Model comparison
Kimi K2 Thinking Turbo vs Sonar
Kimi K2 Thinking Turbo is the stronger model overall, scoring 45.8 to 38.5 on the Noometry Index.
Last verified . 0 shared benchmarks.
PerplexitySummary
- The widest gap is in math, where Kimi K2 Thinking Turbo leads 47.4 to 33.7.
- Kimi K2 Thinking Turbo has downloadable open weights; the other is API-only.
Side by side
| Kimi K2 Thinking Turbo | Sonar | |
|---|---|---|
| Provider | Moonshot AI | Perplexity |
| Noometry Index | 45.8 | 38.5 |
| Released | 2025-11-06 | 2024-01-01 |
| Weights | Open | Proprietary |
| Context window | — | 128K |
| Max output | — | 4K |
| Input $ / M tokens | — | $1 |
| Output $ / M tokens | — | $1 |
| Results tracked | 21 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2 Thinking Turbo leads
Kimi K2 Thinking Turbo: 38.4 (#178), Sonar: 35.7 (#221)
| Benchmark | Kimi K2 Thinking Turbo | Sonar |
|---|---|---|
| LMArena WebDev | 1322 | — |
| LiveBench Coding | — | 35.1% |
| LMArena Coding | 1454 | — |
Reasoning Kimi K2 Thinking Turbo leads
Kimi K2 Thinking Turbo: 32.5 (#75), Sonar: 21.1 (#227)
| Benchmark | Kimi K2 Thinking Turbo | Sonar |
|---|---|---|
| Chess Puzzles | 20% | — |
| LiveBench Reasoning | — | 46.3% |
| LMArena Hard Prompts | 1428 | — |
| LiveBench Data Analysis | — | 37.9% |
| LiveBench | — | 46.9% |
Math Kimi K2 Thinking Turbo leads
Kimi K2 Thinking Turbo: 47.4 (#68), Sonar: 33.7 (#200)
| Benchmark | Kimi K2 Thinking Turbo | Sonar |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 83.1% | — |
| LiveBench Math | — | 41.6% |
| LMArena Math | 1429 | — |
Knowledge Not comparable
Kimi K2 Thinking Turbo: 50.9 (#69), Sonar: —
| Benchmark | Kimi K2 Thinking Turbo | Sonar |
|---|---|---|
| GPQA Diamond | 84.2% | — |
| LMArena Expert | 1439 | — |
Multilingual Not comparable
Kimi K2 Thinking Turbo: 51.4 (#109), Sonar: —
| Benchmark | Kimi K2 Thinking Turbo | Sonar |
|---|---|---|
| LMArena Non-English | 1398 | — |
| LMArena Chinese | 1456 | — |
| LMArena French | 1425 | — |
| LMArena German | 1390 | — |
| LMArena Japanese | 1357 | — |
| LMArena Korean | 1330 | — |
| LMArena Russian | 1391 | — |
| LMArena Spanish | 1406 | — |
Instruction Following Kimi K2 Thinking Turbo leads
Kimi K2 Thinking Turbo: 74.0 (#109), Sonar: 71.4 (#150)
| Benchmark | Kimi K2 Thinking Turbo | Sonar |
|---|---|---|
| LiveBench Instruction Following | — | 76.2% |
| LMArena Instruction Following | 1403 | — |
Long Context Not comparable
Kimi K2 Thinking Turbo: 43.2 (#102), Sonar: —
| Benchmark | Kimi K2 Thinking Turbo | Sonar |
|---|---|---|
| LMArena Longer Query | 1415 | — |
Writing & Preference Kimi K2 Thinking Turbo leads
Kimi K2 Thinking Turbo: 60.0 (#104), Sonar: 52.6 (#167)
| Benchmark | Kimi K2 Thinking Turbo | Sonar |
|---|---|---|
| LMArena Text | 1415 | — |
| LMArena Creative Writing | 1374 | — |
| LMArena Multi-Turn | 1414 | — |
| LiveBench Language | — | 44.1% |
Frequently asked questions
Is Kimi K2 Thinking Turbo better than Sonar?
Kimi K2 Thinking Turbo is the stronger model overall, scoring 45.8 to 38.5 on the Noometry Index.
Is Kimi K2 Thinking Turbo or Sonar better for coding?
Kimi K2 Thinking Turbo scores higher on coding benchmarks: 38.4 versus 35.7 in the Noometry coding category.
How many benchmarks do Kimi K2 Thinking Turbo and Sonar share?
0 benchmarks have published results for both models. Kimi K2 Thinking Turbo has 21 scored results on Noometry and Sonar has 7.