Comparing 2 models
Gemini 3.6 Flash vs Kimi K3
Benchmarks through
Verdict
Gemini 3.6 Flash and Kimi K3 are not yet ranked on the same task, so compare the specifications below. Kimi K3 costs 3.9x less per input token. Only Kimi K3 has open weights for self-hosting.
- Choose Kimi K3 for you need to self-host.
Built from the published task rankings below; ranks come from each task's own weighted benchmarks, so a win on one task says nothing about another.
Measured head to head
Benchmarks both models were run on
| Evaluation | Gemini 3.6 Flash | Kimi K3 | Source |
|---|---|---|---|
| Design Arena Coding | 1279 Elo | 1352 Elo | source · 2026-11-15 |
| Design Arena Full-stack Agent | 1154 Elo | 1289 Elo | source · 2026-11-15 |
| Design Arena UI | 1289 Elo | 1342 Elo | source · 2026-11-15 |
| Design Arena Web-app Agent | 1174 Elo | 1273 Elo | source · 2026-11-15 |
| Design Arena Website | 1292 Elo | 1336 Elo | source · 2026-11-15 |
| FrontierMath Tiers 1-3 (Epoch AI) | 58.9% ± 2.9 | 72.2% ± 2.7 | source · 2026-08-02 |
| GPQA Diamond (Epoch AI) | 85.9% ± 2.5 | 93.1% ± 1.5 | source · 2026-08-07 |
| GPQA Diamond (Epoch AI) | 86.4% ± 2.4 | 93.1% ± 1.5 | source · 2026-08-06 |
| GPQA Diamond (Epoch AI) | 94.1% ± 1.4 | 93.1% ± 1.5 | source · 2026-08-02 |
| LiveBench Agentic Coding | 43.4% | 62.2% | source · 2026-10-18 |
| LiveBench Coding | 77.9% | 81.5% | source · 2026-10-18 |
| LiveBench Data Analysis | 63% | 78.7% | source · 2026-10-18 |
| LiveBench Instruction Following | 75.4% | 71.4% | source · 2026-10-18 |
| LiveBench Language | 83.9% | 85.5% | source · 2026-10-18 |
| LiveBench Math | 86.4% | 84.4% | source · 2026-10-18 |
| LiveBench Reasoning | 85.2% | 90.7% | source · 2026-10-18 |
| LMArena Agent Bash Recovery | -18.2 | 4.4 | source · 2026-10-08 |
| LMArena Creative Writing | 1466 Elo | 1453 Elo | source · 2026-11-11 |
| LMArena Instruction Following | 1467 Elo | 1484 Elo | source · 2026-11-11 |
| LMArena Long Query | 1475 Elo | 1490 Elo | source · 2026-11-11 |
| LMArena Math | 1505 Elo | 1496 Elo | source · 2026-11-11 |
| LMArena Text Factuality | 1472 Elo | 1471 Elo | source · 2026-11-11 |
| LMArena WebDev Image-to-Web | 1545 Elo | 1586 Elo | source · 2026-11-10 |
| OTIS Mock AIME (Epoch AI) | 82.2% ± 5.8 | 97.2% ± 1.1 | source · 2026-08-07 |
| OTIS Mock AIME (Epoch AI) | 94.2% ± 3.1 | 97.2% ± 1.1 | source · 2026-08-02 |
| SimpleQA Verified (Epoch AI) | 66.2% ± 1.5 | 50.6% ± 1.6 | source · 2026-08-27 |
Values are as published by each evaluator, in its own units; rows from different evaluators are not on a common scale.
task evidence
How they place when the question changes
Lower ranks are better. “Best” marks the strongest option in this shortlist for that task.