# Gemini 2.5 Pro vs Kimi K2 (Jul 2025)

> Gemini 2.5 Pro is the stronger model overall, scoring 44.9 to 40.9 on the Noometry Index. Kimi K2 (Jul 2025) costs 3.4× less per token, which makes it the better buy when Gemini 2.5 Pro's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gemini-2-5-pro-vs-kimi-k2
- Last updated: 2026-10-10
- Shared benchmarks: 40

## Summary

- They share 40 benchmarks with published results for both. Gemini 2.5 Pro scores higher in 6 categories and Kimi K2 (Jul 2025) in 3 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Gemini 2.5 Pro leads 55.8 to 36.9.
- The biggest single-benchmark swing is SimpleBench: 62.4% for Gemini 2.5 Pro and 26.3% for Kimi K2 (Jul 2025).
- Kimi K2 (Jul 2025) is cheaper at $0.57 / $2.30 per million input/output tokens, against $1.25 / $10 for Gemini 2.5 Pro.
- Gemini 2.5 Pro accepts more context: 1.05M tokens versus 262K.
- Kimi K2 (Jul 2025) has downloadable open weights; the other is API-only.

## Snapshot

| | Gemini 2.5 Pro | Kimi K2 (Jul 2025) |
|---|---|---|
| Provider | Google | Moonshot AI |
| Noometry Index | 44.9 | 40.9 |
| Rank | 67 | 134 |
| Context | 1.05M | 262K |
| Input $/M | $1.25 | $0.57 |
| Output $/M | $10 | $2.30 |
| Weights | Proprietary | Open |

## Coding

- Gemini 2.5 Pro: 42.8 (#86)
- Kimi K2 (Jul 2025): 43.1 (#83)

| Benchmark | Gemini 2.5 Pro | Kimi K2 (Jul 2025) |
|---|---|---|
| SWE-bench Verified (bash only) | 53.6% | 63.4% |
| Aider Polyglot | 83.1% | 59.1% |
| GSO | 3.9% | 4.9% |
| WeirdML | 54% | 42.8% |
| LMArena Coding | 1452 | 1399 |
| ALE-Bench | 785.52 | 597.5 |
| SWE-bench Verified | 57.6% | — |
| LMArena WebDev | 1227 | — |
| SciCode | 42.8% | — |
| LiveBench Coding | 85.9% | — |
| CadEval | 64% | — |
| AlgoTune | 1.51 | — |

## Agentic & Tool Use

- Gemini 2.5 Pro: 29.1 (#81)
- Kimi K2 (Jul 2025): 32.2 (#59)

| Benchmark | Gemini 2.5 Pro | Kimi K2 (Jul 2025) |
|---|---|---|
| Terminal-Bench | 32.6% | 35.7% |
| METR Time Horizons | 55.4% | 59.2% |
| Berkeley Function Calling Leaderboard | — | 59.1% |
| GDPval | 23.3% | — |
| Remote Labor Index | 0.8% | — |
| TheAgentCompany | 30.3% | — |
| τ²-bench Banking | 13.7% | — |
| DeepResearch Bench | 42.8% | — |
| BALROG | 43.3% | — |
| LMArena Search | 1142 | — |
| Vending-Bench 2 | 573.64 | — |

## Reasoning

- Gemini 2.5 Pro: 28.8 (#85)
- Kimi K2 (Jul 2025): 22.7 (#173)

| Benchmark | Gemini 2.5 Pro | Kimi K2 (Jul 2025) |
|---|---|---|
| SimpleBench | 62.4% | 26.3% |
| Kagi LLM Benchmark | 70.3% | 64.4% |
| LMArena Hard Prompts | 1455 | 1384 |
| Epoch Capabilities Index | 145.32 | 146.02 |
| ForecastBench | 61.3 | 60.2 |
| ARC-AGI-2 | 4.9% | — |
| ARC-AGI-1 | 41% | — |
| CritPt | 2% | — |
| Chess Puzzles | 20% | — |
| EnigmaEval | 5.6% | — |
| LiveBench Reasoning | 89.8% | — |
| DTBench | 82.4% | — |
| LiveBench Data Analysis | 79.9% | — |
| LMCA | 34.8% | — |
| LiveBench | 82.3% | — |

