# Kimi K2.5 vs o1-mini

> Kimi K2.5 is the stronger model overall, scoring 47.8 to 33.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/kimi-k2-5-vs-o1-mini
- Last updated: 2026-10-10
- Shared benchmarks: 25

## Summary

- They share 25 benchmarks with published results for both. Kimi K2.5 scores higher in 9 categories and o1-mini in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Kimi K2.5 leads 31.2 to 8.9.
- The biggest single-benchmark swing is ARC-AGI-1: 65.3% for Kimi K2.5 and 14% for o1-mini.
- Kimi K2.5 has downloadable open weights; the other is API-only.

## Snapshot

| | Kimi K2.5 | o1-mini |
|---|---|---|
| Provider | Moonshot AI | OpenAI |
| Noometry Index | 47.8 | 33.7 |
| Rank | 50 | 230 |
| Context | 262K | — |
| Input $/M | $0.45 | — |
| Output $/M | $2.25 | — |
| Weights | Open | Proprietary |

## Coding

- Kimi K2.5: 48.7 (#48)
- o1-mini: 35.1 (#218)

| Benchmark | Kimi K2.5 | o1-mini |
|---|---|---|
| WeirdML | 45.6% | 36.3% |
| LMArena Coding | 1474 | 1362 |
| SWE-bench Verified | 73.8% | — |
| SWE-bench Verified (bash only) | 70.8% | — |
| Aider Polyglot | — | 32.9% |
| LMArena WebDev | 1436 | — |
| SWE-bench Multilingual | 67.3% | — |
| SciCode | 49% | — |
| LiveBench Coding | — | 48% |
| ALE-Bench | 821.65 | — |
| HumanEval+ | — | 89% |
| MBPP+ | — | 78.8% |

## Agentic & Tool Use

- Kimi K2.5: 34.0 (#44)
- o1-mini: 24.3 (#112)

| Benchmark | Kimi K2.5 | o1-mini |
|---|---|---|
| Terminal-Bench | 43.2% | — |
| Cybench | — | 10% |
| OSWorld | 63.3% | — |
| Vending-Bench 2 | 1,198 | — |

## Reasoning

- Kimi K2.5: 31.2 (#74)
- o1-mini: 8.9 (#340)

| Benchmark | Kimi K2.5 | o1-mini |
|---|---|---|
| ARC-AGI-2 | 11.8% | 0.8% |
| SimpleBench | 46.8% | 18.1% |
| ARC-AGI-1 | 65.3% | 14% |
| LMArena Hard Prompts | 1454 | 1333 |
| Epoch Capabilities Index | 148.05 | 135.82 |
| Kagi LLM Benchmark | 78.5% | — |
| NYT Connections (extended) | 69.9% | — |
| CritPt | 3.1% | — |
| Chess Puzzles | 12% | — |
| EnigmaEval | 3.4% | — |
| Thematic Generalization | 69.4% | — |
| LiveBench Reasoning | — | 72.3% |
| LiveBench Data Analysis | — | 57.9% |
| LiveBench | — | 57.8% |

## Math

- Kimi K2.5: 50.3 (#46)
- o1-mini: 33.7 (#168)

| Benchmark | Kimi K2.5 | o1-mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 92.2% | 46.9% |
| LMArena Math | 1470 | 1358 |
| FrontierMath (Feb 2025 set) | 27.9% | 1.7% |
| MathArena Final-Answer Competitions | 62.3% | — |
| LiveBench Math | — | 62% |
| MATH Level 5 | — | 89.2% |
| FrontierMath Tier 4 (v1) | 4.2% | — |

## Knowledge

- Kimi K2.5: 53.6 (#52)
- o1-mini: 34.8 (#180)

| Benchmark | Kimi K2.5 | o1-mini |
|---|---|---|
| GPQA Diamond | 87.6% | 62.4% |
| LMArena Expert | 1466 | 1316 |
| Humanity's Last Exam | 24.4% | — |
| SimpleQA Verified | 34.3% | — |
| Confabulations | — | 18.6% |
| Vectara Hallucination Rate | 14.2% | — |

## Multimodal

- Kimi K2.5: 40.4 (#37)
- o1-mini: —

| Benchmark | Kimi K2.5 | o1-mini |
|---|---|---|
| LMArena Vision | 1269 | — |
| LMArena Document | 1430 | — |

## Multilingual

- Kimi K2.5: 54.1 (#50)
- o1-mini: 43.8 (#177)

| Benchmark | Kimi K2.5 | o1-mini |
|---|---|---|
| LMArena Non-English | 1433 | 1289 |
| LMArena Chinese | 1495 | 1314 |
| LMArena French | 1454 | 1292 |
| LMArena German | 1441 | 1278 |
| LMArena Japanese | 1422 | 1245 |
| LMArena Korean | 1412 | 1223 |
| LMArena Russian | 1436 | 1283 |
| LMArena Spanish | 1450 | 1302 |

## Instruction Following

- Kimi K2.5: 75.5 (#60)
- o1-mini: 67.0 (#200)

| Benchmark | Kimi K2.5 | o1-mini |
|---|---|---|
| LMArena Instruction Following | 1431 | 1304 |
| LiveBench Instruction Following | — | 65.4% |

## Long Context

- Kimi K2.5: 52.1 (#7)
- o1-mini: 40.1 (#156)

| Benchmark | Kimi K2.5 | o1-mini |
|---|---|---|
| LMArena Longer Query | 1445 | 1321 |
| Fiction.LiveBench | 86.1% | — |
| CL-bench | 19.3% | — |
| CL-bench Life | 13.2% | — |

## Writing & Preference

- Kimi K2.5: 65.3 (#51)
- o1-mini: 48.6 (#196)

| Benchmark | Kimi K2.5 | o1-mini |
|---|---|---|
| LMArena Text | 1445 | 1317 |
| LMArena Creative Writing | 1423 | 1244 |
| LMArena Multi-Turn | 1444 | 1314 |
| Short-Story Creative Writing | — | 64.9% |
| EQ-Bench Creative Writing | 1579 | — |
| LiveBench Language | — | 40.9% |

## FAQ

### Is Kimi K2.5 better than o1-mini?

Kimi K2.5 is the stronger model overall, scoring 47.8 to 33.7 on the Noometry Index.

### Is Kimi K2.5 or o1-mini better for coding?

Kimi K2.5 scores higher on coding benchmarks: 48.7 versus 35.1 in the Noometry coding category.

### How many benchmarks do Kimi K2.5 and o1-mini share?

25 benchmarks have published results for both models. Kimi K2.5 has 51 scored results on Noometry and o1-mini has 39.