Sol |
|---|---|---|
| LMArena Non-English | 1178 | 1389 |
| LMArena Chinese | 1155 | 1416 |
| LMArena Russian | 1204 | 1407 |
| LMArena Spanish | 1165 | 1377 |
| LMArena French | 1194 | — |
| LMArena German | 1174 | — |
| LMArena Japanese | 1102 | — |
| LMArena Korean | 1108 | — |

## Instruction Following

- Claude 3 Haiku: 61.5 (#242)
- GPT-6 Sol: 74.4 (#97)

| Benchmark | Claude 3 Haiku | GPT-6 Sol |
|---|---|---|
| LMArena Instruction Following | 1174 | 1406 |

## Long Context

- Claude 3 Haiku: 36.1 (#232)
- GPT-6 Sol: 43.2 (#100)

| Benchmark | Claude 3 Haiku | GPT-6 Sol |
|---|---|---|
| LMArena Longer Query | 1191 | 1415 |

## Writing & Preference

- Claude 3 Haiku: 29.8 (#286)
- GPT-6 Sol: 72.3 (#15)

| Benchmark | Claude 3 Haiku | GPT-6 Sol |
|---|---|---|
| LMArena Text | 1195 | 1396 |
| LMArena Creative Writing | 1157 | 1392 |
| EQ-Bench Creative Writing | 717 | 2125 |
| LMArena Multi-Turn | 1190 | 1405 |

## FAQ

### Is Claude 3 Haiku better than GPT-6 Sol?

GPT-6 Sol is the stronger model overall, scoring 49.2 to 25.7 on the Noometry Index.

### Is Claude 3 Haiku or GPT-6 Sol better for coding?

GPT-6 Sol scores higher on coding benchmarks: 59.6 versus 26.1 in the Noometry coding category.

### How many benchmarks do Claude 3 Haiku and GPT-6 Sol share?

14 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and GPT-6 Sol has 22.