# Gemini 2.0 Flash (Feb 2025) vs Kimi K2.5

> Kimi K2.5 is the stronger model overall, scoring 47.8 to 34.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemini-2-0-flash-vs-kimi-k2-5
- Last updated: 2026-10-10
- Shared benchmarks: 31

## Summary

- They share 31 benchmarks with published results for both. Gemini 2.0 Flash (Feb 2025) scores higher in 0 categories and Kimi K2.5 in 10 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Kimi K2.5 leads 53.6 to 32.0.
- The biggest single-benchmark swing is SWE-bench Verified (bash only): 13.5% for Gemini 2.0 Flash (Feb 2025) and 70.8% for Kimi K2.5.
- Kimi K2.5 has downloadable open weights; the other is API-only.

## Snapshot

| | Gemini 2.0 Flash (Feb 2025) | Kimi K2.5 |
|---|---|---|
| Provider | Google | Moonshot AI |
| Noometry Index | 34.8 | 47.8 |
| Rank | 223 | 50 |
| Context | — | 262K |
| Input $/M | — | $0.45 |
| Output $/M | — | $2.25 |
| Weights | Proprietary | Open |

## Coding

- Gemini 2.0 Flash (Feb 2025): 28.2 (#308)
- Kimi K2.5: 48.7 (#48)

| Benchmark | Gemini 2.0 Flash (Feb 2025) | Kimi K2.5 |
|---|---|---|
| SWE-bench Verified (bash only) | 13.5% | 70.8% |
| WeirdML | 25.8% | 45.6% |
| LMArena Coding | 1351 | 1474 |
| SWE-bench Verified | — | 73.8% |
| Aider Polyglot | 38.2% | — |
| LMArena WebDev | — | 1436 |
| SWE-bench Multilingual | — | 67.3% |
| SciCode | — | 49% |
| BigCodeBench Instruct | 45.9% | — |
| LiveBench Coding | 63.4% | — |
| BigCodeBench Complete | 59.9% | — |
| CadEval | 30% | — |
| ALE-Bench | — | 821.65 |

## Agentic & Tool Use

- Gemini 2.0 Flash (Feb 2025): 28.0 (#85)
- Kimi K2.5: 34.0 (#44)

| Benchmark | Gemini 2.0 Flash (Feb 2025) | Kimi K2.5 |
|---|---|---|
| Terminal-Bench | — | 43.2% |
| TheAgentCompany | 11.4% | — |
| OSWorld | — | 63.3% |
| Vending-Bench 2 | — | 1,198 |

## Reasoning

- Gemini 2.0 Flash (Feb 2025): 15.2 (#308)
- Kimi K2.5: 31.2 (#74)

| Benchmark | Gemini 2.0 Flash (Feb 2025) | Kimi K2.5 |
|---|---|---|
| ARC-AGI-2 | 1.3% | 11.8% |
| SimpleBench | 31.1% | 46.8% |
| Kagi LLM Benchmark | 37.8% | 78.5% |
| EnigmaEval | 1.1% | 3.4% |
| LMArena Hard Prompts | 1346 | 1454 |
| Epoch Capabilities Index | 135.36 | 148.05 |
| NYT Connections (extended) | — | 69.9% |
| ARC-AGI-1 | — | 65.3% |
| CritPt | — | 3.1% |
| Chess Puzzles | — | 12% |
| Thematic Generalization | — | 69.4% |
| LiveBench Reasoning | 78.2% | — |
| DTBench | 63.2% | — |
| LiveBench Data Analysis | 69.4% | — |
| LiveBench | 66.9% | — |

## Math

- Gemini 2.0 Flash (Feb 2025): 36.1 (#127)
- Kimi K2.5: 50.3 (#46)

| Benchmark | Gemini 2.0 Flash (Feb 2025) | Kimi K2.5 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 57.8% | 92.2% |
| LMArena Math | 1351 | 1470 |
| FrontierMath (Feb 2025 set) | 1.7% | 27.9% |
| MathArena Final-Answer Competitions | — | 62.3% |
| Omni-MATH | 45.9% | — |
| LiveBench Math | 75.8% | — |
| MATH Level 5 | 82.2% | — |
| FrontierMath Tier 4 (v1) | — | 4.2% |

