# Claude 2 vs Claude Sonnet 5

> Claude Sonnet 5 is the stronger model overall, scoring 54.6 to 25.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-2-vs-claude-sonnet-5
- Last updated: 2026-10-11
- Shared benchmarks: 4

## Summary

- They share 4 benchmarks with published results for both. Claude 2 scores higher in 0 categories and Claude Sonnet 5 in 3 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Sonnet 5 leads 66.2 to 9.3.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 2.5% for Claude 2 and 94.7% for Claude Sonnet 5.

## Snapshot

| | Claude 2 | Claude Sonnet 5 |
|---|---|---|
| Provider | Anthropic | Anthropic |
| Noometry Index | 25.0 | 54.6 |
| Rank | 346 | 29 |
| Context | — | 1M |
| Input $/M | — | $2 |
| Output $/M | — | $10 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude 2: —
- Claude Sonnet 5: 55.5 (#26)

| Benchmark | Claude 2 | Claude Sonnet 5 |
|---|---|---|
| DeepSWE | — | 53.8% |
| FrontierCode | — | 42.7% |
| CursorBench | — | 34.1% |
| LMArena WebDev | — | 1541 |
| SciCode | — | 54.3% |
| GSO | — | 37.3% |
| WeirdML | — | 68.8% |
| LMArena Coding | — | 1483 |
| ALE-Bench | — | 1,463 |
| HumanEval+ | 61.6% | — |

## Agentic & Tool Use

- Claude 2: —
- Claude Sonnet 5: 42.8 (#18)

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

## Reasoning

- Claude 2: 21.7 (#216)
- Claude Sonnet 5: 49.1 (#39)

| Benchmark | Claude 2 | Claude Sonnet 5 |
|---|---|---|
| DTBench | 51.9% | 92.5% |
| Epoch Capabilities Index | 120.13 | 156.21 |
| SimpleBench | — | 60.6% |
| NYT Connections (extended) | — | 75.1% |
| CritPt | — | 16.9% |
| Chess Puzzles | — | 35% |
| LMArena Hard Prompts | — | 1461 |
| Mystery Game Puzzles | — | 35% |
| LMCA | — | 50% |
| Surface Evolver Bench | — | 60% |
| Bench to the Future 3 | — | 0.14 |
| ForecastBench | — | 61.1 |

## Math

- Claude 2: 9.3 (#320)
- Claude Sonnet 5: 66.2 (#27)

| Benchmark | Claude 2 | Claude Sonnet 5 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.5% | 94.7% |
| FrontierMath (Tiers 1-3) | — | 65.6% |
| FrontierMath Tier 4 | — | 29.3% |
| ProofBench | — | 77% |
| LMArena Math | — | 1467 |
| MATH Level 5 | 11.7% | — |

## Knowledge

- Claude 2: 16.9 (#287)
- Claude Sonnet 5: 55.6 (#47)

| Benchmark | Claude 2 | Claude Sonnet 5 |
|---|---|---|
| GPQA Diamond | 34.7% | 90.5% |
| SimpleQA Verified | — | 33.7% |
| LMArena Expert | — | 1490 |
| MMLU | 78.5% | — |
| TriviaQA | 87.5% | — |

## Multimodal

- Claude 2: —
- Claude Sonnet 5: 42.4 (#31)

| Benchmark | Claude 2 | Claude Sonnet 5 |
|---|---|---|
| LMArena Vision | — | 1274 |
| Blueprint-Bench 2 | — | 24.9% |
| LMArena Document | — | 1466 |

## Multilingual

- Claude 2: —
- Claude Sonnet 5: 53.8 (#55)

| Benchmark | Claude 2 | Claude Sonnet 5 |
|---|---|---|
| LMArena Non-English | — | 1431 |
| LMArena Chinese | — | 1477 |
| LMArena French | — | 1460 |
| LMArena German | — | 1440 |
| LMArena Japanese | — | 1422 |
| LMArena Korean | — | 1411 |
| LMArena Russian | — | 1451 |
| LMArena Spanish | — | 1437 |

## Instruction Following

- Claude 2: —
- Claude Sonnet 5: 76.3 (#41)

| Benchmark | Claude 2 | Claude Sonnet 5 |
|---|---|---|
| LMArena Instruction Following | — | 1452 |

## Long Context

- Claude 2: —
- Claude Sonnet 5: 44.8 (#55)

| Benchmark | Claude 2 | Claude Sonnet 5 |
|---|---|---|
| LMArena Longer Query | — | 1463 |

## Writing & Preference

- Claude 2: —
- Claude Sonnet 5: 69.2 (#25)

| Benchmark | Claude 2 | Claude Sonnet 5 |
|---|---|---|
| LMArena Text | — | 1442 |
| LMArena Creative Writing | — | 1416 |
| EQ-Bench Creative Writing | — | 1794 |
| EQ-Bench 4 | — | 1236 |
| LMArena Multi-Turn | — | 1454 |

## FAQ

### Is Claude 2 better than Claude Sonnet 5?

Claude Sonnet 5 is the stronger model overall, scoring 54.6 to 25.0 on the Noometry Index.

### How many benchmarks do Claude 2 and Claude Sonnet 5 share?

4 benchmarks have published results for both models. Claude 2 has 8 scored results on Noometry and Claude Sonnet 5 has 51.
