# Command A vs GPT-4 Turbo

> Command A is the stronger model overall, scoring 35.9 to 30.3 on the Noometry Index.

- Canonical page: https://noometry.com/compare/command-a-vs-gpt-4-turbo
- Last updated: 2026-10-10
- Shared benchmarks: 19

## Summary

- They share 19 benchmarks with published results for both. Command A scores higher in 6 categories and GPT-4 Turbo in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Command A leads 33.5 to 8.6.
- Command A is cheaper at $2.50 / $10 per million input/output tokens, against $10 / $30 for GPT-4 Turbo.
- Command A accepts more context: 256K tokens versus 128K.
- Command A has downloadable open weights; the other is API-only.

## Snapshot

| | Command A | GPT-4 Turbo |
|---|---|---|
| Provider | Cohere | OpenAI |
| Noometry Index | 35.9 | 30.3 |
| Rank | 212 | 281 |
| Context | 256K | 128K |
| Input $/M | $2.50 | $10 |
| Output $/M | $10 | $30 |
| Weights | Open | Proprietary |

## Coding

- Command A: 26.8 (#317)
- GPT-4 Turbo: 33.4 (#247)

| Benchmark | Command A | GPT-4 Turbo |
|---|---|---|
| LMArena Coding | 1331 | 1268 |
| Aider Polyglot | 12% | — |
| WeirdML | — | 18% |
| BigCodeBench Instruct | — | 48.2% |
| BigCodeBench Complete | — | 58.2% |
| HumanEval+ | — | 86.6% |
| MBPP+ | — | 73.3% |

## Agentic & Tool Use

- Command A: 35.7 (#36)
- GPT-4 Turbo: —

| Benchmark | Command A | GPT-4 Turbo |
|---|---|---|
| Berkeley Function Calling Leaderboard | 57.1% | — |
| METR Time Horizons | — | 36.7% |

## Reasoning

- Command A: 17.7 (#276)
- GPT-4 Turbo: 14.9 (#311)

| Benchmark | Command A | GPT-4 Turbo |
|---|---|---|
| LMArena Hard Prompts | 1326 | 1251 |
| DTBench | 61.3% | 61.6% |
| LMCA | 10.3% | 9.8% |
| SimpleBench | — | 25.1% |
| Kagi LLM Benchmark | 28.8% | — |
| Chess Puzzles | — | 6% |
| Epoch Capabilities Index | — | 127.25 |
| ForecastBench | — | 59.4 |

## Math

- Command A: 33.5 (#172)
- GPT-4 Turbo: 8.6 (#316)

| Benchmark | Command A | GPT-4 Turbo |
|---|---|---|
| LMArena Math | 1300 | 1272 |
| FrontierMath (Tiers 1-3) | — | 0.7% |
| OTIS Mock AIME 2024-2025 | — | 6.7% |
| MATH Level 5 | — | 46.7% |

## Knowledge

- Command A: 36.5 (#157)
- GPT-4 Turbo: 24.3 (#263)

| Benchmark | Command A | GPT-4 Turbo |
|---|---|---|
| LMArena Expert | 1295 | 1223 |
| GPQA Diamond | — | 46.6% |
| Confabulations | — | 28.4% |
| Vectara Hallucination Rate | 9.3% | — |
| MMLU | — | 81.3% |

## Multimodal

- Command A: —
- GPT-4 Turbo: 30.0 (#104)

| Benchmark | Command A | GPT-4 Turbo |
|---|---|---|
| LMArena Vision | — | 1090 |

## Multilingual

- Command A: 45.5 (#166)
- GPT-4 Turbo: 40.7 (#211)

| Benchmark | Command A | GPT-4 Turbo |
|---|---|---|
| LMArena Non-English | 1313 | 1245 |
| LMArena Chinese | 1327 | 1242 |
| LMArena French | 1352 | 1275 |
| LMArena German | 1341 | 1259 |
| LMArena Japanese | 1283 | 1194 |
| LMArena Korean | 1285 | 1187 |
| LMArena Russian | 1314 | 1259 |
| LMArena Spanish | 1346 | 1260 |

## Instruction Following

- Command A: 69.3 (#172)
- GPT-4 Turbo: 66.0 (#211)

| Benchmark | Command A | GPT-4 Turbo |
|---|---|---|
| LMArena Instruction Following | 1309 | 1250 |

## Long Context

- Command A: 40.6 (#147)
- GPT-4 Turbo: 38.0 (#200)

| Benchmark | Command A | GPT-4 Turbo |
|---|---|---|
| LMArena Longer Query | 1334 | 1254 |

## Writing & Preference

- Command A: 47.8 (#204)
- GPT-4 Turbo: 47.9 (#201)

| Benchmark | Command A | GPT-4 Turbo |
|---|---|---|
| LMArena Text | 1331 | 1272 |
| LMArena Creative Writing | 1319 | 1269 |
| LMArena Multi-Turn | 1338 | 1267 |
| EQ-Bench Creative Writing | 1145 | — |

## FAQ

### Is Command A better than GPT-4 Turbo?

Command A is the stronger model overall, scoring 35.9 to 30.3 on the Noometry Index.

### Which is cheaper, Command A or GPT-4 Turbo?

Command A is cheaper. It lists at $2.50 per million input tokens and $10 per million output tokens; GPT-4 Turbo lists at $10 and $30.

### Is Command A or GPT-4 Turbo better for coding?

GPT-4 Turbo scores higher on coding benchmarks: 33.4 versus 26.8 in the Noometry coding category.

### Which has the bigger context window?

Command A does, with 256K tokens against 128K.

### How many benchmarks do Command A and GPT-4 Turbo share?

19 benchmarks have published results for both models. Command A has 24 scored results on Noometry and GPT-4 Turbo has 36.