Model comparison
Command A vs Kimi K2.6
Kimi K2.6 is the stronger model overall, scoring 47.7 to 36.5 on the Noometry Index.
Last verified . 21 shared benchmarks.
CohereSummary
- They share 21 benchmarks with published results for both. Command A scores higher in 1 category and Kimi K2.6 in 8 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in coding, where Kimi K2.6 leads 50.7 to 27.2.
- The biggest single-benchmark swing is DTBench: 61.3% for Command A and 90.9% for Kimi K2.6.
- Kimi K2.6 is cheaper at $0.95 / $4 per million input/output tokens, against $2.50 / $10 for Command A.
- Kimi K2.6 accepts more context: 262K tokens versus 256K.
Side by side
| Command A | Kimi K2.6 | |
|---|---|---|
| Provider | Cohere | Moonshot AI |
| Noometry Index | 36.5 | 47.7 |
| Released | 2025-03-13 | 2026-04-20 |
| Weights | Open | Open |
| Context window | 256K | 262K |
| Max output | 8K | 262K |
| Input $ / M tokens | $2.50 | $0.95 |
| Output $ / M tokens | $10 | $4 |
| Results tracked | 24 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2.6 leads
Command A: 27.2 (#322), Kimi K2.6: 50.7 (#43)
| Benchmark | Command A | Kimi K2.6 |
|---|---|---|
| LMArena Coding | 1330 | 1488 |
| SWE-bench Verified | — | 76.7% |
| Aider Polyglot | 12% | — |
| LMArena WebDev | — | 1509 |
| SciCode | — | 53.5% |
| WeirdML | — | 55.9% |
| ALE-Bench | — | 1,093 |
Agentic & Tool Use Command A leads
Command A: 35.9 (#40), Kimi K2.6: 21.9 (#137)
| Benchmark | Command A | Kimi K2.6 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 57.1% | — |
| OSWorld 2.0 | — | 4.6% |
| ExploitBench | — | 18.4% |
| GBAEval | — | 0.9% |
| GDP.pdf | — | 12% |
| Vending-Bench 2 | — | 6,205 |
Reasoning Kimi K2.6 leads
Command A: 18.3 (#283), Kimi K2.6: 40.5 (#55)
| Benchmark | Command A | Kimi K2.6 |
|---|---|---|
| LMArena Hard Prompts | 1326 | 1470 |
| DTBench | 61.3% | 90.9% |
| LMCA | 10.3% | 37.3% |
| Kagi LLM Benchmark | 28.8% | — |
| NYT Connections (extended) | — | 87.2% |
| CritPt | — | 8% |
| Chess Puzzles | — | 26% |
| EBR-Bench | — | 2.4% |
| Mystery Game Puzzles | — | 18% |
| Epoch Capabilities Index | — | 151.05 |
Math Kimi K2.6 leads
Command A: 36.2 (#171), Kimi K2.6: 57.0 (#41)
| Benchmark | Command A | Kimi K2.6 |
|---|---|---|
| LMArena Math | 1300 | 1475 |
| FrontierMath (Tiers 1-3) | — | 57.2% |
| FrontierMath Tier 4 | — | 25.6% |
| MathArena Final-Answer Competitions | — | 72.9% |
| OTIS Mock AIME 2024-2025 | — | 96.1% |
| ProofBench | — | 16% |
| FrontierMath (Feb 2025 set) | — | 39% |
| FrontierMath Tier 4 (v1) | — | 14.6% |
Knowledge Kimi K2.6 leads
Command A: 37.1 (#159), Kimi K2.6: 54.0 (#54)
| Benchmark | Command A | Kimi K2.6 |
|---|---|---|
| Vectara Hallucination Rate | 9.3% | 10.8% |
| LMArena Expert | 1295 | 1491 |
| GPQA Diamond | — | 90.8% |
| SimpleQA Verified | — | 34.9% |
Multimodal Not comparable
Command A: —, Kimi K2.6: 31.6 (#103)
| Benchmark | Command A | Kimi K2.6 |
|---|---|---|
| LMArena Vision | — | 1283 |
| Blueprint-Bench 2 | — | 3.9% |
| Furniture Assembly | — | 21.7% |
| LMArena Document | — | 1451 |
Multilingual Kimi K2.6 leads
Command A: 45.3 (#170), Kimi K2.6: 54.9 (#37)
| Benchmark | Command A | Kimi K2.6 |
|---|---|---|
| LMArena Non-English | 1313 | 1446 |
| LMArena Chinese | 1327 | 1521 |
| LMArena French | 1351 | 1471 |
| LMArena German | 1341 | 1450 |
| LMArena Japanese | 1285 | 1443 |
| LMArena Korean | 1285 | 1427 |
| LMArena Russian | 1314 | 1446 |
| LMArena Spanish | 1347 | 1464 |
Instruction Following Kimi K2.6 leads
Command A: 69.1 (#177), Kimi K2.6: 76.3 (#43)
| Benchmark | Command A | Kimi K2.6 |
|---|---|---|
| LMArena Instruction Following | 1309 | 1451 |
Long Context Kimi K2.6 leads
Command A: 40.6 (#151), Kimi K2.6: 44.9 (#52)
| Benchmark | Command A | Kimi K2.6 |
|---|---|---|
| LMArena Longer Query | 1334 | 1468 |
Writing & Preference Kimi K2.6 leads
Command A: 47.6 (#208), Kimi K2.6: 68.5 (#26)
| Benchmark | Command A | Kimi K2.6 |
|---|---|---|
| LMArena Text | 1331 | 1455 |
| LMArena Creative Writing | 1319 | 1434 |
| EQ-Bench Creative Writing | 1145 | 1725 |
| LMArena Multi-Turn | 1339 | 1453 |
| EQ-Bench 4 | — | 1202 |
Frequently asked questions
Is Command A better than Kimi K2.6?
Kimi K2.6 is the stronger model overall, scoring 47.7 to 36.5 on the Noometry Index.
Which is cheaper, Command A or Kimi K2.6?
Kimi K2.6 is cheaper. It lists at $0.95 per million input tokens and $4 per million output tokens; Command A lists at $2.50 and $10.
Is Command A or Kimi K2.6 better for coding?
Kimi K2.6 scores higher on coding benchmarks: 50.7 versus 27.2 in the Noometry coding category.
Which has the bigger context window?
Kimi K2.6 does, with 262K tokens against 256K.
How many benchmarks do Command A and Kimi K2.6 share?
21 benchmarks have published results for both models. Command A has 24 scored results on Noometry and Kimi K2.6 has 51.