# Command R+ vs GPT-5 Mini

> GPT-5 Mini is the stronger model overall, scoring 41.7 to 32.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/command-r-plus-vs-gpt-5-mini
- Last updated: 2026-10-10
- Shared benchmarks: 21

## Summary

- They share 21 benchmarks with published results for both. Command R+ scores higher in 0 categories and GPT-5 Mini in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5 Mini leads 46.3 to 26.6.
- The biggest single-benchmark swing is LMCA: 5% for Command R+ and 34.2% for GPT-5 Mini.
- GPT-5 Mini is cheaper at $0.25 / $2 per million input/output tokens, against $2.50 / $10 for Command R+.
- GPT-5 Mini accepts more context: 400K tokens versus 128K.
- Command R+ has downloadable open weights; the other is API-only.

## Snapshot

| | Command R+ | GPT-5 Mini |
|---|---|---|
| Provider | Cohere | OpenAI |
| Noometry Index | 32.0 | 41.7 |
| Rank | 251 | 115 |
| Context | 128K | 400K |
| Input $/M | $2.50 | $0.25 |
| Output $/M | $10 | $2 |
| Weights | Open | Proprietary |

## Coding

- Command R+: 28.6 (#304)
- GPT-5 Mini: 40.0 (#134)

| Benchmark | Command R+ | GPT-5 Mini |
|---|---|---|
| LMArena Coding | 1187 | 1406 |
| SWE-bench Verified | — | 64.7% |
| SWE-bench Verified (bash only) | — | 59.8% |
| SWE-bench Multilingual | — | 39.7% |
| SciCode | — | 39.2% |
| WeirdML | — | 52.7% |
| BigCodeBench Instruct | 33.8% | — |
| LiveBench Coding | 19.1% | — |
| BigCodeBench Complete | 41.9% | — |
| ALE-Bench | — | 799.77 |
| AlgoTune | — | 1.38 |
| HumanEval+ | 56.7% | — |
| MBPP+ | 63.5% | — |

## Agentic & Tool Use

- Command R+: —
- GPT-5 Mini: 31.0 (#64)

| Benchmark | Command R+ | GPT-5 Mini |
|---|---|---|
| Terminal-Bench | — | 34.8% |
| Berkeley Function Calling Leaderboard | — | 55.5% |
| Vending-Bench 2 | — | -31.18 |

## Reasoning

- Command R+: 8.9 (#341)
- GPT-5 Mini: 24.1 (#153)

| Benchmark | Command R+ | GPT-5 Mini |
|---|---|---|
| LMArena Hard Prompts | 1186 | 1380 |
| DTBench | 54.9% | 80.5% |
| LMCA | 5% | 34.2% |
| Epoch Capabilities Index | 119.28 | 145.51 |
| ARC-AGI-2 | — | 4.4% |
| SimpleBench | 17.4% | — |
| Kagi LLM Benchmark | — | 70.3% |
| ARC-AGI-1 | — | 54.3% |
| CritPt | — | 0% |
| Chess Puzzles | — | 30% |
| EnigmaEval | — | 8.2% |
| LiveBench Reasoning | 24.8% | — |
| Mystery Game Puzzles | — | 10% |
| LiveBench Data Analysis | 38.1% | — |
| ForecastBench | — | 61 |
| LiveBench | 31.8% | — |

## Math

- Command R+: 26.6 (#239)
- GPT-5 Mini: 46.3 (#59)

| Benchmark | Command R+ | GPT-5 Mini |
|---|---|---|
| LMArena Math | 1188 | 1377 |
| FrontierMath (Tiers 1-3) | — | 46.7% |
| FrontierMath Tier 4 | — | 12.2% |
| OTIS Mock AIME 2024-2025 | — | 86.7% |
| ProofBench | — | 9% |
| Omni-MATH | — | 72.2% |
| LiveBench Math | 21.3% | — |
| MATH Level 5 | — | 97.8% |
| FrontierMath (Feb 2025 set) | — | 27.2% |
| FrontierMath Tier 4 (v1) | — | 6.3% |

## Knowledge

- Command R+: 35.9 (#165)
- GPT-5 Mini: 45.5 (#80)

| Benchmark | Command R+ | GPT-5 Mini |
|---|---|---|
| Vectara Hallucination Rate | 6.9% | 12.9% |
| LMArena Expert | 1174 | 1377 |
| GPQA Diamond | — | 75% |
| Humanity's Last Exam | — | 19.4% |
| SimpleQA Verified | — | 21.6% |
| MMLU-Pro | — | 83.5% |
| Confabulations | — | 13.3% |
| GPQA (HELM) | — | 75.6% |
| MMLU | 69.4% | — |

## Multimodal

- Command R+: —
- GPT-5 Mini: 35.0 (#80)

| Benchmark | Command R+ | GPT-5 Mini |
|---|---|---|
| LMArena Vision | — | 1202 |
| VPCT | — | 40.2% |

## Multilingual

- Command R+: 38.8 (#222)
- GPT-5 Mini: 49.1 (#131)

| Benchmark | Command R+ | GPT-5 Mini |
|---|---|---|
| LMArena Non-English | 1216 | 1363 |
| LMArena Chinese | 1226 | 1387 |
| LMArena French | 1208 | 1385 |
| LMArena German | 1216 | 1366 |
| LMArena Japanese | 1166 | 1342 |
| LMArena Korean | 1138 | 1306 |
| LMArena Russian | 1227 | 1362 |
| LMArena Spanish | 1189 | 1355 |

## Instruction Following

- Command R+: 60.2 (#249)
- GPT-5 Mini: 76.4 (#43)

| Benchmark | Command R+ | GPT-5 Mini |
|---|---|---|
| LMArena Instruction Following | 1197 | 1357 |
| LiveBench Instruction Following | 57.6% | — |
| IFEval | — | 92.7% |

## Long Context

- Command R+: 37.3 (#214)
- GPT-5 Mini: 41.9 (#127)

| Benchmark | Command R+ | GPT-5 Mini |
|---|---|---|
| LMArena Longer Query | 1231 | 1355 |
| Fiction.LiveBench | — | 69.4% |

## Writing & Preference

- Command R+: 43.7 (#223)
- GPT-5 Mini: 55.4 (#143)

| Benchmark | Command R+ | GPT-5 Mini |
|---|---|---|
| LMArena Text | 1229 | 1373 |
| LMArena Creative Writing | 1235 | 1325 |
| LMArena Multi-Turn | 1213 | 1363 |
| Short-Story Creative Writing | — | 83.1% |
| EQ-Bench Creative Writing | — | 1313 |
| WildBench | — | 85.5% |
| LiveBench Language | 29.7% | — |

## FAQ

### Is Command R+ better than GPT-5 Mini?

GPT-5 Mini is the stronger model overall, scoring 41.7 to 32.0 on the Noometry Index.

### Which is cheaper, Command R+ or GPT-5 Mini?

GPT-5 Mini is cheaper. It lists at $0.25 per million input tokens and $2 per million output tokens; Command R+ lists at $2.50 and $10.

### Is Command R+ or GPT-5 Mini better for coding?

GPT-5 Mini scores higher on coding benchmarks: 40.0 versus 28.6 in the Noometry coding category.

### Which has the bigger context window?

GPT-5 Mini does, with 400K tokens against 128K.

### How many benchmarks do Command R+ and GPT-5 Mini share?

21 benchmarks have published results for both models. Command R+ has 34 scored results on Noometry and GPT-5 Mini has 60.