# DBRX vs Kimi K2.5

> Kimi K2.5 is the stronger model overall, scoring 47.8 to 29.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/dbrx-vs-kimi-k2-5
- Last updated: 2026-10-10
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. DBRX scores higher in 0 categories and Kimi K2.5 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Kimi K2.5 leads 53.6 to 14.9.
- The biggest single-benchmark swing is GPQA Diamond: 32.9% for DBRX and 87.6% for Kimi K2.5.

## Snapshot

| | DBRX | Kimi K2.5 |
|---|---|---|
| Provider | Databricks | Moonshot AI |
| Noometry Index | 29.0 | 47.8 |
| Rank | 307 | 50 |
| Context | — | 262K |
| Input $/M | — | $0.45 |
| Output $/M | — | $2.25 |
| Weights | Open | Open |

## Coding

- DBRX: 32.3 (#262)
- Kimi K2.5: 48.7 (#48)

| Benchmark | DBRX | Kimi K2.5 |
|---|---|---|
| LMArena Coding | 1132 | 1474 |
| SWE-bench Verified | — | 73.8% |
| SWE-bench Verified (bash only) | — | 70.8% |
| LMArena WebDev | — | 1436 |
| SWE-bench Multilingual | — | 67.3% |
| SciCode | — | 49% |
| WeirdML | — | 45.6% |
| ALE-Bench | — | 821.65 |
| HumanEval+ | 70.1% | — |
| MBPP+ | 55.8% | — |

## Agentic & Tool Use

- DBRX: —
- Kimi K2.5: 34.0 (#44)

| Benchmark | DBRX | Kimi K2.5 |
|---|---|---|
| Terminal-Bench | — | 43.2% |
| OSWorld | — | 63.3% |
| Vending-Bench 2 | — | 1,198 |

## Reasoning

- DBRX: 20.5 (#218)
- Kimi K2.5: 31.2 (#74)

| Benchmark | DBRX | Kimi K2.5 |
|---|---|---|
| LMArena Hard Prompts | 1113 | 1454 |
| ARC-AGI-2 | — | 11.8% |
| SimpleBench | — | 46.8% |
| Kagi LLM Benchmark | — | 78.5% |
| NYT Connections (extended) | — | 69.9% |
| ARC-AGI-1 | — | 65.3% |
| CritPt | — | 3.1% |
| Chess Puzzles | — | 12% |
| EnigmaEval | — | 3.4% |
| Thematic Generalization | — | 69.4% |
| Epoch Capabilities Index | — | 148.05 |

## Math

- DBRX: 22.3 (#265)
- Kimi K2.5: 50.3 (#46)

| Benchmark | DBRX | Kimi K2.5 |
|---|---|---|
| LMArena Math | 1145 | 1470 |
| MathArena Final-Answer Competitions | — | 62.3% |
| OTIS Mock AIME 2024-2025 | — | 92.2% |
| MATH Level 5 | 11.7% | — |
| FrontierMath (Feb 2025 set) | — | 27.9% |
| FrontierMath Tier 4 (v1) | — | 4.2% |

## Knowledge

- DBRX: 14.9 (#289)
- Kimi K2.5: 53.6 (#52)

| Benchmark | DBRX | Kimi K2.5 |
|---|---|---|
| GPQA Diamond | 32.9% | 87.6% |
| LMArena Expert | 1076 | 1466 |
| Humanity's Last Exam | — | 24.4% |
| SimpleQA Verified | — | 34.3% |
| Vectara Hallucination Rate | — | 14.2% |

## Multimodal

- DBRX: —
- Kimi K2.5: 40.4 (#37)

| Benchmark | DBRX | Kimi K2.5 |
|---|---|---|
| LMArena Vision | — | 1269 |
| LMArena Document | — | 1430 |

## Multilingual

- DBRX: 29.4 (#263)
- Kimi K2.5: 54.1 (#50)

| Benchmark | DBRX | Kimi K2.5 |
|---|---|---|
| LMArena Non-English | 1071 | 1433 |
| LMArena Chinese | 1068 | 1495 |
| LMArena French | 1095 | 1454 |
| LMArena German | 1057 | 1441 |
| LMArena Japanese | 990 | 1422 |
| LMArena Korean | 993 | 1412 |
| LMArena Russian | 1078 | 1436 |
| LMArena Spanish | 1064 | 1450 |

## Instruction Following

- DBRX: 57.7 (#265)
- Kimi K2.5: 75.5 (#60)

| Benchmark | DBRX | Kimi K2.5 |
|---|---|---|
| LMArena Instruction Following | 1112 | 1431 |

## Long Context

- DBRX: 33.7 (#253)
- Kimi K2.5: 52.1 (#7)

| Benchmark | DBRX | Kimi K2.5 |
|---|---|---|
| LMArena Longer Query | 1112 | 1445 |
| Fiction.LiveBench | — | 86.1% |
| CL-bench | — | 19.3% |
| CL-bench Life | — | 13.2% |

## Writing & Preference

- DBRX: 33.7 (#271)
- Kimi K2.5: 65.3 (#51)

| Benchmark | DBRX | Kimi K2.5 |
|---|---|---|
| LMArena Text | 1119 | 1445 |
| LMArena Creative Writing | 1104 | 1423 |
| LMArena Multi-Turn | 1111 | 1444 |
| EQ-Bench Creative Writing | — | 1579 |

## FAQ

### Is DBRX better than Kimi K2.5?

Kimi K2.5 is the stronger model overall, scoring 47.8 to 29.0 on the Noometry Index.

### Is DBRX or Kimi K2.5 better for coding?

Kimi K2.5 scores higher on coding benchmarks: 48.7 versus 32.3 in the Noometry coding category.

### How many benchmarks do DBRX and Kimi K2.5 share?

18 benchmarks have published results for both models. DBRX has 21 scored results on Noometry and Kimi K2.5 has 51.