# Command R vs Gemini 3 Flash Preview

> Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 31.4 on the Noometry Index. Command R costs 4.3× less per token, which makes it the better buy when Gemini 3 Flash Preview's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/command-r-vs-gemini-3-flash-preview
- Last updated: 2026-10-11
- Shared benchmarks: 19

## Summary

- They share 19 benchmarks with published results for both. Command R scores higher in 0 categories and Gemini 3 Flash Preview in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3 Flash Preview leads 49.2 to 13.8.
- The biggest single-benchmark swing is DTBench: 46.4% for Command R and 89.1% for Gemini 3 Flash Preview.
- Command R is cheaper at $0.15 / $0.60 per million input/output tokens, against $0.50 / $3 for Gemini 3 Flash Preview.
- Gemini 3 Flash Preview accepts more context: 1.05M tokens versus 128K.
- Command R has downloadable open weights; the other is API-only.

## Snapshot

| | Command R | Gemini 3 Flash Preview |
|---|---|---|
| Provider | Cohere | Google |
| Noometry Index | 31.4 | 52.3 |
| Rank | 272 | 40 |
| Context | 128K | 1.05M |
| Input $/M | $0.15 | $0.50 |
| Output $/M | $0.60 | $3 |
| Weights | Open | Proprietary |

## Coding

- Command R: 29.3 (#306)
- Gemini 3 Flash Preview: 50.9 (#42)

| Benchmark | Command R | Gemini 3 Flash Preview |
|---|---|---|
| LMArena Coding | 1169 | 1460 |
| SWE-bench Verified | — | 75.4% |
| SWE-bench Verified (bash only) | — | 75.8% |
| LMArena WebDev | — | 1439 |
| SWE-bench Multilingual | — | 72.7% |
| GSO | — | 9.8% |
| WeirdML | — | 61.6% |
| BigCodeBench Instruct | 37.1% | — |
| LiveBench Coding | 17.9% | — |
| BigCodeBench Complete | 45.2% | — |
| ALE-Bench | — | 1,367 |

## Agentic & Tool Use

- Command R: —
- Gemini 3 Flash Preview: 38.7 (#29)

| Benchmark | Command R | Gemini 3 Flash Preview |
|---|---|---|
| Terminal-Bench | — | 64.3% |
| τ²-bench Airline | — | 82.5% |
| τ²-bench Banking | — | 27.3% |
| τ²-bench Retail | — | 76.8% |
| τ²-bench Telecom | — | 91.2% |
| DeepResearch Bench | — | 49.8% |
| BALROG | — | 48.1% |
| GDP.pdf | — | 10% |
| LMArena Search | — | 1198 |
| Vending-Bench 2 | — | 3,635 |

## Reasoning

- Command R: 13.8 (#331)
- Gemini 3 Flash Preview: 49.2 (#37)

| Benchmark | Command R | Gemini 3 Flash Preview |
|---|---|---|
| LMArena Hard Prompts | 1164 | 1465 |
| DTBench | 46.4% | 89.1% |
| LMCA | 9.2% | 43.1% |
| ARC-AGI-2 | — | 33.6% |
| SimpleBench | — | 61.1% |
| NYT Connections (extended) | — | 83.1% |
| ARC-AGI-1 | — | 84.7% |
| Chess Puzzles | — | 40% |
| LiveBench Reasoning | 21.9% | — |
| Mystery Game Puzzles | — | 26% |
| LiveBench Data Analysis | 33.3% | — |
| Epoch Capabilities Index | — | 151.8 |
| ForecastBench | — | 58.5 |
| LiveBench | 27.5% | — |

## Math

- Command R: 28.0 (#246)
- Gemini 3 Flash Preview: 51.7 (#55)

| Benchmark | Command R | Gemini 3 Flash Preview |
|---|---|---|
| LMArena Math | 1155 | 1473 |
| FrontierMath (Tiers 1-3) | — | 51.2% |
| FrontierMath Tier 4 | — | 17.1% |
| MathArena Final-Answer Competitions | — | 67.6% |
| OTIS Mock AIME 2024-2025 | — | 95.6% |
| ProofBench | — | 15% |
| LiveBench Math | 19.4% | — |
| FrontierMath (Feb 2025 set) | — | 35.6% |
| FrontierMath Tier 4 (v1) | — | 4.2% |

## Knowledge

- Command R: 31.0 (#221)
- Gemini 3 Flash Preview: 58.8 (#33)

| Benchmark | Command R | Gemini 3 Flash Preview |
|---|---|---|
| LMArena Expert | 1138 | 1462 |
| GPQA Diamond | — | 89.4% |
| SimpleQA Verified | — | 66.8% |
| Vectara Hallucination Rate | — | 13.5% |
| MMLU | 65.2% | — |

## Multimodal

- Command R: —
- Gemini 3 Flash Preview: 45.5 (#16)

| Benchmark | Command R | Gemini 3 Flash Preview |
|---|---|---|
| LMArena Vision | — | 1285 |
| GeoBench | — | 88% |
| VPCT | — | 72.6% |
| Blueprint-Bench 2 | — | 0% |
| LMArena Document | — | 1413 |

## Multilingual

- Command R: 35.7 (#245)
- Gemini 3 Flash Preview: 55.7 (#27)

| Benchmark | Command R | Gemini 3 Flash Preview |
|---|---|---|
| LMArena Non-English | 1174 | 1458 |
| LMArena Chinese | 1182 | 1511 |
| LMArena French | 1162 | 1477 |
| LMArena German | 1176 | 1497 |
| LMArena Japanese | 1143 | 1489 |
| LMArena Korean | 1163 | 1443 |
| LMArena Russian | 1174 | 1480 |
| LMArena Spanish | 1151 | 1469 |

## Instruction Following

- Command R: 58.1 (#261)
- Gemini 3 Flash Preview: 75.7 (#56)

| Benchmark | Command R | Gemini 3 Flash Preview |
|---|---|---|
| LMArena Instruction Following | 1167 | 1437 |
| LiveBench Instruction Following | 55.6% | — |

## Long Context

- Command R: 36.3 (#231)
- Gemini 3 Flash Preview: 44.4 (#67)

| Benchmark | Command R | Gemini 3 Flash Preview |
|---|---|---|
| LMArena Longer Query | 1198 | 1452 |

## Writing & Preference

- Command R: 38.2 (#254)
- Gemini 3 Flash Preview: 65.5 (#45)

| Benchmark | Command R | Gemini 3 Flash Preview |
|---|---|---|
| LMArena Text | 1187 | 1466 |
| LMArena Creative Writing | 1170 | 1457 |
| LMArena Multi-Turn | 1163 | 1471 |
| LiveBench Language | 16.7% | — |

## FAQ

### Is Command R better than Gemini 3 Flash Preview?

Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 31.4 on the Noometry Index. Command R costs 4.3× less per token, which makes it the better buy when Gemini 3 Flash Preview's lead doesn't matter for your workload.

### Which is cheaper, Command R or Gemini 3 Flash Preview?

Command R is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Gemini 3 Flash Preview lists at $0.50 and $3.

### Is Command R or Gemini 3 Flash Preview better for coding?

Gemini 3 Flash Preview scores higher on coding benchmarks: 50.9 versus 29.3 in the Noometry coding category.

### Which has the bigger context window?

Gemini 3 Flash Preview does, with 1.05M tokens against 128K.

### How many benchmarks do Command R and Gemini 3 Flash Preview share?

19 benchmarks have published results for both models. Command R has 29 scored results on Noometry and Gemini 3 Flash Preview has 59.