# Kimi K2 Thinking Turbo vs Mercury 2

> Kimi K2 Thinking Turbo is the stronger model overall, scoring 45.4 to 38.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/kimi-k2-thinking-turbo-vs-mercury-2
- Last updated: 2026-10-10
- Shared benchmarks: 12

## Summary

- They share 12 benchmarks with published results for both. Kimi K2 Thinking Turbo scores higher in 7 categories and Mercury 2 in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Kimi K2 Thinking Turbo leads 50.9 to 35.6.
- Kimi K2 Thinking Turbo has downloadable open weights; the other is API-only.

## Snapshot

| | Kimi K2 Thinking Turbo | Mercury 2 |
|---|---|---|
| Provider | Moonshot AI | Inception |
| Noometry Index | 45.4 | 38.8 |
| Rank | 63 | 167 |
| Context | — | 128K |
| Input $/M | — | $0.25 |
| Output $/M | — | $0.75 |
| Weights | Open | Proprietary |

## Coding

- Kimi K2 Thinking Turbo: 38.1 (#166)
- Mercury 2: 33.2 (#250)

| Benchmark | Kimi K2 Thinking Turbo | Mercury 2 |
|---|---|---|
| LMArena WebDev | 1322 | 1170 |
| LMArena Coding | 1454 | 1391 |
| SciCode | — | 38.7% |
| WeirdML | — | 43.2% |
| ALE-Bench | — | 785.58 |

## Reasoning

- Kimi K2 Thinking Turbo: 31.4 (#72)
- Mercury 2: 23.0 (#170)

| Benchmark | Kimi K2 Thinking Turbo | Mercury 2 |
|---|---|---|
| LMArena Hard Prompts | 1428 | 1362 |
| CritPt | — | 0.8% |
| Chess Puzzles | 20% | — |

## Math

- Kimi K2 Thinking Turbo: 45.5 (#62)
- Mercury 2: —

| Benchmark | Kimi K2 Thinking Turbo | Mercury 2 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 83.1% | — |
| LMArena Math | 1429 | — |

## Knowledge

- Kimi K2 Thinking Turbo: 50.9 (#64)
- Mercury 2: 35.6 (#170)

| Benchmark | Kimi K2 Thinking Turbo | Mercury 2 |
|---|---|---|
| LMArena Expert | 1439 | 1358 |
| GPQA Diamond | 84.2% | — |
| Vectara Hallucination Rate | — | 12.3% |

## Multilingual

- Kimi K2 Thinking Turbo: 51.6 (#104)
- Mercury 2: 46.8 (#153)

| Benchmark | Kimi K2 Thinking Turbo | Mercury 2 |
|---|---|---|
| LMArena Non-English | 1398 | 1331 |
| LMArena Chinese | 1457 | 1416 |
| LMArena Russian | 1390 | 1303 |
| LMArena French | 1425 | — |
| LMArena German | 1390 | — |
| LMArena Japanese | 1356 | — |
| LMArena Korean | 1329 | — |
| LMArena Spanish | 1407 | — |

## Instruction Following

- Kimi K2 Thinking Turbo: 74.2 (#103)
- Mercury 2: 70.4 (#161)

| Benchmark | Kimi K2 Thinking Turbo | Mercury 2 |
|---|---|---|
| LMArena Instruction Following | 1403 | 1328 |

## Long Context

- Kimi K2 Thinking Turbo: 43.2 (#99)
- Mercury 2: 40.4 (#149)

| Benchmark | Kimi K2 Thinking Turbo | Mercury 2 |
|---|---|---|
| LMArena Longer Query | 1415 | 1329 |

## Writing & Preference

- Kimi K2 Thinking Turbo: 60.2 (#99)
- Mercury 2: 54.0 (#151)

| Benchmark | Kimi K2 Thinking Turbo | Mercury 2 |
|---|---|---|
| LMArena Text | 1415 | 1355 |
| LMArena Creative Writing | 1373 | 1289 |
| LMArena Multi-Turn | 1414 | 1358 |

## FAQ

### Is Kimi K2 Thinking Turbo better than Mercury 2?

Kimi K2 Thinking Turbo is the stronger model overall, scoring 45.4 to 38.8 on the Noometry Index.

### Is Kimi K2 Thinking Turbo or Mercury 2 better for coding?

Kimi K2 Thinking Turbo scores higher on coding benchmarks: 38.1 versus 33.2 in the Noometry coding category.

### How many benchmarks do Kimi K2 Thinking Turbo and Mercury 2 share?

12 benchmarks have published results for both models. Kimi K2 Thinking Turbo has 21 scored results on Noometry and Mercury 2 has 17.