# Kimi K2.5 vs Wizardlm 70b

> Kimi K2.5 is the stronger model overall, scoring 48.1 to 33.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/kimi-k2-5-vs-wizardlm-70b
- Last updated: 2026-10-11
- Shared benchmarks: 12

## Summary

- They share 12 benchmarks with published results for both. Kimi K2.5 scores higher in 7 categories and Wizardlm 70b in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Kimi K2.5 leads 65.1 to 34.8.

## Snapshot

| | Kimi K2.5 | Wizardlm 70b |
|---|---|---|
| Provider | Moonshot AI | Microsoft |
| Noometry Index | 48.1 | 33.0 |
| Rank | 57 | 249 |
| Context | 262K | — |
| Input $/M | $0.45 | — |
| Output $/M | $2.25 | — |
| Weights | Open | Open |

## Coding

- Kimi K2.5: 48.8 (#53)
- Wizardlm 70b: 31.4 (#285)

| Benchmark | Kimi K2.5 | Wizardlm 70b |
|---|---|---|
| LMArena Coding | 1474 | 1081 |
| SWE-bench Verified | 73.8% | — |
| SWE-bench Verified (bash only) | 70.8% | — |
| LMArena WebDev | 1437 | — |
| SWE-bench Multilingual | 67.3% | — |
| SciCode | 49% | — |
| WeirdML | 45.6% | — |
| ALE-Bench | 821.65 | — |

## Agentic & Tool Use

- Kimi K2.5: 34.2 (#48)
- Wizardlm 70b: —

| Benchmark | Kimi K2.5 | Wizardlm 70b |
|---|---|---|
| Terminal-Bench | 43.2% | — |
| OSWorld | 63.3% | — |
| Vending-Bench 2 | 1,198 | — |

## Reasoning

- Kimi K2.5: 31.2 (#80)
- Wizardlm 70b: 20.7 (#234)

| Benchmark | Kimi K2.5 | Wizardlm 70b |
|---|---|---|
| LMArena Hard Prompts | 1453 | 1079 |
| 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 | 148.03 | — |

## Math

- Kimi K2.5: 51.8 (#53)
- Wizardlm 70b: 32.2 (#218)

| Benchmark | Kimi K2.5 | Wizardlm 70b |
|---|---|---|
| LMArena Math | 1470 | 1116 |
| MathArena Final-Answer Competitions | 62.3% | — |
| OTIS Mock AIME 2024-2025 | 92.2% | — |
| FrontierMath (Feb 2025 set) | 27.9% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |

## Knowledge

- Kimi K2.5: 53.6 (#56)
- Wizardlm 70b: —

| Benchmark | Kimi K2.5 | Wizardlm 70b |
|---|---|---|
| GPQA Diamond | 87.6% | — |
| Humanity's Last Exam | 24.4% | — |
| SimpleQA Verified | 34.3% | — |
| Vectara Hallucination Rate | 14.2% | — |
| LMArena Expert | 1466 | — |

## Multimodal

- Kimi K2.5: 41.1 (#39)
- Wizardlm 70b: —

| Benchmark | Kimi K2.5 | Wizardlm 70b |
|---|---|---|
| LMArena Vision | 1269 | — |
| LMArena Document | 1430 | — |

## Multilingual

- Kimi K2.5: 53.9 (#53)
- Wizardlm 70b: 29.6 (#265)

| Benchmark | Kimi K2.5 | Wizardlm 70b |
|---|---|---|
| LMArena Non-English | 1433 | 1078 |
| LMArena Chinese | 1495 | 1052 |
| LMArena German | 1441 | 1083 |
| LMArena Russian | 1435 | 1155 |
| LMArena French | 1454 | — |
| LMArena Japanese | 1421 | — |
| LMArena Korean | 1410 | — |
| LMArena Spanish | 1450 | — |

## Instruction Following

- Kimi K2.5: 75.3 (#64)
- Wizardlm 70b: 56.3 (#273)

| Benchmark | Kimi K2.5 | Wizardlm 70b |
|---|---|---|
| LMArena Instruction Following | 1431 | 1093 |

## Long Context

- Kimi K2.5: 52.1 (#7)
- Wizardlm 70b: 33.3 (#263)

| Benchmark | Kimi K2.5 | Wizardlm 70b |
|---|---|---|
| LMArena Longer Query | 1445 | 1097 |
| Fiction.LiveBench | 86.1% | — |
| CL-bench | 19.3% | — |
| CL-bench Life | 13.2% | — |

## Writing & Preference

- Kimi K2.5: 65.1 (#53)
- Wizardlm 70b: 34.8 (#269)

| Benchmark | Kimi K2.5 | Wizardlm 70b |
|---|---|---|
| LMArena Text | 1445 | 1120 |
| LMArena Creative Writing | 1423 | 1149 |
| LMArena Multi-Turn | 1444 | 1108 |
| EQ-Bench Creative Writing | 1579 | — |

## FAQ

### Is Kimi K2.5 better than Wizardlm 70b?

Kimi K2.5 is the stronger model overall, scoring 48.1 to 33.0 on the Noometry Index.

### Is Kimi K2.5 or Wizardlm 70b better for coding?

Kimi K2.5 scores higher on coding benchmarks: 48.8 versus 31.4 in the Noometry coding category.

### How many benchmarks do Kimi K2.5 and Wizardlm 70b share?

12 benchmarks have published results for both models. Kimi K2.5 has 51 scored results on Noometry and Wizardlm 70b has 12.