# Command R vs GPT-4

> Command R is the stronger model overall, scoring 31.0 to 28.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/command-r-vs-gpt-4
- Last updated: 2026-10-10
- Shared benchmarks: 22

## Summary

- They share 22 benchmarks with published results for both. Command R scores higher in 3 categories and GPT-4 in 5 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Command R leads 25.8 to 10.1.
- The biggest single-benchmark swing is DTBench: 46.4% for Command R and 62.7% for GPT-4.
- Command R is cheaper at $0.15 / $0.60 per million input/output tokens, against $30 / $60 for GPT-4.
- Command R accepts more context: 128K tokens versus 8K.
- Command R has downloadable open weights; the other is API-only.

## Snapshot

| | Command R | GPT-4 |
|---|---|---|
| Provider | Cohere | OpenAI |
| Noometry Index | 31.0 | 28.9 |
| Rank | 267 | 308 |
| Context | 128K | 8K |
| Input $/M | $0.15 | $30 |
| Output $/M | $0.60 | $60 |
| Weights | Open | Proprietary |

## Coding

- Command R: 28.8 (#301)
- GPT-4: 31.2 (#277)

| Benchmark | Command R | GPT-4 |
|---|---|---|
| BigCodeBench Instruct | 37.1% | 46% |
| LMArena Coding | 1170 | 1254 |
| BigCodeBench Complete | 45.2% | 57.2% |
| WeirdML | — | 12.4% |
| LiveBench Coding | 17.9% | — |
| HumanEval+ | — | 79.3% |

## Agentic & Tool Use

- Command R: —
- GPT-4: —

| Benchmark | Command R | GPT-4 |
|---|---|---|
| METR Time Horizons | — | 36.1% |

## Reasoning

- Command R: 13.3 (#329)
- GPT-4: 17.3 (#285)

| Benchmark | Command R | GPT-4 |
|---|---|---|
| LMArena Hard Prompts | 1164 | 1241 |
| DTBench | 46.4% | 62.7% |
| LMCA | 9.2% | 17.1% |
| Chess Puzzles | — | 4% |
| LiveBench Reasoning | 21.9% | — |
| Mystery Game Puzzles | — | 12% |
| LiveBench Data Analysis | 33.3% | — |
| BIG-Bench Hard | — | 75.1% |
| Epoch Capabilities Index | — | 125.88 |
| ForecastBench | — | 57.8 |
| HellaSwag | — | 95.3% |
| LiveBench | 27.5% | — |
| WinoGrande | — | 87.5% |

## Math

- Command R: 25.8 (#244)
- GPT-4: 10.1 (#304)

| Benchmark | Command R | GPT-4 |
|---|---|---|
| LMArena Math | 1155 | 1269 |
| OTIS Mock AIME 2024-2025 | — | 1.1% |
| LiveBench Math | 19.4% | — |
| MATH Level 5 | — | 23% |
| GSM8K | — | 92% |

## Knowledge

- Command R: 30.5 (#219)
- GPT-4: 18.4 (#277)

| Benchmark | Command R | GPT-4 |
|---|---|---|
| LMArena Expert | 1138 | 1211 |
| MMLU | 65.2% | 86.4% |
| GPQA Diamond | — | 35.7% |
| TriviaQA | — | 84.8% |

## Multilingual

- Command R: 35.9 (#240)
- GPT-4: 40.8 (#210)

| Benchmark | Command R | GPT-4 |
|---|---|---|
| LMArena Non-English | 1174 | 1246 |
| LMArena Chinese | 1182 | 1242 |
| LMArena French | 1161 | 1282 |
| LMArena German | 1176 | 1251 |
| LMArena Japanese | 1143 | 1209 |
| LMArena Korean | 1162 | 1184 |
| LMArena Russian | 1174 | 1251 |
| LMArena Spanish | 1150 | 1261 |

## Instruction Following

- Command R: 58.3 (#256)
- GPT-4: 65.5 (#217)

| Benchmark | Command R | GPT-4 |
|---|---|---|
| LMArena Instruction Following | 1167 | 1241 |
| LiveBench Instruction Following | 55.6% | — |

## Long Context

- Command R: 36.3 (#226)
- GPT-4: 37.7 (#207)

| Benchmark | Command R | GPT-4 |
|---|---|---|
| LMArena Longer Query | 1198 | 1244 |

## Writing & Preference

- Command R: 38.4 (#248)
- GPT-4: 35.0 (#263)

| Benchmark | Command R | GPT-4 |
|---|---|---|
| LMArena Text | 1187 | 1263 |
| LMArena Creative Writing | 1170 | 1244 |
| LMArena Multi-Turn | 1163 | 1257 |
| EQ-Bench Creative Writing | — | 752 |
| LiveBench Language | 16.7% | — |

## FAQ

### Is Command R better than GPT-4?

Command R is the stronger model overall, scoring 31.0 to 28.9 on the Noometry Index.

### Which is cheaper, Command R or GPT-4?

Command R is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; GPT-4 lists at $30 and $60.

### Is Command R or GPT-4 better for coding?

GPT-4 scores higher on coding benchmarks: 31.2 versus 28.8 in the Noometry coding category.

### Which has the bigger context window?

Command R does, with 128K tokens against 8K.

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

22 benchmarks have published results for both models. Command R has 29 scored results on Noometry and GPT-4 has 38.