Model comparison
Kimi K2 Thinking Turbo vs MiniMax-M2.7
Kimi K2 Thinking Turbo is the stronger model overall, scoring 45.8 to 37.7 on the Noometry Index.
Last verified . 18 shared benchmarks.
MiniMaxSummary
- They share 18 benchmarks with published results for both. Kimi K2 Thinking Turbo scores higher in 5 categories and MiniMax-M2.7 in 3 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Kimi K2 Thinking Turbo leads 47.4 to 25.9.
Side by side
| Kimi K2 Thinking Turbo | MiniMax-M2.7 | |
|---|---|---|
| Provider | Moonshot AI | MiniMax |
| Noometry Index | 45.8 | 37.7 |
| Released | 2025-11-06 | 2026-03-18 |
| Weights | Open | Open |
| Context window | — | 205K |
| Max output | — | 131K |
| Input $ / M tokens | — | $0.30 |
| Output $ / M tokens | — | $1.20 |
| Results tracked | 21 | 30 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2.7 leads
Kimi K2 Thinking Turbo: 38.4 (#178), MiniMax-M2.7: 41.8 (#120)
| Benchmark | Kimi K2 Thinking Turbo | MiniMax-M2.7 |
|---|---|---|
| LMArena WebDev | 1322 | 1398 |
| LMArena Coding | 1454 | 1454 |
| SciCode | — | 47% |
| WeirdML | — | 37% |
| ALE-Bench | — | 599.25 |
Agentic & Tool Use Not comparable
Kimi K2 Thinking Turbo: —, MiniMax-M2.7: 25.1 (#111)
| Benchmark | Kimi K2 Thinking Turbo | MiniMax-M2.7 |
|---|---|---|
| Terminal-Bench | — | 45.1% |
| ExploitBench | — | 13.3% |
| GBAEval | — | 0% |
Reasoning Kimi K2 Thinking Turbo leads
Kimi K2 Thinking Turbo: 32.5 (#75), MiniMax-M2.7: 19.7 (#253)
| Benchmark | Kimi K2 Thinking Turbo | MiniMax-M2.7 |
|---|---|---|
| LMArena Hard Prompts | 1428 | 1422 |
| NYT Connections (extended) | — | 24.7% |
| CritPt | — | 0.6% |
| Chess Puzzles | 20% | — |
| Thematic Generalization | — | 39.3% |
| Epoch Capabilities Index | — | 145.85 |
Math Kimi K2 Thinking Turbo leads
Kimi K2 Thinking Turbo: 47.4 (#68), MiniMax-M2.7: 25.9 (#263)
| Benchmark | Kimi K2 Thinking Turbo | MiniMax-M2.7 |
|---|---|---|
| LMArena Math | 1429 | 1420 |
| OTIS Mock AIME 2024-2025 | 83.1% | — |
| ProofBench | — | 3% |
Knowledge Kimi K2 Thinking Turbo leads
Kimi K2 Thinking Turbo: 50.9 (#69), MiniMax-M2.7: 37.7 (#152)
| Benchmark | Kimi K2 Thinking Turbo | MiniMax-M2.7 |
|---|---|---|
| LMArena Expert | 1439 | 1444 |
| GPQA Diamond | 84.2% | — |
| Vectara Hallucination Rate | — | 12.9% |
Multilingual Kimi K2 Thinking Turbo leads
Kimi K2 Thinking Turbo: 51.4 (#109), MiniMax-M2.7: 50.3 (#123)
| Benchmark | Kimi K2 Thinking Turbo | MiniMax-M2.7 |
|---|---|---|
| LMArena Non-English | 1398 | 1382 |
| LMArena Chinese | 1456 | 1441 |
| LMArena French | 1425 | 1421 |
| LMArena German | 1390 | 1398 |
| LMArena Japanese | 1357 | 1262 |
| LMArena Korean | 1330 | 1313 |
| LMArena Russian | 1391 | 1383 |
| LMArena Spanish | 1406 | 1403 |
Instruction Following Too close to call
Kimi K2 Thinking Turbo: 74.0 (#109), MiniMax-M2.7: 74.1 (#103)
| Benchmark | Kimi K2 Thinking Turbo | MiniMax-M2.7 |
|---|---|---|
| LMArena Instruction Following | 1403 | 1405 |
Long Context Too close to call
Kimi K2 Thinking Turbo: 43.2 (#102), MiniMax-M2.7: 43.3 (#99)
| Benchmark | Kimi K2 Thinking Turbo | MiniMax-M2.7 |
|---|---|---|
| LMArena Longer Query | 1415 | 1419 |
Writing & Preference Kimi K2 Thinking Turbo leads
Kimi K2 Thinking Turbo: 60.0 (#104), MiniMax-M2.7: 58.9 (#112)
| Benchmark | Kimi K2 Thinking Turbo | MiniMax-M2.7 |
|---|---|---|
| LMArena Text | 1415 | 1405 |
| LMArena Creative Writing | 1374 | 1354 |
| LMArena Multi-Turn | 1414 | 1412 |
Frequently asked questions
Is Kimi K2 Thinking Turbo better than MiniMax-M2.7?
Kimi K2 Thinking Turbo is the stronger model overall, scoring 45.8 to 37.7 on the Noometry Index.
Is Kimi K2 Thinking Turbo or MiniMax-M2.7 better for coding?
MiniMax-M2.7 scores higher on coding benchmarks: 41.8 versus 38.4 in the Noometry coding category.
How many benchmarks do Kimi K2 Thinking Turbo and MiniMax-M2.7 share?
18 benchmarks have published results for both models. Kimi K2 Thinking Turbo has 21 scored results on Noometry and MiniMax-M2.7 has 30.