# Kimi K2.7 Code vs Qwen3-30B-A3B

> Kimi K2.7 Code is the stronger model overall, scoring 43.0 to 38.5 on the Noometry Index. Qwen3-30B-A3B costs 8.0× 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-qwen3-30b-a3b
- Last updated: 2026-10-10
- Shared benchmarks: 7

## Summary

- They share 7 benchmarks with published results for both. Kimi K2.7 Code scores higher in 4 categories and Qwen3-30B-A3B in 1 category; 5 gaps are clear of the uncertainty.
- The widest gap is in math, where Kimi K2.7 Code leads 52.6 to 36.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 95.6% for Kimi K2.7 Code and 70.3% for Qwen3-30B-A3B.
- Qwen3-30B-A3B is cheaper at $0.12 / $0.50 per million input/output tokens, against $0.95 / $4 for Kimi K2.7 Code.
- Kimi K2.7 Code accepts more context: 262K tokens versus 41K.

## Snapshot

| | Kimi K2.7 Code | Qwen3-30B-A3B |
|---|---|---|
| Provider | Moonshot AI | Alibaba (Qwen) |
| Noometry Index | 43.0 | 38.5 |
| Rank | 90 | 174 |
| Context | 262K | 41K |
| Input $/M | $0.95 | $0.12 |
| Output $/M | $4 | $0.50 |
| Weights | Open | Open |

## Coding

- Kimi K2.7 Code: 42.4 (#92)
- Qwen3-30B-A3B: 37.0 (#188)

| Benchmark | Kimi K2.7 Code | Qwen3-30B-A3B |
|---|---|---|
| SciCode | 47.5% | 33.3% |
| WeirdML | 54.1% | 29.8% |
| DeepSWE | 30.5% | — |
| FrontierCode | 30.1% | — |
| LMArena WebDev | 1473 | — |
| LMArena Coding | — | 1416 |
| ALE-Bench | 886.23 | — |

## Agentic & Tool Use

- Kimi K2.7 Code: 23.9 (#115)
- Qwen3-30B-A3B: 29.5 (#75)

| Benchmark | Kimi K2.7 Code | Qwen3-30B-A3B |
|---|---|---|
| APEX-Agents | 37.6% | — |
| Berkeley Function Calling Leaderboard | — | 41.4% |
| GBAEval | 0.9% | — |
| Vending-Bench 2 | 5,083 | — |

## Reasoning

- Kimi K2.7 Code: 38.2 (#56)
- Qwen3-30B-A3B: 21.6 (#193)

| Benchmark | Kimi K2.7 Code | Qwen3-30B-A3B |
|---|---|---|
| CritPt | 10% | 0.3% |
| Chess Puzzles | 21% | 8% |
| Epoch Capabilities Index | 150.01 | 139.63 |
| SimpleBench | 57.9% | — |
| Kagi LLM Benchmark | — | 54.9% |
| LMArena Hard Prompts | — | 1398 |
| DTBench | — | 69.3% |
| LMCA | — | 22.4% |
| Surface Evolver Bench | 48.8% | — |

## Math

- Kimi K2.7 Code: 52.6 (#39)
- Qwen3-30B-A3B: 36.0 (#133)

| Benchmark | Kimi K2.7 Code | Qwen3-30B-A3B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 95.6% | 70.3% |
| FrontierMath (Tiers 1-3) | 54% | — |
| FrontierMath Tier 4 | 12.2% | — |
| MathArena Final-Answer Competitions | — | 47.8% |
| LMArena Math | — | 1394 |

## Knowledge

- Kimi K2.7 Code: 53.6 (#51)
- Qwen3-30B-A3B: 41.7 (#96)

| Benchmark | Kimi K2.7 Code | Qwen3-30B-A3B |
|---|---|---|
| GPQA Diamond | 87.9% | 70.1% |
| SimpleQA Verified | 36.5% | — |
| Confabulations | — | 12.3% |
| LMArena Expert | — | 1395 |

## Multilingual

- Kimi K2.7 Code: —
- Qwen3-30B-A3B: 49.8 (#126)

| Benchmark | Kimi K2.7 Code | Qwen3-30B-A3B |
|---|---|---|
| LMArena Non-English | — | 1372 |
| LMArena Chinese | — | 1434 |
| LMArena French | — | 1419 |
| LMArena German | — | 1379 |
| LMArena Japanese | — | 1338 |
| LMArena Korean | — | 1333 |
| LMArena Russian | — | 1369 |
| LMArena Spanish | — | 1403 |

## Instruction Following

- Kimi K2.7 Code: —
- Qwen3-30B-A3B: 72.2 (#137)

| Benchmark | Kimi K2.7 Code | Qwen3-30B-A3B |
|---|---|---|
| LMArena Instruction Following | — | 1364 |

## Long Context

- Kimi K2.7 Code: —
- Qwen3-30B-A3B: 31.0 (#278)

| Benchmark | Kimi K2.7 Code | Qwen3-30B-A3B |
|---|---|---|
| Fiction.LiveBench | — | 40.6% |
| LMArena Longer Query | — | 1379 |

## Writing & Preference

- Kimi K2.7 Code: —
- Qwen3-30B-A3B: 55.9 (#138)

| Benchmark | Kimi K2.7 Code | Qwen3-30B-A3B |
|---|---|---|
| LMArena Text | — | 1384 |
| LMArena Creative Writing | — | 1318 |
| Short-Story Creative Writing | — | 75.3% |
| LMArena Multi-Turn | — | 1378 |

## FAQ

### Is Kimi K2.7 Code better than Qwen3-30B-A3B?

Kimi K2.7 Code is the stronger model overall, scoring 43.0 to 38.5 on the Noometry Index. Qwen3-30B-A3B costs 8.0× 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 Qwen3-30B-A3B?

Qwen3-30B-A3B is cheaper. It lists at $0.12 per million input tokens and $0.50 per million output tokens; Kimi K2.7 Code lists at $0.95 and $4.

### Is Kimi K2.7 Code or Qwen3-30B-A3B better for coding?

Kimi K2.7 Code scores higher on coding benchmarks: 42.4 versus 37.0 in the Noometry coding category.

### Which has the bigger context window?

Kimi K2.7 Code does, with 262K tokens against 41K.

### How many benchmarks do Kimi K2.7 Code and Qwen3-30B-A3B share?

7 benchmarks have published results for both models. Kimi K2.7 Code has 19 scored results on Noometry and Qwen3-30B-A3B has 32.