## Math

- Gemini 2.5 Pro: 31.9 (#191)
- Kimi K2 (Jul 2025): 40.1 (#81)

| Benchmark | Gemini 2.5 Pro | Kimi K2 (Jul 2025) |
|---|---|---|
| Omni-MATH | 41.6% | 65.4% |
| LMArena Math | 1450 | 1396 |
| FrontierMath (Feb 2025 set) | 14.1% | 21.4% |
| FrontierMath Tier 4 (v1) | 4.2% | 0% |
| FrontierMath (Tiers 1-3) | 24.6% | — |
| FrontierMath Tier 4 | 0% | — |
| OTIS Mock AIME 2024-2025 | 84.7% | — |
| LiveBench Math | 90.2% | — |
| MATH Level 5 | 95.9% | — |

## Knowledge

- Gemini 2.5 Pro: 55.8 (#41)
- Kimi K2 (Jul 2025): 36.9 (#153)

| Benchmark | Gemini 2.5 Pro | Kimi K2 (Jul 2025) |
|---|---|---|
| MMLU-Pro | 86.3% | 81.9% |
| Confabulations | 10.6% | 20.4% |
| Vectara Hallucination Rate | 7% | 17.9% |
| GPQA (HELM) | 74.9% | 65.3% |
| LMArena Expert | 1452 | 1363 |
| GPQA Diamond | 85.3% | — |
| Humanity's Last Exam | 21.6% | — |

## Multimodal

- Gemini 2.5 Pro: 44.5 (#16)
- Kimi K2 (Jul 2025): —

| Benchmark | Gemini 2.5 Pro | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Vision | 1263 | — |
| GeoBench | 86% | — |
| VPCT | 48% | — |
| LMArena Document | 1421 | — |
| SpatialViz-Bench | 44.7% | — |

## Multilingual

- Gemini 2.5 Pro: 55.5 (#30)
- Kimi K2 (Jul 2025): 49.8 (#125)

| Benchmark | Gemini 2.5 Pro | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Non-English | 1452 | 1372 |
| LMArena Chinese | 1507 | 1416 |
| LMArena French | 1473 | 1379 |
| LMArena German | 1487 | 1386 |
| LMArena Japanese | 1462 | 1349 |
| LMArena Korean | 1435 | 1324 |
| LMArena Russian | 1460 | 1384 |
| LMArena Spanish | 1473 | 1383 |

## Instruction Following

- Gemini 2.5 Pro: 75.2 (#71)
- Kimi K2 (Jul 2025): 71.3 (#151)

| Benchmark | Gemini 2.5 Pro | Kimi K2 (Jul 2025) |
|---|---|---|
| IFEval | 84% | 85% |
| LMArena Instruction Following | 1436 | 1347 |
| LiveBench Instruction Following | 80.6% | — |

## Long Context

- Gemini 2.5 Pro: 59.7 (#5)
- Kimi K2 (Jul 2025): 41.2 (#140)

| Benchmark | Gemini 2.5 Pro | Kimi K2 (Jul 2025) |
|---|---|---|
| Fiction.LiveBench | 91.7% | 66.7% |
| LMArena Longer Query | 1449 | 1353 |
| CL-bench | — | 17.6% |

## Writing & Preference

- Gemini 2.5 Pro: 63.9 (#60)
- Kimi K2 (Jul 2025): 62.5 (#76)

| Benchmark | Gemini 2.5 Pro | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Text | 1458 | 1380 |
| LMArena Creative Writing | 1453 | 1349 |
| Short-Story Creative Writing | 83.8% | 85.6% |
| EQ-Bench Creative Writing | 1421 | 1666 |
| WildBench | 85.7% | 86.2% |
| LMArena Multi-Turn | 1453 | 1371 |
| LiveBench Language | 67.8% | — |

## FAQ

### Is Gemini 2.5 Pro better than Kimi K2 (Jul 2025)?

Gemini 2.5 Pro is the stronger model overall, scoring 44.9 to 40.9 on the Noometry Index. Kimi K2 (Jul 2025) costs 3.4× less per token, which makes it the better buy when Gemini 2.5 Pro's lead doesn't matter for your workload.

### Which is cheaper, Gemini 2.5 Pro or Kimi K2 (Jul 2025)?

Kimi K2 (Jul 2025) is cheaper. It lists at $0.57 per million input tokens and $2.30 per million output tokens; Gemini 2.5 Pro lists at $1.25 and $10.

### Is Gemini 2.5 Pro or Kimi K2 (Jul 2025) better for coding?

They score almost the same on coding (42.8 vs 43.1); test both on your own repository before choosing.

### Which has the bigger context window?

Gemini 2.5 Pro does, with 1.05M tokens against 262K.

### How many benchmarks do Gemini 2.5 Pro and Kimi K2 (Jul 2025) share?

40 benchmarks have published results for both models. Gemini 2.5 Pro has 78 scored results on Noometry and Kimi K2 (Jul 2025) has 42.