Xentir Gemini 3 Flash vs Kimi K2.6
Gemini 3 Flash · Google DeepMind, released 2025-12-17
Kimi K2.6 OPEN WEIGHTS · Moonshot, released 2026-04-20
“Epoch AI, 'AI Benchmarking Hub'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks' [online resource].” · epoch.ai/benchmarks · Licensed CC BY 4.0 · data last verified 2026-09-09 · Methodology · Data Sources
Kimi K2.6 leads on more of the 8 benchmarks where both are measured — Gemini 3 Flash on 3, Kimi K2.6 on 5. The remaining 1 of 9 tracked benchmark cannot be compared: 0 have a result for only one of the two models, 1 for neither. Nothing on this page is estimated to fill those in.
Head-to-head
Measured on 8 of 9 tracked benchmarks for both models — Gemini 3 Flash leads on 3, Kimi K2.6 leads on 5.
| Benchmark | Gemini 3 Flash | Kimi K2.6 | Leads |
|---|---|---|---|
| Epoch Capabilities Index (ECI) | 151.8 | 151.0 | Gemini 3 Flash |
| SWE-bench Verified | 0.754 | 0.767 | Kimi K2.6 |
| GPQA Diamond | 0.894 (high) | 0.908 | Kimi K2.6 |
| MATH Level 5 | Not measured | Not measured | Not measured on both |
| OTIS Mock AIME 2024-2025 | 0.956 (high) | 0.961 | Kimi K2.6 |
| FrontierMath | 0.356 | 0.390 | Kimi K2.6 |
| FrontierMath Tier 4 | 0.042 | 0.146 | Kimi K2.6 |
| SimpleQA Verified | 0.668 (high) | 0.349 | Gemini 3 Flash |
| Chess Puzzles | 0.400 (high) | 0.260 | Gemini 3 Flash |
What remains uncertain
- 1 tracked benchmark has no published result for either model.
A missing result means Xentir has not found one published by the source it cites, not that the model performs badly. See Data Sources.
Reference price
| Per 1M tokens | Gemini 3 Flash | Kimi K2.6 |
|---|---|---|
| Output | $3.00 | — |
List price as published by the vendor. Xentir does not verify negotiated or enterprise rates, and price is not a measure of capability — see Data Sources.
Full profiles
Gemini 3 Flash → · Kimi K2.6 → · the full AI Model Rankings table