# Kimi K2.7 Code vs Nemotron 3 Ultra

> Nemotron 3 Ultra is the stronger model overall, scoring 44.7 to 43.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/kimi-k2-7-code-vs-nemotron-3-ultra
- Last updated: 2026-10-10
- Shared benchmarks: 8

## Summary

- They share 8 benchmarks with published results for both. Kimi K2.7 Code scores higher in 4 categories and Nemotron 3 Ultra in 0 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in math, where Kimi K2.7 Code leads 52.6 to 34.4.
- The biggest single-benchmark swing is FrontierCode: 30.1% for Kimi K2.7 Code and 13.6% for Nemotron 3 Ultra.
- Nemotron 3 Ultra is cheaper at $0.60 / $2.40 per million input/output tokens, against $0.95 / $4 for Kimi K2.7 Code.

## Snapshot

| | Kimi K2.7 Code | Nemotron 3 Ultra |
|---|---|---|
| Provider | Moonshot AI | NVIDIA |
| Noometry Index | 43.0 | 44.7 |
| Rank | 90 | 71 |
| Context | 262K | 262K |
| Input $/M | $0.95 | $0.60 |
| Output $/M | $4 | $2.40 |
| Weights | Open | Open |

## Coding

- Kimi K2.7 Code: 42.4 (#92)
- Nemotron 3 Ultra: 37.7 (#174)

| Benchmark | Kimi K2.7 Code | Nemotron 3 Ultra |
|---|---|---|
| FrontierCode | 30.1% | 13.6% |
| SciCode | 47.5% | 40.3% |
| WeirdML | 54.1% | 43.5% |
| DeepSWE | 30.5% | — |
| LMArena WebDev | 1473 | — |
| LMArena Coding | — | 1468 |
| ALE-Bench | 886.23 | — |

## Agentic & Tool Use

- Kimi K2.7 Code: 23.9 (#115)
- Nemotron 3 Ultra: —

| Benchmark | Kimi K2.7 Code | Nemotron 3 Ultra |
|---|---|---|
| APEX-Agents | 37.6% | — |
| GBAEval | 0.9% | — |
| Vending-Bench 2 | 5,083 | — |

## Reasoning

- Kimi K2.7 Code: 38.2 (#56)
- Nemotron 3 Ultra: 30.3 (#78)

| Benchmark | Kimi K2.7 Code | Nemotron 3 Ultra |
|---|---|---|
| CritPt | 10% | 3.1% |
| Chess Puzzles | 21% | 12% |
| Epoch Capabilities Index | 150.01 | 146.2 |
| SimpleBench | 57.9% | — |
| LMArena Hard Prompts | — | 1452 |
| Mystery Game Puzzles | — | 20% |
| DTBench | — | 90.1% |
| LMCA | — | 36.9% |
| Surface Evolver Bench | 48.8% | — |

## Math

- Kimi K2.7 Code: 52.6 (#39)
- Nemotron 3 Ultra: 34.4 (#160)

| Benchmark | Kimi K2.7 Code | Nemotron 3 Ultra |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 95.6% | 86.7% |
| FrontierMath (Tiers 1-3) | 54% | — |
| FrontierMath Tier 4 | 12.2% | — |
| ProofBench | — | 2% |
| LMArena Math | — | 1456 |

## Knowledge

- Kimi K2.7 Code: 53.6 (#51)
- Nemotron 3 Ultra: 52.5 (#56)

| Benchmark | Kimi K2.7 Code | Nemotron 3 Ultra |
|---|---|---|
| GPQA Diamond | 87.9% | 85.4% |
| SimpleQA Verified | 36.5% | — |
| LMArena Expert | — | 1472 |

## Multilingual

- Kimi K2.7 Code: —
- Nemotron 3 Ultra: 53.7 (#61)

| Benchmark | Kimi K2.7 Code | Nemotron 3 Ultra |
|---|---|---|
| LMArena Non-English | — | 1427 |
| LMArena Chinese | — | 1498 |
| LMArena French | — | 1475 |
| LMArena German | — | 1471 |
| LMArena Korean | — | 1387 |
| LMArena Russian | — | 1415 |
| LMArena Spanish | — | 1452 |

## Instruction Following

- Kimi K2.7 Code: —
- Nemotron 3 Ultra: 74.9 (#84)

| Benchmark | Kimi K2.7 Code | Nemotron 3 Ultra |
|---|---|---|
| LMArena Instruction Following | — | 1417 |

## Long Context

- Kimi K2.7 Code: —
- Nemotron 3 Ultra: 43.9 (#77)

| Benchmark | Kimi K2.7 Code | Nemotron 3 Ultra |
|---|---|---|
| LMArena Longer Query | — | 1437 |

## Writing & Preference

- Kimi K2.7 Code: —
- Nemotron 3 Ultra: 66.3 (#35)

| Benchmark | Kimi K2.7 Code | Nemotron 3 Ultra |
|---|---|---|
| LMArena Text | — | 1444 |
| LMArena Creative Writing | — | 1392 |
| EQ-Bench Creative Writing | — | 1692 |
| LMArena Multi-Turn | — | 1412 |

## FAQ

### Is Kimi K2.7 Code better than Nemotron 3 Ultra?

Nemotron 3 Ultra is the stronger model overall, scoring 44.7 to 43.0 on the Noometry Index.

### Which is cheaper, Kimi K2.7 Code or Nemotron 3 Ultra?

Nemotron 3 Ultra is cheaper. It lists at $0.60 per million input tokens and $2.40 per million output tokens; Kimi K2.7 Code lists at $0.95 and $4.

### Is Kimi K2.7 Code or Nemotron 3 Ultra better for coding?

Kimi K2.7 Code scores higher on coding benchmarks: 42.4 versus 37.7 in the Noometry coding category.

### Which has the bigger context window?

Both accept 262K tokens.

### How many benchmarks do Kimi K2.7 Code and Nemotron 3 Ultra share?

8 benchmarks have published results for both models. Kimi K2.7 Code has 19 scored results on Noometry and Nemotron 3 Ultra has 29.