Model comparison
Gemini 3 Flash Preview vs Kimi K2.5
Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 48.1 on the Noometry Index.
Last verified . 40 shared benchmarks.
GoogleSummary
- They share 40 benchmarks with published results for both. Gemini 3 Flash Preview scores higher in 8 categories and Kimi K2.5 in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3 Flash Preview leads 49.2 to 31.2.
- The biggest single-benchmark swing is SimpleQA Verified: 66.8% for Gemini 3 Flash Preview and 34.3% for Kimi K2.5.
- Kimi K2.5 is cheaper at $0.45 / $2.25 per million input/output tokens, against $0.50 / $3 for Gemini 3 Flash Preview.
- Gemini 3 Flash Preview accepts more context: 1.05M tokens versus 262K.
- Kimi K2.5 has downloadable open weights; the other is API-only.
Side by side
| Gemini 3 Flash Preview | Kimi K2.5 | |
|---|---|---|
| Provider | Moonshot AI | |
| Noometry Index | 52.3 | 48.1 |
| Released | 2025-12-17 | 2026-01-27 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 262K |
| Max output | 66K | 262K |
| Input $ / M tokens | $0.50 | $0.45 |
| Output $ / M tokens | $3 | $2.25 |
| Results tracked | 59 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 50.9 (#42), Kimi K2.5: 48.8 (#53)
| Benchmark | Gemini 3 Flash Preview | Kimi K2.5 |
|---|---|---|
| SWE-bench Verified | 75.4% | 73.8% |
| SWE-bench Verified (bash only) | 75.8% | 70.8% |
| LMArena WebDev | 1439 | 1437 |
| SWE-bench Multilingual | 72.7% | 67.3% |
| WeirdML | 61.6% | 45.6% |
| LMArena Coding | 1460 | 1474 |
| ALE-Bench | 1,367 | 821.65 |
| SciCode | — | 49% |
| GSO | 9.8% | — |
Agentic & Tool Use Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 38.7 (#29), Kimi K2.5: 34.2 (#48)
| Benchmark | Gemini 3 Flash Preview | Kimi K2.5 |
|---|---|---|
| Terminal-Bench | 64.3% | 43.2% |
| Vending-Bench 2 | 3,635 | 1,198 |
| τ²-bench Airline | 82.5% | — |
| τ²-bench Banking | 27.3% | — |
| τ²-bench Retail | 76.8% | — |
| τ²-bench Telecom | 91.2% | — |
| DeepResearch Bench | 49.8% | — |
| OSWorld | — | 63.3% |
| BALROG | 48.1% | — |
| GDP.pdf | 10% | — |
| LMArena Search | 1198 | — |
Reasoning Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 49.2 (#37), Kimi K2.5: 31.2 (#80)
| Benchmark | Gemini 3 Flash Preview | Kimi K2.5 |
|---|---|---|
| ARC-AGI-2 | 33.6% | 11.8% |
| SimpleBench | 61.1% | 46.8% |
| NYT Connections (extended) | 83.1% | 69.9% |
| ARC-AGI-1 | 84.7% | 65.3% |
| Chess Puzzles | 40% | 12% |
| LMArena Hard Prompts | 1465 | 1453 |
| Epoch Capabilities Index | 151.8 | 148.03 |
| Kagi LLM Benchmark | — | 78.5% |
| CritPt | — | 3.1% |
| EnigmaEval | — | 3.4% |
| Thematic Generalization | — | 69.4% |
| Mystery Game Puzzles | 26% | — |
| DTBench | 89.1% | — |
| LMCA | 43.1% | — |
| ForecastBench | 58.5 | — |
Math Too close to call
Gemini 3 Flash Preview: 51.7 (#55), Kimi K2.5: 51.8 (#53)
| Benchmark | Gemini 3 Flash Preview | Kimi K2.5 |
|---|---|---|
| MathArena Final-Answer Competitions | 67.6% | 62.3% |
| OTIS Mock AIME 2024-2025 | 95.6% | 92.2% |
