Model comparison
Command A vs Kimi K2 Thinking Turbo
Kimi K2 Thinking Turbo is the stronger model overall, scoring 45.8 to 36.5 on the Noometry Index.
Last verified . 17 shared benchmarks.
CohereSummary
- They share 17 benchmarks with published results for both. Command A scores higher in 0 categories and Kimi K2 Thinking Turbo in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Kimi K2 Thinking Turbo leads 32.5 to 18.3.
Side by side
| Command A | Kimi K2 Thinking Turbo | |
|---|---|---|
| Provider | Cohere | Moonshot AI |
| Noometry Index | 36.5 | 45.8 |
| Released | 2025-03-13 | 2025-11-06 |
| Weights | Open | Open |
| Context window | 256K | — |
| Max output | 8K | — |
| Input $ / M tokens | $2.50 | — |
| Output $ / M tokens | $10 | — |
| Results tracked | 24 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2 Thinking Turbo leads
Command A: 27.2 (#322), Kimi K2 Thinking Turbo: 38.4 (#178)
| Benchmark | Command A | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Coding | 1330 | 1454 |
| Aider Polyglot | 12% | — |
| LMArena WebDev | — | 1322 |
Agentic & Tool Use Not comparable
Command A: 35.9 (#40), Kimi K2 Thinking Turbo: —
| Benchmark | Command A | Kimi K2 Thinking Turbo |
|---|---|---|
| Berkeley Function Calling Leaderboard | 57.1% | — |
Reasoning Kimi K2 Thinking Turbo leads
Command A: 18.3 (#283), Kimi K2 Thinking Turbo: 32.5 (#75)
| Benchmark | Command A | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Hard Prompts | 1326 | 1428 |
| Kagi LLM Benchmark | 28.8% | — |
| Chess Puzzles | — | 20% |
| DTBench | 61.3% | — |
| LMCA | 10.3% | — |
Math Kimi K2 Thinking Turbo leads
Command A: 36.2 (#171), Kimi K2 Thinking Turbo: 47.4 (#68)
| Benchmark | Command A | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Math | 1300 | 1429 |
| OTIS Mock AIME 2024-2025 | — | 83.1% |
Knowledge Kimi K2 Thinking Turbo leads
Command A: 37.1 (#159), Kimi K2 Thinking Turbo: 50.9 (#69)
| Benchmark | Command A | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Expert | 1295 | 1439 |
| GPQA Diamond | — | 84.2% |
| Vectara Hallucination Rate | 9.3% | — |
Multilingual Kimi K2 Thinking Turbo leads
Command A: 45.3 (#170), Kimi K2 Thinking Turbo: 51.4 (#109)
| Benchmark | Command A | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Non-English | 1313 | 1398 |
| LMArena Chinese | 1327 | 1456 |
| LMArena French | 1351 | 1425 |
| LMArena German | 1341 | 1390 |
| LMArena Japanese | 1285 | 1357 |
| LMArena Korean | 1285 | 1330 |
| LMArena Russian | 1314 | 1391 |
| LMArena Spanish | 1347 | 1406 |
Instruction Following Kimi K2 Thinking Turbo leads
Command A: 69.1 (#177), Kimi K2 Thinking Turbo: 74.0 (#109)
| Benchmark | Command A | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Instruction Following | 1309 | 1403 |
Long Context Kimi K2 Thinking Turbo leads
Command A: 40.6 (#151), Kimi K2 Thinking Turbo: 43.2 (#102)
| Benchmark | Command A | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Longer Query | 1334 | 1415 |
Writing & Preference Kimi K2 Thinking Turbo leads
Command A: 47.6 (#208), Kimi K2 Thinking Turbo: 60.0 (#104)
| Benchmark | Command A | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Text | 1331 | 1415 |
| LMArena Creative Writing | 1319 | 1374 |
| LMArena Multi-Turn | 1339 | 1414 |
| EQ-Bench Creative Writing | 1145 | — |
Frequently asked questions
Is Command A better than Kimi K2 Thinking Turbo?
Kimi K2 Thinking Turbo is the stronger model overall, scoring 45.8 to 36.5 on the Noometry Index.
Is Command A or Kimi K2 Thinking Turbo better for coding?
Kimi K2 Thinking Turbo scores higher on coding benchmarks: 38.4 versus 27.2 in the Noometry coding category.
How many benchmarks do Command A and Kimi K2 Thinking Turbo share?
17 benchmarks have published results for both models. Command A has 24 scored results on Noometry and Kimi K2 Thinking Turbo has 21.