Model comparison
Command R+ vs Kimi K2.5
Kimi K2.5 is the stronger model overall, scoring 48.1 to 32.4 on the Noometry Index.
Last verified . 20 shared benchmarks.
CohereSummary
- They share 20 benchmarks with published results for both. Command R+ scores higher in 0 categories and Kimi K2.5 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Kimi K2.5 leads 51.8 to 28.9.
- The biggest single-benchmark swing is SimpleBench: 17.4% for Command R+ and 46.8% for Kimi K2.5.
- Kimi K2.5 is cheaper at $0.45 / $2.25 per million input/output tokens, against $2.50 / $10 for Command R+.
- Kimi K2.5 accepts more context: 262K tokens versus 128K.
Side by side
| Command R+ | Kimi K2.5 | |
|---|---|---|
| Provider | Cohere | Moonshot AI |
| Noometry Index | 32.4 | 48.1 |
| Released | 2024-08-30 | 2026-01-27 |
| Weights | Open | Open |
| Context window | 128K | 262K |
| Max output | 4K | 262K |
| Input $ / M tokens | $2.50 | $0.45 |
| Output $ / M tokens | $10 | $2.25 |
| Results tracked | 34 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2.5 leads
Command R+: 29.1 (#309), Kimi K2.5: 48.8 (#53)
| Benchmark | Command R+ | Kimi K2.5 |
|---|---|---|
| LMArena Coding | 1187 | 1474 |
| SWE-bench Verified | — | 73.8% |
| SWE-bench Verified (bash only) | — | 70.8% |
| LMArena WebDev | — | 1437 |
| SWE-bench Multilingual | — | 67.3% |
| SciCode | — | 49% |
| WeirdML | — | 45.6% |
| BigCodeBench Instruct | 33.8% | — |
| LiveBench Coding | 19.1% | — |
| BigCodeBench Complete | 41.9% | — |
| ALE-Bench | — | 821.65 |
| HumanEval+ | 56.7% | — |
| MBPP+ | 63.5% | — |
Agentic & Tool Use Not comparable
Command R+: —, Kimi K2.5: 34.2 (#48)
| Benchmark | Command R+ | Kimi K2.5 |
|---|---|---|
| Terminal-Bench | — | 43.2% |
| OSWorld | — | 63.3% |
| Vending-Bench 2 | — | 1,198 |
Reasoning Kimi K2.5 leads
Command R+: 9.2 (#344), Kimi K2.5: 31.2 (#80)
| Benchmark | Command R+ | Kimi K2.5 |
|---|---|---|
| SimpleBench | 17.4% | 46.8% |
| LMArena Hard Prompts | 1186 | 1453 |
| Epoch Capabilities Index | 119.34 | 148.03 |
| ARC-AGI-2 | — | 11.8% |
| Kagi LLM Benchmark | — | 78.5% |
| NYT Connections (extended) | — | 69.9% |
| ARC-AGI-1 | — | 65.3% |
| CritPt | — | 3.1% |
| Chess Puzzles | — | 12% |
| EnigmaEval | — | 3.4% |
| Thematic Generalization | — | 69.4% |
| LiveBench Reasoning | 24.8% | — |
| DTBench | 54.9% | — |
| LiveBench Data Analysis | 38.1% | — |
| LMCA | 5% | — |
| LiveBench | 31.8% | — |
Math Kimi K2.5 leads
Command R+: 28.9 (#242), Kimi K2.5: 51.8 (#53)
| Benchmark | Command R+ | Kimi K2.5 |
|---|---|---|
| LMArena Math | 1188 | 1470 |
| MathArena Final-Answer Competitions | — | 62.3% |
| OTIS Mock AIME 2024-2025 | — | 92.2% |
| LiveBench Math | 21.3% | — |
| FrontierMath (Feb 2025 set) | — | 27.9% |
| FrontierMath Tier 4 (v1) | — | 4.2% |
Knowledge Kimi K2.5 leads
Command R+: 36.4 (#169), Kimi K2.5: 53.6 (#56)
| Benchmark | Command R+ | Kimi K2.5 |
|---|---|---|
| Vectara Hallucination Rate | 6.9% | 14.2% |
| LMArena Expert | 1174 | 1466 |
| GPQA Diamond | — | 87.6% |
| Humanity's Last Exam | — | 24.4% |
| SimpleQA Verified | — | 34.3% |
| MMLU | 69.4% | — |
Multimodal Not comparable
Command R+: —, Kimi K2.5: 41.1 (#39)
| Benchmark | Command R+ | Kimi K2.5 |
|---|---|---|
| LMArena Vision | — | 1269 |
| LMArena Document | — | 1430 |
Multilingual Kimi K2.5 leads
Command R+: 38.6 (#227), Kimi K2.5: 53.9 (#53)
| Benchmark | Command R+ | Kimi K2.5 |
|---|---|---|
| LMArena Non-English | 1216 | 1433 |
| LMArena Chinese | 1226 | 1495 |
| LMArena French | 1209 | 1454 |
| LMArena German | 1216 | 1441 |
| LMArena Japanese | 1166 | 1421 |
| LMArena Korean | 1138 | 1410 |
| LMArena Russian | 1227 | 1435 |
| LMArena Spanish | 1189 | 1450 |
Instruction Following Kimi K2.5 leads
Command R+: 60.0 (#254), Kimi K2.5: 75.3 (#64)
| Benchmark | Command R+ | Kimi K2.5 |
|---|---|---|
| LMArena Instruction Following | 1197 | 1431 |
| LiveBench Instruction Following | 57.6% | — |
Long Context Kimi K2.5 leads
Command R+: 37.3 (#219), Kimi K2.5: 52.1 (#7)
| Benchmark | Command R+ | Kimi K2.5 |
|---|---|---|
| LMArena Longer Query | 1230 | 1445 |
| Fiction.LiveBench | — | 86.1% |
| CL-bench | — | 19.3% |
| CL-bench Life | — | 13.2% |
Writing & Preference Kimi K2.5 leads
Command R+: 43.5 (#228), Kimi K2.5: 65.1 (#53)
| Benchmark | Command R+ | Kimi K2.5 |
|---|---|---|
| LMArena Text | 1229 | 1445 |
| LMArena Creative Writing | 1235 | 1423 |
| LMArena Multi-Turn | 1213 | 1444 |
| EQ-Bench Creative Writing | — | 1579 |
| LiveBench Language | 29.7% | — |
Frequently asked questions
Is Command R+ better than Kimi K2.5?
Kimi K2.5 is the stronger model overall, scoring 48.1 to 32.4 on the Noometry Index.
Which is cheaper, Command R+ or Kimi K2.5?
Kimi K2.5 is cheaper. It lists at $0.45 per million input tokens and $2.25 per million output tokens; Command R+ lists at $2.50 and $10.
Is Command R+ or Kimi K2.5 better for coding?
Kimi K2.5 scores higher on coding benchmarks: 48.8 versus 29.1 in the Noometry coding category.
Which has the bigger context window?
Kimi K2.5 does, with 262K tokens against 128K.
How many benchmarks do Command R+ and Kimi K2.5 share?
20 benchmarks have published results for both models. Command R+ has 34 scored results on Noometry and Kimi K2.5 has 51.