# Kimi K2.7 Code vs Mercury 2

> Kimi K2.7 Code is the stronger model overall, scoring 43.0 to 38.8 on the Noometry Index. Mercury 2 costs 4.6× less per token, which makes it the better buy when Kimi K2.7 Code's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/kimi-k2-7-code-vs-mercury-2
- Last updated: 2026-10-10
- Shared benchmarks: 5

## Summary

- They share 5 benchmarks with published results for both. Kimi K2.7 Code scores higher in 3 categories and Mercury 2 in 0 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Kimi K2.7 Code leads 53.6 to 35.6.
- The biggest single-benchmark swing is WeirdML: 54.1% for Kimi K2.7 Code and 43.2% for Mercury 2.
- Mercury 2 is cheaper at $0.25 / $0.75 per million input/output tokens, against $0.95 / $4 for Kimi K2.7 Code.
- Kimi K2.7 Code accepts more context: 262K tokens versus 128K.
- Kimi K2.7 Code has downloadable open weights; the other is API-only.

## Snapshot

| | Kimi K2.7 Code | Mercury 2 |
|---|---|---|
| Provider | Moonshot AI | Inception |
| Noometry Index | 43.0 | 38.8 |
| Rank | 90 | 167 |
| Context | 262K | 128K |
| Input $/M | $0.95 | $0.25 |
| Output $/M | $4 | $0.75 |
| Weights | Open | Proprietary |

## Coding

- Kimi K2.7 Code: 42.4 (#92)
- Mercury 2: 33.2 (#250)

| Benchmark | Kimi K2.7 Code | Mercury 2 |
|---|---|---|
| LMArena WebDev | 1473 | 1170 |
| SciCode | 47.5% | 38.7% |
| WeirdML | 54.1% | 43.2% |
| ALE-Bench | 886.23 | 785.58 |
| DeepSWE | 30.5% | — |
| FrontierCode | 30.1% | — |
| LMArena Coding | — | 1391 |

## Agentic & Tool Use

- Kimi K2.7 Code: 23.9 (#115)
- Mercury 2: —

| Benchmark | Kimi K2.7 Code | Mercury 2 |
|---|---|---|
| APEX-Agents | 37.6% | — |
| GBAEval | 0.9% | — |
| Vending-Bench 2 | 5,083 | — |

## Reasoning

- Kimi K2.7 Code: 38.2 (#56)
- Mercury 2: 23.0 (#170)

| Benchmark | Kimi K2.7 Code | Mercury 2 |
|---|---|---|
| CritPt | 10% | 0.8% |
| SimpleBench | 57.9% | — |
| Chess Puzzles | 21% | — |
| LMArena Hard Prompts | — | 1362 |
| Surface Evolver Bench | 48.8% | — |
| Epoch Capabilities Index | 150.01 | — |

## Math

- Kimi K2.7 Code: 52.6 (#39)
- Mercury 2: —

| Benchmark | Kimi K2.7 Code | Mercury 2 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 54% | — |
| FrontierMath Tier 4 | 12.2% | — |
| OTIS Mock AIME 2024-2025 | 95.6% | — |

## Knowledge

- Kimi K2.7 Code: 53.6 (#51)
- Mercury 2: 35.6 (#170)

| Benchmark | Kimi K2.7 Code | Mercury 2 |
|---|---|---|
| GPQA Diamond | 87.9% | — |
| SimpleQA Verified | 36.5% | — |
| Vectara Hallucination Rate | — | 12.3% |
| LMArena Expert | — | 1358 |

## Multilingual

- Kimi K2.7 Code: —
- Mercury 2: 46.8 (#153)

| Benchmark | Kimi K2.7 Code | Mercury 2 |
|---|---|---|
| LMArena Non-English | — | 1331 |
| LMArena Chinese | — | 1416 |
| LMArena Russian | — | 1303 |

## Instruction Following

- Kimi K2.7 Code: —
- Mercury 2: 70.4 (#161)

| Benchmark | Kimi K2.7 Code | Mercury 2 |
|---|---|---|
| LMArena Instruction Following | — | 1328 |

## Long Context

- Kimi K2.7 Code: —
- Mercury 2: 40.4 (#149)

| Benchmark | Kimi K2.7 Code | Mercury 2 |
|---|---|---|
| LMArena Longer Query | — | 1329 |

## Writing & Preference

- Kimi K2.7 Code: —
- Mercury 2: 54.0 (#151)

| Benchmark | Kimi K2.7 Code | Mercury 2 |
|---|---|---|
| LMArena Text | — | 1355 |
| LMArena Creative Writing | — | 1289 |
| LMArena Multi-Turn | — | 1358 |

## FAQ

### Is Kimi K2.7 Code better than Mercury 2?

Kimi K2.7 Code is the stronger model overall, scoring 43.0 to 38.8 on the Noometry Index. Mercury 2 costs 4.6× less per token, which makes it the better buy when Kimi K2.7 Code's lead doesn't matter for your workload.

### Which is cheaper, Kimi K2.7 Code or Mercury 2?

Mercury 2 is cheaper. It lists at $0.25 per million input tokens and $0.75 per million output tokens; Kimi K2.7 Code lists at $0.95 and $4.

### Is Kimi K2.7 Code or Mercury 2 better for coding?

Kimi K2.7 Code scores higher on coding benchmarks: 42.4 versus 33.2 in the Noometry coding category.

### Which has the bigger context window?

Kimi K2.7 Code does, with 262K tokens against 128K.

### How many benchmarks do Kimi K2.7 Code and Mercury 2 share?

5 benchmarks have published results for both models. Kimi K2.7 Code has 19 scored results on Noometry and Mercury 2 has 17.