| LMArena Math | 1473 | 1470 |
| FrontierMath (Feb 2025 set) | 35.6% | 27.9% |
| FrontierMath Tier 4 (v1) | 4.2% | 4.2% |
| FrontierMath (Tiers 1-3) | 51.2% | — |
| FrontierMath Tier 4 | 17.1% | — |
| ProofBench | 15% | — |
Knowledge Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 58.8 (#33), Kimi K2.5: 53.6 (#56)
| Benchmark | Gemini 3 Flash Preview | Kimi K2.5 |
|---|---|---|
| GPQA Diamond | 89.4% | 87.6% |
| SimpleQA Verified | 66.8% | 34.3% |
| Vectara Hallucination Rate | 13.5% | 14.2% |
| LMArena Expert | 1462 | 1466 |
| Humanity's Last Exam | — | 24.4% |
Multimodal Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 45.5 (#16), Kimi K2.5: 41.1 (#39)
| Benchmark | Gemini 3 Flash Preview | Kimi K2.5 |
|---|---|---|
| LMArena Vision | 1285 | 1269 |
| LMArena Document | 1413 | 1430 |
| GeoBench | 88% | — |
| VPCT | 72.6% | — |
| Blueprint-Bench 2 | 0% | — |
Multilingual Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 55.7 (#27), Kimi K2.5: 53.9 (#53)
| Benchmark | Gemini 3 Flash Preview | Kimi K2.5 |
|---|---|---|
| LMArena Non-English | 1458 | 1433 |
| LMArena Chinese | 1511 | 1495 |
| LMArena French | 1477 | 1454 |
| LMArena German | 1497 | 1441 |
| LMArena Japanese | 1489 | 1421 |
| LMArena Korean | 1443 | 1410 |
| LMArena Russian | 1480 | 1435 |
| LMArena Spanish | 1469 | 1450 |
Instruction Following Too close to call
Gemini 3 Flash Preview: 75.7 (#56), Kimi K2.5: 75.3 (#64)
| Benchmark | Gemini 3 Flash Preview | Kimi K2.5 |
|---|---|---|
| LMArena Instruction Following | 1437 | 1431 |
Long Context Kimi K2.5 leads
Gemini 3 Flash Preview: 44.4 (#67), Kimi K2.5: 52.1 (#7)
| Benchmark | Gemini 3 Flash Preview | Kimi K2.5 |
|---|---|---|
| LMArena Longer Query | 1452 | 1445 |
| Fiction.LiveBench | — | 86.1% |
| CL-bench | — | 19.3% |
| CL-bench Life | — | 13.2% |
Writing & Preference Too close to call
Gemini 3 Flash Preview: 65.5 (#45), Kimi K2.5: 65.1 (#53)
| Benchmark | Gemini 3 Flash Preview | Kimi K2.5 |
|---|---|---|
| LMArena Text | 1466 | 1445 |
| LMArena Creative Writing | 1457 | 1423 |
| LMArena Multi-Turn | 1471 | 1444 |
| EQ-Bench Creative Writing | — | 1579 |
Frequently asked questions
Is Gemini 3 Flash Preview better than Kimi K2.5?
Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 48.1 on the Noometry Index.
Which is cheaper, Gemini 3 Flash Preview or Kimi K2.5?
Kimi K2.5 is cheaper. It lists at $0.45 per million input tokens and $2.25 per million output tokens; Gemini 3 Flash Preview lists at $0.50 and $3.
Is Gemini 3 Flash Preview or Kimi K2.5 better for coding?
Gemini 3 Flash Preview scores higher on coding benchmarks: 50.9 versus 48.8 in the Noometry coding category.
Which has the bigger context window?
Gemini 3 Flash Preview does, with 1.05M tokens against 262K.
How many benchmarks do Gemini 3 Flash Preview and Kimi K2.5 share?
40 benchmarks have published results for both models. Gemini 3 Flash Preview has 59 scored results on Noometry and Kimi K2.5 has 51.