# DeepSeek Coder 33B vs Kimi K2 (Jul 2025)

> Kimi K2 (Jul 2025) has enough public results to be ranked (#134); DeepSeek Coder 33B does not yet, so treat this comparison as directional.

- Canonical page: https://noometry.com/compare/deepseek-coder-33b-vs-kimi-k2
- Last updated: 2026-10-10
- Shared benchmarks: 1

## Summary

- They share 1 benchmark with published results for both. DeepSeek Coder 33B scores higher in 0 categories and Kimi K2 (Jul 2025) in 1 category; one gap is clear of the uncertainty.
- The widest gap is in coding, where Kimi K2 (Jul 2025) leads 43.1 to 37.4.

## Snapshot

| | DeepSeek Coder 33B | Kimi K2 (Jul 2025) |
|---|---|---|
| Provider | DeepSeek | Moonshot AI |
| Noometry Index | 38.3 | 40.9 |
| Rank | — | 134 |
| Context | — | 262K |
| Input $/M | — | $0.57 |
| Output $/M | — | $2.30 |
| Weights | Open | Open |

## Coding

- DeepSeek Coder 33B: 37.4 (#180)
- Kimi K2 (Jul 2025): 43.1 (#83)

| Benchmark | DeepSeek Coder 33B | Kimi K2 (Jul 2025) |
|---|---|---|
| SWE-bench Verified (bash only) | — | 63.4% |
| Aider Polyglot | — | 59.1% |
| GSO | — | 4.9% |
| WeirdML | — | 42.8% |
| BigCodeBench Instruct | 42% | — |
| LMArena Coding | — | 1399 |
| BigCodeBench Complete | 51.1% | — |
| ALE-Bench | — | 597.5 |
| HumanEval+ | 75% | — |
| MBPP+ | 70.1% | — |

## Agentic & Tool Use

- DeepSeek Coder 33B: —
- Kimi K2 (Jul 2025): 32.2 (#59)

| Benchmark | DeepSeek Coder 33B | Kimi K2 (Jul 2025) |
|---|---|---|
| Terminal-Bench | — | 35.7% |
| Berkeley Function Calling Leaderboard | — | 59.1% |
| METR Time Horizons | — | 59.2% |

## Reasoning

- DeepSeek Coder 33B: —
- Kimi K2 (Jul 2025): 22.7 (#173)

| Benchmark | DeepSeek Coder 33B | Kimi K2 (Jul 2025) |
|---|---|---|
| Epoch Capabilities Index | 95.74 | 146.02 |
| SimpleBench | — | 26.3% |
| Kagi LLM Benchmark | — | 64.4% |
| LMArena Hard Prompts | — | 1384 |
| ForecastBench | — | 60.2 |
| WinoGrande | 62% | — |

## Math

- DeepSeek Coder 33B: —
- Kimi K2 (Jul 2025): 40.1 (#81)

| Benchmark | DeepSeek Coder 33B | Kimi K2 (Jul 2025) |
|---|---|---|
| Omni-MATH | — | 65.4% |
| LMArena Math | — | 1396 |
| FrontierMath (Feb 2025 set) | — | 21.4% |
| FrontierMath Tier 4 (v1) | — | 0% |
| GSM8K | 35.4% | — |

## Knowledge

- DeepSeek Coder 33B: —
- Kimi K2 (Jul 2025): 36.9 (#153)

| Benchmark | DeepSeek Coder 33B | Kimi K2 (Jul 2025) |
|---|---|---|
| MMLU-Pro | — | 81.9% |
| Confabulations | — | 20.4% |
| Vectara Hallucination Rate | — | 17.9% |
| GPQA (HELM) | — | 65.3% |
| LMArena Expert | — | 1363 |
| ARC (AI2) Challenge | 42.2% | — |
| MMLU | 39.4% | — |

## Multilingual

- DeepSeek Coder 33B: —
- Kimi K2 (Jul 2025): 49.8 (#125)

| Benchmark | DeepSeek Coder 33B | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Non-English | — | 1372 |
| LMArena Chinese | — | 1416 |
| LMArena French | — | 1379 |
| LMArena German | — | 1386 |
| LMArena Japanese | — | 1349 |
| LMArena Korean | — | 1324 |
| LMArena Russian | — | 1384 |
| LMArena Spanish | — | 1383 |

## Instruction Following

- DeepSeek Coder 33B: —
- Kimi K2 (Jul 2025): 71.3 (#151)

| Benchmark | DeepSeek Coder 33B | Kimi K2 (Jul 2025) |
|---|---|---|
| IFEval | — | 85% |
| LMArena Instruction Following | — | 1347 |

## Long Context

- DeepSeek Coder 33B: —
- Kimi K2 (Jul 2025): 41.2 (#140)

| Benchmark | DeepSeek Coder 33B | Kimi K2 (Jul 2025) |
|---|---|---|
| Fiction.LiveBench | — | 66.7% |
| CL-bench | — | 17.6% |
| LMArena Longer Query | — | 1353 |

## Writing & Preference

- DeepSeek Coder 33B: —
- Kimi K2 (Jul 2025): 62.5 (#76)

| Benchmark | DeepSeek Coder 33B | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Text | — | 1380 |
| LMArena Creative Writing | — | 1349 |
| Short-Story Creative Writing | — | 85.6% |
| EQ-Bench Creative Writing | — | 1666 |
| WildBench | — | 86.2% |
| LMArena Multi-Turn | — | 1371 |

## FAQ

### Is DeepSeek Coder 33B better than Kimi K2 (Jul 2025)?

Kimi K2 (Jul 2025) has enough public results to be ranked (#134); DeepSeek Coder 33B does not yet, so treat this comparison as directional.

### Is DeepSeek Coder 33B or Kimi K2 (Jul 2025) better for coding?

Kimi K2 (Jul 2025) scores higher on coding benchmarks: 43.1 versus 37.4 in the Noometry coding category.

### How many benchmarks do DeepSeek Coder 33B and Kimi K2 (Jul 2025) share?

1 benchmark has published results for both models. DeepSeek Coder 33B has 9 scored results on Noometry and Kimi K2 (Jul 2025) has 42.