# Kimi K2.7 Code vs Llama 4 Maverick

> Kimi K2.7 Code is the stronger model overall, scoring 43.3 to 30.9 on the Noometry Index. Llama 4 Maverick costs 5.6× 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-llama-4-maverick
- Last updated: 2026-10-11
- Shared benchmarks: 8

## Summary

- They share 8 benchmarks with published results for both. Kimi K2.7 Code scores higher in 4 categories and Llama 4 Maverick in 1 category; 5 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Kimi K2.7 Code leads 39.0 to 10.1.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 95.6% for Kimi K2.7 Code and 20.6% for Llama 4 Maverick.
- Llama 4 Maverick is cheaper at $0.19 / $0.65 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.

## Snapshot

| | Kimi K2.7 Code | Llama 4 Maverick |
|---|---|---|
| Provider | Moonshot AI | Meta |
| Noometry Index | 43.3 | 30.9 |
| Rank | 94 | 282 |
| Context | 262K | 128K |
| Input $/M | $0.95 | $0.19 |
| Output $/M | $4 | $0.65 |
| Weights | Open | Open |

## Coding

- Kimi K2.7 Code: 42.9 (#95)
- Llama 4 Maverick: 26.6 (#324)

| Benchmark | Kimi K2.7 Code | Llama 4 Maverick |
|---|---|---|
| SciCode | 47.5% | 33.1% |
| WeirdML | 54.1% | 24.5% |
| ALE-Bench | 886.23 | 172.97 |
| DeepSWE | 30.5% | — |
| FrontierCode | 30.1% | — |
| SWE-bench Verified (bash only) | — | 21% |
| Aider Polyglot | — | 15.6% |
| LMArena WebDev | 1473 | — |
| BigCodeBench Instruct | — | 49.7% |
| LMArena Coding | — | 1302 |
| BigCodeBench Complete | — | 61.4% |

## Agentic & Tool Use

- Kimi K2.7 Code: 24.0 (#122)
- Llama 4 Maverick: 28.2 (#91)

| Benchmark | Kimi K2.7 Code | Llama 4 Maverick |
|---|---|---|
| APEX-Agents | 37.6% | — |
| Berkeley Function Calling Leaderboard | — | 37.3% |
| GBAEval | 0.9% | — |
| Vending-Bench 2 | 5,083 | — |

## Reasoning

- Kimi K2.7 Code: 39.0 (#61)
- Llama 4 Maverick: 10.1 (#342)

| Benchmark | Kimi K2.7 Code | Llama 4 Maverick |
|---|---|---|
| SimpleBench | 57.9% | 27.7% |
| CritPt | 10% | 0% |
| Epoch Capabilities Index | 149.97 | 132.2 |
| ARC-AGI-2 | — | 0% |
| Kagi LLM Benchmark | — | 55.9% |
| NYT Connections (extended) | — | 8% |
| ARC-AGI-1 | — | 4.4% |
| Chess Puzzles | 21% | — |
| EnigmaEval | — | 0.6% |
| LMArena Hard Prompts | — | 1281 |
| DTBench | — | 61.9% |
| LMCA | — | 15.9% |
| Surface Evolver Bench | 48.8% | — |
| ForecastBench | — | 57.5 |

## Math

- Kimi K2.7 Code: 52.9 (#48)
- Llama 4 Maverick: 26.0 (#262)

| Benchmark | Kimi K2.7 Code | Llama 4 Maverick |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 95.6% | 20.6% |
| FrontierMath (Tiers 1-3) | 54% | — |
| FrontierMath Tier 4 | 12.2% | — |
| Omni-MATH | — | 42.2% |
| LMArena Math | — | 1299 |
| MATH Level 5 | — | 73% |
| FrontierMath (Feb 2025 set) | — | 0.7% |

## Knowledge

- Kimi K2.7 Code: 53.5 (#57)
- Llama 4 Maverick: 33.4 (#204)

| Benchmark | Kimi K2.7 Code | Llama 4 Maverick |
|---|---|---|
| GPQA Diamond | 87.9% | 67% |
| Humanity's Last Exam | — | 5.7% |
| SimpleQA Verified | 36.5% | — |
| MMLU-Pro | — | 81% |
| Confabulations | — | 22.6% |
| Vectara Hallucination Rate | — | 8.2% |
| GPQA (HELM) | — | 65% |
| LMArena Expert | — | 1259 |

## Multimodal

- Kimi K2.7 Code: —
- Llama 4 Maverick: 31.6 (#105)

| Benchmark | Kimi K2.7 Code | Llama 4 Maverick |
|---|---|---|
| LMArena Vision | — | 1142 |
| GeoBench | — | 52% |
| SpatialViz-Bench | — | 31.8% |

## Multilingual

- Kimi K2.7 Code: —
- Llama 4 Maverick: 42.2 (#195)

| Benchmark | Kimi K2.7 Code | Llama 4 Maverick |
|---|---|---|
| LMArena Non-English | — | 1269 |
| LMArena Chinese | — | 1277 |
| LMArena French | — | 1259 |
| LMArena German | — | 1291 |
| LMArena Japanese | — | 1207 |
| LMArena Korean | — | 1203 |
| LMArena Russian | — | 1286 |
| LMArena Spanish | — | 1293 |

## Instruction Following

- Kimi K2.7 Code: —
- Llama 4 Maverick: 71.7 (#146)

| Benchmark | Kimi K2.7 Code | Llama 4 Maverick |
|---|---|---|
| IFEval | — | 90.8% |
| LMArena Instruction Following | — | 1267 |

## Long Context

- Kimi K2.7 Code: —
- Llama 4 Maverick: 31.4 (#279)

| Benchmark | Kimi K2.7 Code | Llama 4 Maverick |
|---|---|---|
| Fiction.LiveBench | — | 46.2% |
| LMArena Longer Query | — | 1280 |

## Writing & Preference

- Kimi K2.7 Code: —
- Llama 4 Maverick: 38.8 (#252)

| Benchmark | Kimi K2.7 Code | Llama 4 Maverick |
|---|---|---|
| LMArena Text | — | 1287 |
| LMArena Creative Writing | — | 1267 |
| Short-Story Creative Writing | — | 62% |
| EQ-Bench Creative Writing | — | 860 |
| WildBench | — | 80% |
| LMArena Multi-Turn | — | 1289 |

## FAQ

### Is Kimi K2.7 Code better than Llama 4 Maverick?

Kimi K2.7 Code is the stronger model overall, scoring 43.3 to 30.9 on the Noometry Index. Llama 4 Maverick costs 5.6× 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 Llama 4 Maverick?

Llama 4 Maverick is cheaper. It lists at $0.19 per million input tokens and $0.65 per million output tokens; Kimi K2.7 Code lists at $0.95 and $4.

### Is Kimi K2.7 Code or Llama 4 Maverick better for coding?

Kimi K2.7 Code scores higher on coding benchmarks: 42.9 versus 26.6 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 Llama 4 Maverick share?

8 benchmarks have published results for both models. Kimi K2.7 Code has 19 scored results on Noometry and Llama 4 Maverick has 54.