# Grok-3 mini vs Kimi K2.5

> Kimi K2.5 is the stronger model overall, scoring 48.1 to 41.2 on the Noometry Index.

- Canonical page: https://noometry.com/compare/grok-3-mini-vs-kimi-k2-5
- Last updated: 2026-10-11
- Shared benchmarks: 26

## Summary

- They share 26 benchmarks with published results for both. Grok-3 mini scores higher in 1 category and Kimi K2.5 in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Kimi K2.5 leads 31.2 to 13.6.
- The biggest single-benchmark swing is ARC-AGI-1: 16.5% for Grok-3 mini and 65.3% for Kimi K2.5.
- Kimi K2.5 has downloadable open weights; the other is API-only.

## Snapshot

| | Grok-3 mini | Kimi K2.5 |
|---|---|---|
| Provider | xAI | Moonshot AI |
| Noometry Index | 41.2 | 48.1 |
| Rank | 141 | 57 |
| Context | — | 262K |
| Input $/M | — | $0.45 |
| Output $/M | — | $2.25 |
| Weights | Proprietary | Open |

## Coding

- Grok-3 mini: 40.8 (#131)
- Kimi K2.5: 48.8 (#53)

| Benchmark | Grok-3 mini | Kimi K2.5 |
|---|---|---|
| WeirdML | 42.6% | 45.6% |
| LMArena Coding | 1379 | 1474 |
| SWE-bench Verified | — | 73.8% |
| SWE-bench Verified (bash only) | — | 70.8% |
| Aider Polyglot | 49.3% | — |
| LMArena WebDev | — | 1437 |
| SWE-bench Multilingual | — | 67.3% |
| SciCode | — | 49% |
| ALE-Bench | — | 821.65 |

## Agentic & Tool Use

- Grok-3 mini: —
- Kimi K2.5: 34.2 (#48)

| Benchmark | Grok-3 mini | Kimi K2.5 |
|---|---|---|
| Terminal-Bench | — | 43.2% |
| OSWorld | — | 63.3% |
| Vending-Bench 2 | — | 1,198 |

## Reasoning

- Grok-3 mini: 13.6 (#334)
- Kimi K2.5: 31.2 (#80)

| Benchmark | Grok-3 mini | Kimi K2.5 |
|---|---|---|
| ARC-AGI-2 | 0.4% | 11.8% |
| Kagi LLM Benchmark | 61.3% | 78.5% |
| ARC-AGI-1 | 16.5% | 65.3% |
| LMArena Hard Prompts | 1375 | 1453 |
| Epoch Capabilities Index | 140.35 | 148.03 |
| SimpleBench | — | 46.8% |
| NYT Connections (extended) | — | 69.9% |
| CritPt | — | 3.1% |
| Chess Puzzles | — | 12% |
| EnigmaEval | — | 3.4% |
| Thematic Generalization | — | 69.4% |

## Math

- Grok-3 mini: 42.1 (#85)
- Kimi K2.5: 51.8 (#53)

| Benchmark | Grok-3 mini | Kimi K2.5 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 77.8% | 92.2% |
| LMArena Math | 1386 | 1470 |
| FrontierMath (Feb 2025 set) | 5.9% | 27.9% |
| MathArena Final-Answer Competitions | — | 62.3% |
| Omni-MATH | 31.8% | — |
| MATH Level 5 | 90.9% | — |
| FrontierMath Tier 4 (v1) | — | 4.2% |

## Knowledge

- Grok-3 mini: 46.4 (#81)
- Kimi K2.5: 53.6 (#56)

| Benchmark | Grok-3 mini | Kimi K2.5 |
|---|---|---|
| GPQA Diamond | 76.3% | 87.6% |
| LMArena Expert | 1395 | 1466 |
| Humanity's Last Exam | — | 24.4% |
| SimpleQA Verified | — | 34.3% |
| MMLU-Pro | 79.9% | — |
| Confabulations | 10.8% | — |
| Vectara Hallucination Rate | — | 14.2% |
| GPQA (HELM) | 67.5% | — |

## Multimodal

- Grok-3 mini: —
- Kimi K2.5: 41.1 (#39)

| Benchmark | Grok-3 mini | Kimi K2.5 |
|---|---|---|
| LMArena Vision | — | 1269 |
| LMArena Document | — | 1430 |

## Multilingual

- Grok-3 mini: 48.1 (#145)
- Kimi K2.5: 53.9 (#53)

| Benchmark | Grok-3 mini | Kimi K2.5 |
|---|---|---|
| LMArena Non-English | 1352 | 1433 |
| LMArena Chinese | 1387 | 1495 |
| LMArena French | 1357 | 1454 |
| LMArena German | 1349 | 1441 |
| LMArena Japanese | 1342 | 1421 |
| LMArena Korean | 1335 | 1410 |
| LMArena Russian | 1353 | 1435 |
| LMArena Spanish | 1381 | 1450 |

## Instruction Following

- Grok-3 mini: 78.5 (#9)
- Kimi K2.5: 75.3 (#64)

| Benchmark | Grok-3 mini | Kimi K2.5 |
|---|---|---|
| LMArena Instruction Following | 1357 | 1431 |
| IFEval | 95.1% | — |

## Long Context

- Grok-3 mini: 41.0 (#147)
- Kimi K2.5: 52.1 (#7)

| Benchmark | Grok-3 mini | Kimi K2.5 |
|---|---|---|
| Fiction.LiveBench | 66.7% | 86.1% |
| LMArena Longer Query | 1372 | 1445 |
| CL-bench | — | 19.3% |
| CL-bench Life | — | 13.2% |

## Writing & Preference

- Grok-3 mini: 52.5 (#169)
- Kimi K2.5: 65.1 (#53)

| Benchmark | Grok-3 mini | Kimi K2.5 |
|---|---|---|
| LMArena Text | 1370 | 1445 |
| LMArena Creative Writing | 1342 | 1423 |
| LMArena Multi-Turn | 1355 | 1444 |
| Short-Story Creative Writing | 73.5% | — |
| EQ-Bench Creative Writing | — | 1579 |
| WildBench | 65.1% | — |

## FAQ

### Is Grok-3 mini better than Kimi K2.5?

Kimi K2.5 is the stronger model overall, scoring 48.1 to 41.2 on the Noometry Index.

### Is Grok-3 mini or Kimi K2.5 better for coding?

Kimi K2.5 scores higher on coding benchmarks: 48.8 versus 40.8 in the Noometry coding category.

### How many benchmarks do Grok-3 mini and Kimi K2.5 share?

26 benchmarks have published results for both models. Grok-3 mini has 35 scored results on Noometry and Kimi K2.5 has 51.