# Chatgpt 4o Latest 20250326 vs Claude Sonnet 4.6

> Claude Sonnet 4.6 is the stronger model overall, scoring 50.3 to 43.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/chatgpt-4o-vs-claude-sonnet-4-6
- Last updated: 2026-10-12
- Shared benchmarks: 19

## Summary

- They share 19 benchmarks with published results for both. Chatgpt 4o Latest 20250326 scores higher in 1 category and Claude Sonnet 4.6 in 8 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Sonnet 4.6 leads 52.9 to 38.6.

## Snapshot

| | Chatgpt 4o Latest 20250326 | Claude Sonnet 4.6 |
|---|---|---|
| Provider | OpenAI | Anthropic |
| Noometry Index | 43.8 | 50.3 |
| Rank | 82 | 50 |
| Context | — | 1M |
| Input $/M | — | $3 |
| Output $/M | — | $15 |
| Weights | Proprietary | Proprietary |

## Coding

- Chatgpt 4o Latest 20250326: 41.6 (#122)
- Claude Sonnet 4.6: 46.3 (#67)

| Benchmark | Chatgpt 4o Latest 20250326 | Claude Sonnet 4.6 |
|---|---|---|
| LMArena Coding | 1413 | 1504 |
| SWE-bench Verified | — | 75.2% |
| DeepSWE | — | 29.9% |
| FrontierCode | — | 24.3% |
| LMArena WebDev | — | 1522 |
| SciCode | — | 46.8% |
| WeirdML | — | 66.1% |
| ALE-Bench | — | 1,327 |

## Agentic & Tool Use

- Chatgpt 4o Latest 20250326: —
- Claude Sonnet 4.6: 39.1 (#28)

| Benchmark | Chatgpt 4o Latest 20250326 | Claude Sonnet 4.6 |
|---|---|---|
| Terminal-Bench | — | 53.4% |
| APEX-Agents | — | 43% |
| OSWorld 2.0 | — | 9.3% |
| DeepResearch Bench | — | 54.9% |
| OSWorld | — | 72.1% |
| ExploitBench | — | 23.6% |
| GBAEval | — | 48.8% |
| GDP.pdf | — | 18% |
| LMArena Search | — | 1221 |
| Vending-Bench 2 | — | 7,204 |

## Reasoning

- Chatgpt 4o Latest 20250326: 33.8 (#71)
- Claude Sonnet 4.6: 46.1 (#45)

| Benchmark | Chatgpt 4o Latest 20250326 | Claude Sonnet 4.6 |
|---|---|---|
| LMArena Hard Prompts | 1424 | 1484 |
| ARC-AGI-2 | — | 60.4% |
| Kagi LLM Benchmark | 75% | — |
| NYT Connections (extended) | — | 80.9% |
| ARC-AGI-1 | — | 86.5% |
| CritPt | — | 3.1% |
| Chess Puzzles | — | 13% |
| Thematic Generalization | — | 76.3% |
| Mystery Game Puzzles | — | 16% |
| DTBench | — | 89.9% |
| LMCA | — | 46.5% |
| Epoch Capabilities Index | — | 152.24 |
| ForecastBench | — | 62 |

## Math

- Chatgpt 4o Latest 20250326: 38.6 (#134)
- Claude Sonnet 4.6: 52.9 (#49)

| Benchmark | Chatgpt 4o Latest 20250326 | Claude Sonnet 4.6 |
|---|---|---|
| LMArena Math | 1407 | 1462 |
| OTIS Mock AIME 2024-2025 | — | 85.8% |
| ProofBench | — | 45% |
| FrontierMath (Feb 2025 set) | — | 32.4% |
| FrontierMath Tier 4 (v1) | — | 8.3% |

## Knowledge

- Chatgpt 4o Latest 20250326: 39.2 (#137)
- Claude Sonnet 4.6: 51.7 (#65)

| Benchmark | Chatgpt 4o Latest 20250326 | Claude Sonnet 4.6 |
|---|---|---|
| LMArena Expert | 1401 | 1500 |
| GPQA Diamond | — | 87.4% |
| SimpleQA Verified | — | 35.5% |
| Confabulations | 16.6% | — |
| Vectara Hallucination Rate | — | 10.6% |

## Multimodal

- Chatgpt 4o Latest 20250326: 39.6 (#58)
- Claude Sonnet 4.6: 38.0 (#68)

| Benchmark | Chatgpt 4o Latest 20250326 | Claude Sonnet 4.6 |
|---|---|---|
| LMArena Vision | 1243 | 1283 |
| Blueprint-Bench 2 | — | 6.7% |
| LMArena Document | — | 1482 |

## Multilingual

- Chatgpt 4o Latest 20250326: 52.9 (#76)
- Claude Sonnet 4.6: 54.4 (#41)

| Benchmark | Chatgpt 4o Latest 20250326 | Claude Sonnet 4.6 |
|---|---|---|
| LMArena Non-English | 1419 | 1440 |
| LMArena Chinese | 1457 | 1491 |
| LMArena French | 1446 | 1465 |
| LMArena German | 1423 | 1428 |
| LMArena Japanese | 1405 | 1420 |
| LMArena Korean | 1396 | 1411 |
| LMArena Russian | 1429 | 1440 |
| LMArena Spanish | 1434 | 1464 |

## Instruction Following

- Chatgpt 4o Latest 20250326: 74.0 (#107)
- Claude Sonnet 4.6: 77.4 (#25)

| Benchmark | Chatgpt 4o Latest 20250326 | Claude Sonnet 4.6 |
|---|---|---|
| LMArena Instruction Following | 1403 | 1475 |

## Long Context

- Chatgpt 4o Latest 20250326: 43.1 (#107)
- Claude Sonnet 4.6: 45.3 (#44)

| Benchmark | Chatgpt 4o Latest 20250326 | Claude Sonnet 4.6 |
|---|---|---|
| LMArena Longer Query | 1413 | 1479 |

## Writing & Preference

- Chatgpt 4o Latest 20250326: 62.6 (#72)
- Claude Sonnet 4.6: 70.2 (#22)

| Benchmark | Chatgpt 4o Latest 20250326 | Claude Sonnet 4.6 |
|---|---|---|
| LMArena Text | 1429 | 1458 |
| LMArena Creative Writing | 1405 | 1435 |
| EQ-Bench Creative Writing | 1501 | 1810 |
| LMArena Multi-Turn | 1454 | 1464 |
| EQ-Bench 4 | — | 1207 |

## FAQ

### Is Chatgpt 4o Latest 20250326 better than Claude Sonnet 4.6?

Claude Sonnet 4.6 is the stronger model overall, scoring 50.3 to 43.8 on the Noometry Index.

### Is Chatgpt 4o Latest 20250326 or Claude Sonnet 4.6 better for coding?

Claude Sonnet 4.6 scores higher on coding benchmarks: 46.3 versus 41.6 in the Noometry coding category.

### How many benchmarks do Chatgpt 4o Latest 20250326 and Claude Sonnet 4.6 share?

19 benchmarks have published results for both models. Chatgpt 4o Latest 20250326 has 21 scored results on Noometry and Claude Sonnet 4.6 has 57.