Model comparison
Command A vs Kimi K2 (Jul 2025)
Kimi K2 (Jul 2025) is the stronger model overall, scoring 40.9 to 35.9 on the Noometry Index.
Last verified . 22 shared benchmarks.
CohereSummary
- They share 22 benchmarks with published results for both. Command A scores higher in 1 category and Kimi K2 (Jul 2025) in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in coding, where Kimi K2 (Jul 2025) leads 43.1 to 26.8.
- The biggest single-benchmark swing is Aider Polyglot: 12% for Command A and 59.1% for Kimi K2 (Jul 2025).
- Kimi K2 (Jul 2025) is cheaper at $0.57 / $2.30 per million input/output tokens, against $2.50 / $10 for Command A.
- Kimi K2 (Jul 2025) accepts more context: 262K tokens versus 256K.
Side by side
| Command A | Kimi K2 (Jul 2025) | |
|---|---|---|
| Provider | Cohere | Moonshot AI |
| Noometry Index | 35.9 | 40.9 |
| Released | 2025-03-13 | 2025-07-12 |
| Weights | Open | Open |
| Context window | 256K | 262K |
| Max output | 8K | 262K |
| Input $ / M tokens | $2.50 | $0.57 |
| Output $ / M tokens | $10 | $2.30 |
| Results tracked | 24 | 42 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2 (Jul 2025) leads
Command A: 26.8 (#317), Kimi K2 (Jul 2025): 43.1 (#83)
| Benchmark | Command A | Kimi K2 (Jul 2025) |
|---|---|---|
| Aider Polyglot | 12% | 59.1% |
| LMArena Coding | 1331 | 1399 |
| SWE-bench Verified (bash only) | — | 63.4% |
| GSO | — | 4.9% |
| WeirdML | — | 42.8% |
| ALE-Bench | — | 597.5 |
Agentic & Tool Use Command A leads
Command A: 35.7 (#36), Kimi K2 (Jul 2025): 32.2 (#59)
| Benchmark | Command A | Kimi K2 (Jul 2025) |
|---|---|---|
| Berkeley Function Calling Leaderboard | 57.1% | 59.1% |
| Terminal-Bench | — | 35.7% |
| METR Time Horizons | — | 59.2% |
Reasoning Kimi K2 (Jul 2025) leads
Command A: 17.7 (#276), Kimi K2 (Jul 2025): 22.7 (#173)
| Benchmark | Command A | Kimi K2 (Jul 2025) |
|---|---|---|
| Kagi LLM Benchmark | 28.8% | 64.4% |
| LMArena Hard Prompts | 1326 | 1384 |
| SimpleBench | — | 26.3% |
| DTBench | 61.3% | — |
| LMCA | 10.3% | — |
| Epoch Capabilities Index | — | 146.02 |
| ForecastBench | — | 60.2 |
Math Kimi K2 (Jul 2025) leads
Command A: 33.5 (#172), Kimi K2 (Jul 2025): 40.1 (#81)
| Benchmark | Command A | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Math | 1300 | 1396 |
| Omni-MATH | — | 65.4% |
| FrontierMath (Feb 2025 set) | — | 21.4% |
| FrontierMath Tier 4 (v1) | — | 0% |
Knowledge Too close to call
Command A: 36.5 (#157), Kimi K2 (Jul 2025): 36.9 (#153)
| Benchmark | Command A | Kimi K2 (Jul 2025) |
|---|---|---|
| Vectara Hallucination Rate | 9.3% | 17.9% |
| LMArena Expert | 1295 | 1363 |
| MMLU-Pro | — | 81.9% |
| Confabulations | — | 20.4% |
| GPQA (HELM) | — | 65.3% |
Multilingual Kimi K2 (Jul 2025) leads
Command A: 45.5 (#166), Kimi K2 (Jul 2025): 49.8 (#125)
| Benchmark | Command A | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Non-English | 1313 | 1372 |
| LMArena Chinese | 1327 | 1416 |
| LMArena French | 1352 | 1379 |
| LMArena German | 1341 | 1386 |
| LMArena Japanese | 1283 | 1349 |
| LMArena Korean | 1285 | 1324 |
| LMArena Russian | 1314 | 1384 |
| LMArena Spanish | 1346 | 1383 |
Instruction Following Kimi K2 (Jul 2025) leads
Command A: 69.3 (#172), Kimi K2 (Jul 2025): 71.3 (#151)
| Benchmark | Command A | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Instruction Following | 1309 | 1347 |
| IFEval | — | 85% |
Long Context Too close to call
Command A: 40.6 (#147), Kimi K2 (Jul 2025): 41.2 (#140)
| Benchmark | Command A | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Longer Query | 1334 | 1353 |
| Fiction.LiveBench | — | 66.7% |
| CL-bench | — | 17.6% |
Writing & Preference Kimi K2 (Jul 2025) leads
Command A: 47.8 (#204), Kimi K2 (Jul 2025): 62.5 (#76)
| Benchmark | Command A | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Text | 1331 | 1380 |
| LMArena Creative Writing | 1319 | 1349 |
| EQ-Bench Creative Writing | 1145 | 1666 |
| LMArena Multi-Turn | 1338 | 1371 |
| Short-Story Creative Writing | — | 85.6% |
| WildBench | — | 86.2% |
Frequently asked questions
Is Command A better than Kimi K2 (Jul 2025)?
Kimi K2 (Jul 2025) is the stronger model overall, scoring 40.9 to 35.9 on the Noometry Index.
Which is cheaper, Command A or Kimi K2 (Jul 2025)?
Kimi K2 (Jul 2025) is cheaper. It lists at $0.57 per million input tokens and $2.30 per million output tokens; Command A lists at $2.50 and $10.
Is Command A or Kimi K2 (Jul 2025) better for coding?
Kimi K2 (Jul 2025) scores higher on coding benchmarks: 43.1 versus 26.8 in the Noometry coding category.
Which has the bigger context window?
Kimi K2 (Jul 2025) does, with 262K tokens against 256K.
How many benchmarks do Command A and Kimi K2 (Jul 2025) share?
22 benchmarks have published results for both models. Command A has 24 scored results on Noometry and Kimi K2 (Jul 2025) has 42.