# Claude Haiku 4.5 vs Command R+

> Claude Haiku 4.5 is the stronger model overall, scoring 39.3 to 32.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-haiku-4-5-vs-command-r-plus
- Last updated: 2026-10-10
- Shared benchmarks: 21

## Summary

- They share 21 benchmarks with published results for both. Claude Haiku 4.5 scores higher in 8 categories and Command R+ in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Haiku 4.5 leads 43.0 to 26.6.
- The biggest single-benchmark swing is LMCA: 30.9% for Claude Haiku 4.5 and 5% for Command R+.
- Claude Haiku 4.5 is cheaper at $1 / $5 per million input/output tokens, against $2.50 / $10 for Command R+.
- Claude Haiku 4.5 accepts more context: 200K tokens versus 128K.
- Command R+ has downloadable open weights; the other is API-only.

## Snapshot

| | Claude Haiku 4.5 | Command R+ |
|---|---|---|
| Provider | Anthropic | Cohere |
| Noometry Index | 39.3 | 32.0 |
| Rank | 155 | 251 |
| Context | 200K | 128K |
| Input $/M | $1 | $2.50 |
| Output $/M | $5 | $10 |
| Weights | Proprietary | Open |

## Coding

- Claude Haiku 4.5: 43.9 (#71)
- Command R+: 28.6 (#304)

| Benchmark | Claude Haiku 4.5 | Command R+ |
|---|---|---|
| LMArena Coding | 1454 | 1187 |
| SWE-bench Verified (bash only) | 66.6% | — |
| LMArena WebDev | 1330 | — |
| SWE-bench Multilingual | 64.7% | — |
| SciCode | 43.3% | — |
| WeirdML | 45.4% | — |
| BigCodeBench Instruct | — | 33.8% |
| LiveBench Coding | — | 19.1% |
| BigCodeBench Complete | — | 41.9% |
| ALE-Bench | 653.48 | — |
| HumanEval+ | — | 56.7% |
| MBPP+ | — | 63.5% |

## Agentic & Tool Use

- Claude Haiku 4.5: 33.5 (#50)
- Command R+: —

| Benchmark | Claude Haiku 4.5 | Command R+ |
|---|---|---|
| Terminal-Bench | 35.5% | — |
| Berkeley Function Calling Leaderboard | 68.7% | — |
| DeepResearch Bench | 45.5% | — |
| BALROG | 31.2% | — |
| ExploitBench | 13.7% | — |
| Vending-Bench 2 | 458.89 | — |

## Reasoning

- Claude Haiku 4.5: 15.1 (#310)
- Command R+: 8.9 (#341)

| Benchmark | Claude Haiku 4.5 | Command R+ |
|---|---|---|
| LMArena Hard Prompts | 1420 | 1186 |
| DTBench | 73.6% | 54.9% |
| LMCA | 30.9% | 5% |
| Epoch Capabilities Index | 142.42 | 119.28 |
| ARC-AGI-2 | 4% | — |
| SimpleBench | — | 17.4% |
| NYT Connections (extended) | 14.3% | — |
| ARC-AGI-1 | 47.7% | — |
| CritPt | 0% | — |
| Chess Puzzles | 8% | — |
| LiveBench Reasoning | — | 24.8% |
| LiveBench Data Analysis | — | 38.1% |
| ForecastBench | 61.4 | — |
| LiveBench | — | 31.8% |

## Math

- Claude Haiku 4.5: 43.0 (#69)
- Command R+: 26.6 (#239)

| Benchmark | Claude Haiku 4.5 | Command R+ |
|---|---|---|
| LMArena Math | 1395 | 1188 |
| OTIS Mock AIME 2024-2025 | 66.7% | — |
| Omni-MATH | 56.1% | — |
| LiveBench Math | — | 21.3% |
| MATH Level 5 | 96.4% | — |
| FrontierMath (Feb 2025 set) | 5.9% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |

## Knowledge

- Claude Haiku 4.5: 37.6 (#146)
- Command R+: 35.9 (#165)

| Benchmark | Claude Haiku 4.5 | Command R+ |
|---|---|---|
| Vectara Hallucination Rate | 9.8% | 6.9% |
| LMArena Expert | 1443 | 1174 |
| GPQA Diamond | 71.2% | — |
| SimpleQA Verified | 13.2% | — |
| MMLU-Pro | 77.7% | — |
| GPQA (HELM) | 60.5% | — |
| MMLU | — | 69.4% |

## Multimodal

- Claude Haiku 4.5: 27.0 (#111)
- Command R+: —

| Benchmark | Claude Haiku 4.5 | Command R+ |
|---|---|---|
| Blueprint-Bench 2 | 0% | — |
| LMArena Document | 1420 | — |

## Multilingual

- Claude Haiku 4.5: 50.1 (#124)
- Command R+: 38.8 (#222)

| Benchmark | Claude Haiku 4.5 | Command R+ |
|---|---|---|
| LMArena Non-English | 1376 | 1216 |
| LMArena Chinese | 1415 | 1226 |
| LMArena French | 1408 | 1208 |
| LMArena German | 1377 | 1216 |
| LMArena Japanese | 1339 | 1166 |
| LMArena Korean | 1346 | 1138 |
| LMArena Russian | 1380 | 1227 |
| LMArena Spanish | 1420 | 1189 |

## Instruction Following

- Claude Haiku 4.5: 71.6 (#144)
- Command R+: 60.2 (#249)

| Benchmark | Claude Haiku 4.5 | Command R+ |
|---|---|---|
| LMArena Instruction Following | 1414 | 1197 |
| LiveBench Instruction Following | — | 57.6% |
| IFEval | 80.1% | — |

## Long Context

- Claude Haiku 4.5: 43.6 (#86)
- Command R+: 37.3 (#214)

| Benchmark | Claude Haiku 4.5 | Command R+ |
|---|---|---|
| LMArena Longer Query | 1427 | 1231 |

## Writing & Preference

- Claude Haiku 4.5: 58.1 (#119)
- Command R+: 43.7 (#223)

| Benchmark | Claude Haiku 4.5 | Command R+ |
|---|---|---|
| LMArena Text | 1396 | 1229 |
| LMArena Creative Writing | 1371 | 1235 |
| LMArena Multi-Turn | 1409 | 1213 |
| WildBench | 83.9% | — |
| EQ-Bench 4 | 1064 | — |
| LiveBench Language | — | 29.7% |

## FAQ

### Is Claude Haiku 4.5 better than Command R+?

Claude Haiku 4.5 is the stronger model overall, scoring 39.3 to 32.0 on the Noometry Index.

### Which is cheaper, Claude Haiku 4.5 or Command R+?

Claude Haiku 4.5 is cheaper. It lists at $1 per million input tokens and $5 per million output tokens; Command R+ lists at $2.50 and $10.

### Is Claude Haiku 4.5 or Command R+ better for coding?

Claude Haiku 4.5 scores higher on coding benchmarks: 43.9 versus 28.6 in the Noometry coding category.

### Which has the bigger context window?

Claude Haiku 4.5 does, with 200K tokens against 128K.

### How many benchmarks do Claude Haiku 4.5 and Command R+ share?

21 benchmarks have published results for both models. Claude Haiku 4.5 has 53 scored results on Noometry and Command R+ has 34.