# Claude Sonnet 5 vs Command A

> Claude Sonnet 5 is the stronger model overall, scoring 54.5 to 35.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-sonnet-5-vs-command-a
- Last updated: 2026-10-10
- Shared benchmarks: 20

## Summary

- They share 20 benchmarks with published results for both. Claude Sonnet 5 scores higher in 9 categories and Command A in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Sonnet 5 leads 66.1 to 33.5.
- The biggest single-benchmark swing is LMCA: 50% for Claude Sonnet 5 and 10.3% for Command A.
- Claude Sonnet 5 is cheaper at $2 / $10 per million input/output tokens, against $2.50 / $10 for Command A.
- Claude Sonnet 5 accepts more context: 1M tokens versus 256K.
- Command A has downloadable open weights; the other is API-only.

## Snapshot

| | Claude Sonnet 5 | Command A |
|---|---|---|
| Provider | Anthropic | Cohere |
| Noometry Index | 54.5 | 35.9 |
| Rank | 26 | 212 |
| Context | 1M | 256K |
| Input $/M | $2 | $2.50 |
| Output $/M | $10 | $10 |
| Weights | Proprietary | Open |

## Coding

- Claude Sonnet 5: 55.5 (#20)
- Command A: 26.8 (#317)

| Benchmark | Claude Sonnet 5 | Command A |
|---|---|---|
| LMArena Coding | 1483 | 1331 |
| DeepSWE | 53.8% | — |
| FrontierCode | 42.7% | — |
| Aider Polyglot | — | 12% |
| CursorBench | 34.1% | — |
| LMArena WebDev | 1540 | — |
| SciCode | 53.6% | — |
| GSO | 37.3% | — |
| WeirdML | 68.8% | — |
| ALE-Bench | 1,463 | — |

## Agentic & Tool Use

- Claude Sonnet 5: 42.7 (#16)
- Command A: 35.7 (#36)

| Benchmark | Claude Sonnet 5 | Command A |
|---|---|---|
| APEX-Agents | 54.5% | — |
| Berkeley Function Calling Leaderboard | — | 57.1% |
| GBAEval | 65.3% | — |
| LMArena Search | 1194 | — |
| Vending-Bench 2 | 6,378 | — |

## Reasoning

- Claude Sonnet 5: 48.2 (#37)
- Command A: 17.7 (#276)

| Benchmark | Claude Sonnet 5 | Command A |
|---|---|---|
| LMArena Hard Prompts | 1461 | 1326 |
| DTBench | 92.5% | 61.3% |
| LMCA | 50% | 10.3% |
| SimpleBench | 60.6% | — |
| Kagi LLM Benchmark | — | 28.8% |
| 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 | — |
| Epoch Capabilities Index | 156.34 | — |
| ForecastBench | 61.1 | — |

## Math

- Claude Sonnet 5: 66.1 (#21)
- Command A: 33.5 (#172)

| Benchmark | Claude Sonnet 5 | Command A |
|---|---|---|
| LMArena Math | 1467 | 1300 |
| FrontierMath (Tiers 1-3) | 65.6% | — |
| FrontierMath Tier 4 | 29.3% | — |
| OTIS Mock AIME 2024-2025 | 94.7% | — |
| ProofBench | 77% | — |

## Knowledge

- Claude Sonnet 5: 55.7 (#42)
- Command A: 36.5 (#157)

| Benchmark | Claude Sonnet 5 | Command A |
|---|---|---|
| LMArena Expert | 1491 | 1295 |
| GPQA Diamond | 90.5% | — |
| SimpleQA Verified | 33.7% | — |
| Vectara Hallucination Rate | — | 9.3% |

## Multimodal

- Claude Sonnet 5: 42.4 (#26)
- Command A: —

| Benchmark | Claude Sonnet 5 | Command A |
|---|---|---|
| LMArena Vision | 1275 | — |
| Blueprint-Bench 2 | 24.9% | — |
| LMArena Document | 1466 | — |

## Multilingual

- Claude Sonnet 5: 54.0 (#55)
- Command A: 45.5 (#166)

| Benchmark | Claude Sonnet 5 | Command A |
|---|---|---|
| LMArena Non-English | 1431 | 1313 |
| LMArena Chinese | 1475 | 1327 |
| LMArena French | 1457 | 1352 |
| LMArena German | 1448 | 1341 |
| LMArena Japanese | 1422 | 1283 |
| LMArena Korean | 1411 | 1285 |
| LMArena Russian | 1452 | 1314 |
| LMArena Spanish | 1436 | 1346 |

## Instruction Following

- Claude Sonnet 5: 76.6 (#39)
- Command A: 69.3 (#172)

| Benchmark | Claude Sonnet 5 | Command A |
|---|---|---|
| LMArena Instruction Following | 1453 | 1309 |

## Long Context

- Claude Sonnet 5: 44.8 (#53)
- Command A: 40.6 (#147)

| Benchmark | Claude Sonnet 5 | Command A |
|---|---|---|
| LMArena Longer Query | 1464 | 1334 |

## Writing & Preference

- Claude Sonnet 5: 69.4 (#24)
- Command A: 47.8 (#204)

| Benchmark | Claude Sonnet 5 | Command A |
|---|---|---|
| LMArena Text | 1443 | 1331 |
| LMArena Creative Writing | 1416 | 1319 |
| EQ-Bench Creative Writing | 1794 | 1145 |
| LMArena Multi-Turn | 1454 | 1338 |
| EQ-Bench 4 | 1236 | — |

## FAQ

### Is Claude Sonnet 5 better than Command A?

Claude Sonnet 5 is the stronger model overall, scoring 54.5 to 35.9 on the Noometry Index.

### Which is cheaper, Claude Sonnet 5 or Command A?

Claude Sonnet 5 is cheaper. It lists at $2 per million input tokens and $10 per million output tokens; Command A lists at $2.50 and $10.

### Is Claude Sonnet 5 or Command A better for coding?

Claude Sonnet 5 scores higher on coding benchmarks: 55.5 versus 26.8 in the Noometry coding category.

### Which has the bigger context window?

Claude Sonnet 5 does, with 1M tokens against 256K.

### How many benchmarks do Claude Sonnet 5 and Command A share?

20 benchmarks have published results for both models. Claude Sonnet 5 has 51 scored results on Noometry and Command A has 24.