Model comparison
Command R+ vs Gemini 2.5 Flash
Gemini 2.5 Flash is the stronger model overall, scoring 39.3 to 32.4 on the Noometry Index.
Last verified . 22 shared benchmarks.
Cohere
GoogleSummary
- They share 22 benchmarks with published results for both. Command R+ scores higher in 0 categories and Gemini 2.5 Flash in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Gemini 2.5 Flash leads 75.7 to 60.0.
- The biggest single-benchmark swing is SimpleBench: 17.4% for Command R+ and 41.2% for Gemini 2.5 Flash.
- Gemini 2.5 Flash is cheaper at $0.30 / $2.50 per million input/output tokens, against $2.50 / $10 for Command R+.
- Gemini 2.5 Flash accepts more context: 1.05M tokens versus 128K.
- Command R+ has downloadable open weights; the other is API-only.
Side by side
| Command R+ | Gemini 2.5 Flash | |
|---|---|---|
| Provider | Cohere | |
| Noometry Index | 32.4 | 39.3 |
| Released | 2024-08-30 | 2025-04-17 |
| Weights | Open | Proprietary |
| Context window | 128K | 1.05M |
| Max output | 4K | 66K |
| Input $ / M tokens | $2.50 | $0.30 |
| Output $ / M tokens | $10 | $2.50 |
| Results tracked | 34 | 54 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 2.5 Flash leads
Command R+: 29.1 (#309), Gemini 2.5 Flash: 35.8 (#220)
| Benchmark | Command R+ | Gemini 2.5 Flash |
|---|---|---|
| LMArena Coding | 1187 | 1424 |
| SWE-bench Verified (bash only) | — | 28.7% |
| Aider Polyglot | — | 55.1% |
| WeirdML | — | 41.9% |
| BigCodeBench Instruct | 33.8% | — |
| LiveBench Coding | 19.1% | — |
| BigCodeBench Complete | 41.9% | — |
| ALE-Bench | — | 661.88 |
| HumanEval+ | 56.7% | — |
| MBPP+ | 63.5% | — |
Agentic & Tool Use Not comparable
Command R+: —, Gemini 2.5 Flash: 30.8 (#74)
| Benchmark | Command R+ | Gemini 2.5 Flash |
|---|---|---|
| Terminal-Bench | — | 17.1% |
| Berkeley Function Calling Leaderboard | — | 56.2% |
| TheAgentCompany | — | 41.1% |
| BALROG | — | 33.5% |
| Vending-Bench 2 | — | 548.84 |
Reasoning Gemini 2.5 Flash leads
Command R+: 9.2 (#344), Gemini 2.5 Flash: 18.1 (#286)
| Benchmark | Command R+ | Gemini 2.5 Flash |
|---|---|---|
| SimpleBench | 17.4% | 41.2% |
| LMArena Hard Prompts | 1186 | 1422 |
| DTBench | 54.9% | 76.5% |
| LMCA | 5% | 27.5% |
| Epoch Capabilities Index | 119.34 | 143.03 |
| ARC-AGI-2 | — | 2.5% |
| Kagi LLM Benchmark | — | 56.8% |
| ARC-AGI-1 | — | 33.3% |
| CritPt | — | 1.1% |
| EnigmaEval | — | 2.7% |
| LiveBench Reasoning | 24.8% | — |
| LiveBench Data Analysis | 38.1% | — |
| ForecastBench | — | 60.6 |
| LiveBench | 31.8% | — |
Math Gemini 2.5 Flash leads
Command R+: 28.9 (#242), Gemini 2.5 Flash: 39.9 (#98)
| Benchmark | Command R+ | Gemini 2.5 Flash |
|---|---|---|
| LMArena Math | 1188 | 1415 |
| OTIS Mock AIME 2024-2025 | — | 73.1% |
| Omni-MATH | — | 38.5% |
| LiveBench Math | 21.3% | — |
