Model comparison
Kimi K2 Thinking Turbo vs Mercury
Kimi K2 Thinking Turbo is the stronger model overall, scoring 45.8 to 37.6 on the Noometry Index.
Last verified . 8 shared benchmarks.
Summary
- They share 8 benchmarks with published results for both. Kimi K2 Thinking Turbo scores higher in 5 categories and Mercury in 1 category; 5 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Kimi K2 Thinking Turbo leads 32.5 to 17.5.
- Kimi K2 Thinking Turbo has downloadable open weights; the other is API-only.
Side by side
| Kimi K2 Thinking Turbo | Mercury | |
|---|---|---|
| Provider | Moonshot AI | Inception |
| Noometry Index | 45.8 | 37.6 |
| Released | 2025-11-06 | — |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 21 | 9 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Kimi K2 Thinking Turbo: 38.4 (#178), Mercury: 38.7 (#170)
| Benchmark | Kimi K2 Thinking Turbo | Mercury |
|---|---|---|
| LMArena Coding | 1454 | 1322 |
| LMArena WebDev | 1322 | — |
Reasoning Kimi K2 Thinking Turbo leads
Kimi K2 Thinking Turbo: 32.5 (#75), Mercury: 17.5 (#293)
| Benchmark | Kimi K2 Thinking Turbo | Mercury |
|---|---|---|
| LMArena Hard Prompts | 1428 | 1285 |
| Kagi LLM Benchmark | — | 21.6% |
| Chess Puzzles | 20% | — |
Math Not comparable
Kimi K2 Thinking Turbo: 47.4 (#68), Mercury: —
| Benchmark | Kimi K2 Thinking Turbo | Mercury |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 83.1% | — |
| LMArena Math | 1429 | — |
Knowledge Not comparable
Kimi K2 Thinking Turbo: 50.9 (#69), Mercury: —
| Benchmark | Kimi K2 Thinking Turbo | Mercury |
|---|---|---|
| GPQA Diamond | 84.2% | — |
| LMArena Expert | 1439 | — |
Multilingual Kimi K2 Thinking Turbo leads
Kimi K2 Thinking Turbo: 51.4 (#109), Mercury: 41.6 (#206)
| Benchmark | Kimi K2 Thinking Turbo | Mercury |
|---|---|---|
| LMArena Non-English | 1398 | 1260 |
| 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), Mercury: 65.2 (#224)
| Benchmark | Kimi K2 Thinking Turbo | Mercury |
|---|---|---|
| LMArena Instruction Following | 1403 | 1239 |
Long Context Kimi K2 Thinking Turbo leads
Kimi K2 Thinking Turbo: 43.2 (#102), Mercury: 38.4 (#198)
| Benchmark | Kimi K2 Thinking Turbo | Mercury |
|---|---|---|
| LMArena Longer Query | 1415 | 1266 |
Writing & Preference Kimi K2 Thinking Turbo leads
Kimi K2 Thinking Turbo: 60.0 (#104), Mercury: 46.2 (#221)
| Benchmark | Kimi K2 Thinking Turbo | Mercury |
|---|---|---|
| LMArena Text | 1415 | 1282 |
| LMArena Creative Writing | 1374 | 1191 |
| LMArena Multi-Turn | 1414 | 1282 |
Frequently asked questions
Is Kimi K2 Thinking Turbo better than Mercury?
Kimi K2 Thinking Turbo is the stronger model overall, scoring 45.8 to 37.6 on the Noometry Index.
Is Kimi K2 Thinking Turbo or Mercury better for coding?
They score almost the same on coding (38.4 vs 38.7); test both on your own repository before choosing.
How many benchmarks do Kimi K2 Thinking Turbo and Mercury share?
8 benchmarks have published results for both models. Kimi K2 Thinking Turbo has 21 scored results on Noometry and Mercury has 9.