Model comparison
Gemini 3 Flash Preview vs Kimi K2.6
Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 47.7 on the Noometry Index.
Last verified . 42 shared benchmarks.
GoogleSummary
- They share 42 benchmarks with published results for both. Gemini 3 Flash Preview scores higher in 6 categories and Kimi K2.6 in 4 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where Gemini 3 Flash Preview leads 38.7 to 21.9.
- The biggest single-benchmark swing is SimpleQA Verified: 66.8% for Gemini 3 Flash Preview and 34.9% for Kimi K2.6.
- Gemini 3 Flash Preview is cheaper at $0.50 / $3 per million input/output tokens, against $0.95 / $4 for Kimi K2.6.
- Gemini 3 Flash Preview accepts more context: 1.05M tokens versus 262K.
- Kimi K2.6 has downloadable open weights; the other is API-only.
Side by side
| Gemini 3 Flash Preview | Kimi K2.6 | |
|---|---|---|
| Provider | Moonshot AI | |
| Noometry Index | 52.3 | 47.7 |
| Released | 2025-12-17 | 2026-04-20 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 262K |
| Max output | 66K | 262K |
| Input $ / M tokens | $0.50 | $0.95 |
| Output $ / M tokens | $3 | $4 |
| Results tracked | 59 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Gemini 3 Flash Preview: 50.9 (#42), Kimi K2.6: 50.7 (#43)
| Benchmark | Gemini 3 Flash Preview | Kimi K2.6 |
|---|---|---|
| SWE-bench Verified | 75.4% | 76.7% |
| LMArena WebDev | 1439 | 1509 |
| WeirdML | 61.6% | 55.9% |
| LMArena Coding | 1460 | 1488 |
| ALE-Bench | 1,367 | 1,093 |
| SWE-bench Verified (bash only) | 75.8% | — |
| SWE-bench Multilingual | 72.7% | — |
| SciCode | — | 53.5% |
| GSO | 9.8% | — |
Agentic & Tool Use Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 38.7 (#29), Kimi K2.6: 21.9 (#137)
| Benchmark | Gemini 3 Flash Preview | Kimi K2.6 |
|---|---|---|
| GDP.pdf | 10% | 12% |
| Vending-Bench 2 | 3,635 | 6,205 |
| Terminal-Bench | 64.3% | — |
| OSWorld 2.0 | — | 4.6% |
| τ²-bench Airline | 82.5% | — |
| τ²-bench Banking | 27.3% | — |
| τ²-bench Retail | 76.8% | — |
| τ²-bench Telecom | 91.2% | — |
| DeepResearch Bench | 49.8% | — |
| BALROG | 48.1% | — |
| ExploitBench | — | 18.4% |
| GBAEval | — | 0.9% |
| LMArena Search | 1198 | — |
Reasoning Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 49.2 (#37), Kimi K2.6: 40.5 (#55)
| Benchmark | Gemini 3 Flash Preview | Kimi K2.6 |
|---|---|---|
| NYT Connections (extended) | 83.1% | 87.2% |
| Chess Puzzles | 40% | 26% |
| LMArena Hard Prompts | 1465 | 1470 |
| Mystery Game Puzzles | 26% | 18% |
| DTBench | 89.1% | 90.9% |
| LMCA | 43.1% | 37.3% |
| Epoch Capabilities Index | 151.8 | 151.05 |
| ARC-AGI-2 | 33.6% | — |
| SimpleBench | 61.1% | — |
| ARC-AGI-1 | 84.7% | — |
| CritPt | — | 8% |
| EBR-Bench | — | 2.4% |
| ForecastBench | 58.5 | — |
Math Kimi K2.6 leads
Gemini 3 Flash Preview: 51.7 (#55), Kimi K2.6: 57.0 (#41)
| Benchmark | Gemini 3 Flash Preview | Kimi K2.6 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 51.2% | 57.2% |
| FrontierMath Tier 4 | 17.1% | 25.6% |
| MathArena Final-Answer Competitions | 67.6% | 72.9% |
| OTIS Mock AIME 2024-2025 | 95.6% | 96.1% |
| ProofBench | 15% | 16% |
| LMArena Math | 1473 | 1475 |
| FrontierMath (Feb 2025 set) | 35.6% | 39% |
| FrontierMath Tier 4 (v1) | 4.2% | 14.6% |
Knowledge Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 58.8 (#33), Kimi K2.6: 54.0 (#54)
| Benchmark | Gemini 3 Flash Preview | Kimi K2.6 |
|---|---|---|
| GPQA Diamond | 89.4% | 90.8% |
| SimpleQA Verified | 66.8% | 34.9% |
| Vectara Hallucination Rate | 13.5% | 10.8% |
| LMArena Expert | 1462 | 1491 |
Multimodal Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 45.5 (#16), Kimi K2.6: 31.6 (#103)
| Benchmark | Gemini 3 Flash Preview | Kimi K2.6 |
|---|---|---|
| LMArena Vision | 1285 | 1283 |
| Blueprint-Bench 2 | 0% | 3.9% |
| LMArena Document | 1413 | 1451 |
| GeoBench | 88% | — |
| VPCT | 72.6% | — |
| Furniture Assembly | — | 21.7% |
Multilingual Too close to call
Gemini 3 Flash Preview: 55.7 (#27), Kimi K2.6: 54.9 (#37)
| Benchmark | Gemini 3 Flash Preview | Kimi K2.6 |
|---|---|---|
| LMArena Non-English | 1458 | 1446 |
| LMArena Chinese | 1511 | 1521 |
| LMArena French | 1477 | 1471 |
| LMArena German | 1497 | 1450 |
| LMArena Japanese | 1489 | 1443 |
| LMArena Korean | 1443 | 1427 |
| LMArena Russian | 1480 | 1446 |
| LMArena Spanish | 1469 | 1464 |
Instruction Following Too close to call
Gemini 3 Flash Preview: 75.7 (#56), Kimi K2.6: 76.3 (#43)
| Benchmark | Gemini 3 Flash Preview | Kimi K2.6 |
|---|---|---|
| LMArena Instruction Following | 1437 | 1451 |
Long Context Too close to call
Gemini 3 Flash Preview: 44.4 (#67), Kimi K2.6: 44.9 (#52)
| Benchmark | Gemini 3 Flash Preview | Kimi K2.6 |
|---|---|---|
| LMArena Longer Query | 1452 | 1468 |
Writing & Preference Kimi K2.6 leads
Gemini 3 Flash Preview: 65.5 (#45), Kimi K2.6: 68.5 (#26)
| Benchmark | Gemini 3 Flash Preview | Kimi K2.6 |
|---|---|---|
| LMArena Text | 1466 | 1455 |
| LMArena Creative Writing | 1457 | 1434 |
| LMArena Multi-Turn | 1471 | 1453 |
| EQ-Bench Creative Writing | — | 1725 |
| EQ-Bench 4 | — | 1202 |
Frequently asked questions
Is Gemini 3 Flash Preview better than Kimi K2.6?
Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 47.7 on the Noometry Index.
Which is cheaper, Gemini 3 Flash Preview or Kimi K2.6?
Gemini 3 Flash Preview is cheaper. It lists at $0.50 per million input tokens and $3 per million output tokens; Kimi K2.6 lists at $0.95 and $4.
Is Gemini 3 Flash Preview or Kimi K2.6 better for coding?
They score almost the same on coding (50.9 vs 50.7); test both on your own repository before choosing.
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 K2.6 share?
42 benchmarks have published results for both models. Gemini 3 Flash Preview has 59 scored results on Noometry and Kimi K2.6 has 51.