| FrontierMath (Feb 2025 set) | — | 4.8% |
| FrontierMath Tier 4 (v1) | — | 4.2% |
Knowledge Too close to call
Command R+: 36.4 (#169), Gemini 2.5 Flash: 36.4 (#168)
| Benchmark | Command R+ | Gemini 2.5 Flash |
|---|---|---|
| Vectara Hallucination Rate | 6.9% | 7.8% |
| LMArena Expert | 1174 | 1426 |
| Humanity's Last Exam | — | 12.1% |
| MMLU-Pro | — | 63.9% |
| Confabulations | — | 16.8% |
| GPQA (HELM) | — | 39% |
| MMLU | 69.4% | — |
Multimodal Not comparable
Command R+: —, Gemini 2.5 Flash: 41.8 (#32)
| Benchmark | Command R+ | Gemini 2.5 Flash |
|---|---|---|
| LMArena Vision | — | 1253 |
| GeoBench | — | 76% |
| VPCT | — | 46.2% |
| SpatialViz-Bench | — | 36.9% |
Multilingual Gemini 2.5 Flash leads
Command R+: 38.6 (#227), Gemini 2.5 Flash: 52.3 (#88)
| Benchmark | Command R+ | Gemini 2.5 Flash |
|---|---|---|
| LMArena Non-English | 1216 | 1409 |
| LMArena Chinese | 1226 | 1450 |
| LMArena French | 1209 | 1433 |
| LMArena German | 1216 | 1418 |
| LMArena Japanese | 1166 | 1405 |
| LMArena Korean | 1138 | 1385 |
| LMArena Russian | 1227 | 1415 |
| LMArena Spanish | 1189 | 1421 |
Instruction Following Gemini 2.5 Flash leads
Command R+: 60.0 (#254), Gemini 2.5 Flash: 75.7 (#54)
| Benchmark | Command R+ | Gemini 2.5 Flash |
|---|---|---|
| LMArena Instruction Following | 1197 | 1405 |
| LiveBench Instruction Following | 57.6% | — |
| IFEval | — | 89.8% |
Long Context Gemini 2.5 Flash leads
Command R+: 37.3 (#219), Gemini 2.5 Flash: 47.5 (#17)
| Benchmark | Command R+ | Gemini 2.5 Flash |
|---|---|---|
| LMArena Longer Query | 1230 | 1419 |
| Fiction.LiveBench | — | 77.8% |
Writing & Preference Gemini 2.5 Flash leads
Command R+: 43.5 (#228), Gemini 2.5 Flash: 53.8 (#157)
| Benchmark | Command R+ | Gemini 2.5 Flash |
|---|---|---|
| LMArena Text | 1229 | 1417 |
| LMArena Creative Writing | 1235 | 1400 |
| LMArena Multi-Turn | 1213 | 1408 |
| Short-Story Creative Writing | — | 76.5% |
| EQ-Bench Creative Writing | — | 1137 |
| WildBench | — | 81.7% |
| LiveBench Language | 29.7% | — |
Frequently asked questions
Is Command R+ better than Gemini 2.5 Flash?
Gemini 2.5 Flash is the stronger model overall, scoring 39.3 to 32.4 on the Noometry Index.
Which is cheaper, Command R+ or Gemini 2.5 Flash?
Gemini 2.5 Flash is cheaper. It lists at $0.30 per million input tokens and $2.50 per million output tokens; Command R+ lists at $2.50 and $10.
Is Command R+ or Gemini 2.5 Flash better for coding?
Gemini 2.5 Flash scores higher on coding benchmarks: 35.8 versus 29.1 in the Noometry coding category.
Which has the bigger context window?
Gemini 2.5 Flash does, with 1.05M tokens against 128K.
How many benchmarks do Command R+ and Gemini 2.5 Flash share?
22 benchmarks have published results for both models. Command R+ has 34 scored results on Noometry and Gemini 2.5 Flash has 54.