## Knowledge

- Gemini 2.0 Flash (Feb 2025): 32.0 (#207)
- Kimi K2.5: 53.6 (#52)

| Benchmark | Gemini 2.0 Flash (Feb 2025) | Kimi K2.5 |
|---|---|---|
| GPQA Diamond | 64.1% | 87.6% |
| Humanity's Last Exam | 6.6% | 24.4% |
| LMArena Expert | 1340 | 1466 |
| SimpleQA Verified | — | 34.3% |
| MMLU-Pro | 73.7% | — |
| Confabulations | 12.4% | — |
| Vectara Hallucination Rate | — | 14.2% |
| GPQA (HELM) | 55.6% | — |
| MMLU | 79.7% | — |

## Multimodal

- Gemini 2.0 Flash (Feb 2025): 35.9 (#74)
- Kimi K2.5: 40.4 (#37)

| Benchmark | Gemini 2.0 Flash (Feb 2025) | Kimi K2.5 |
|---|---|---|
| LMArena Vision | 1158 | 1269 |
| GeoBench | 77% | — |
| LMArena Document | — | 1430 |

## Multilingual

- Gemini 2.0 Flash (Feb 2025): 47.6 (#144)
- Kimi K2.5: 54.1 (#50)

| Benchmark | Gemini 2.0 Flash (Feb 2025) | Kimi K2.5 |
|---|---|---|
| LMArena Non-English | 1342 | 1433 |
| LMArena Chinese | 1373 | 1495 |
| LMArena French | 1390 | 1454 |
| LMArena German | 1354 | 1441 |
| LMArena Japanese | 1293 | 1422 |
| LMArena Korean | 1314 | 1412 |
| LMArena Russian | 1351 | 1436 |
| LMArena Spanish | 1363 | 1450 |

## Instruction Following

- Gemini 2.0 Flash (Feb 2025): 74.6 (#91)
- Kimi K2.5: 75.5 (#60)

| Benchmark | Gemini 2.0 Flash (Feb 2025) | Kimi K2.5 |
|---|---|---|
| LMArena Instruction Following | 1336 | 1431 |
| LiveBench Instruction Following | 85.8% | — |
| IFEval | 84.1% | — |

## Long Context

- Gemini 2.0 Flash (Feb 2025): 38.1 (#198)
- Kimi K2.5: 52.1 (#7)

| Benchmark | Gemini 2.0 Flash (Feb 2025) | Kimi K2.5 |
|---|---|---|
| Fiction.LiveBench | 61.1% | 86.1% |
| LMArena Longer Query | 1345 | 1445 |
| CL-bench | — | 19.3% |
| CL-bench Life | — | 13.2% |

## Writing & Preference

- Gemini 2.0 Flash (Feb 2025): 49.8 (#184)
- Kimi K2.5: 65.3 (#51)

| Benchmark | Gemini 2.0 Flash (Feb 2025) | Kimi K2.5 |
|---|---|---|
| LMArena Text | 1354 | 1445 |
| LMArena Creative Writing | 1340 | 1423 |
| EQ-Bench Creative Writing | 1128 | 1579 |
| LMArena Multi-Turn | 1350 | 1444 |
| Short-Story Creative Writing | 73.8% | — |
| WildBench | 80% | — |
| LiveBench Language | 51.3% | — |

## FAQ

### Is Gemini 2.0 Flash (Feb 2025) better than Kimi K2.5?

Kimi K2.5 is the stronger model overall, scoring 47.8 to 34.8 on the Noometry Index.

### Is Gemini 2.0 Flash (Feb 2025) or Kimi K2.5 better for coding?

Kimi K2.5 scores higher on coding benchmarks: 48.7 versus 28.2 in the Noometry coding category.

### How many benchmarks do Gemini 2.0 Flash (Feb 2025) and Kimi K2.5 share?

31 benchmarks have published results for both models. Gemini 2.0 Flash (Feb 2025) has 54 scored results on Noometry and Kimi K2.5 has 51.