Kimi K3 vs Qwen3.8 Max Preview
Kimi K3 leads Qwen3.8 Max Preview by 1.3 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. Kimi K3 wins 10 and Qwen3.8 Max Preview wins 6 of 16 shared benchmarks. Qwen3.8 Max Preview is cheaper for agent workloads.
Add more models to this comparison →Pillars
| Pillar | Kimi K3 | Qwen3.8 Max Preview |
|---|---|---|
| Agentic coding | 63 | 58 |
| Long-horizon autonomy | 65 | 63 |
| Knowledge-work agents | 42 | 46 |
| Computer use | 43 | 41 |
| Security & context learning | 53 | 52 |
Shared benchmarks
| Benchmark | Kimi K3 | Qwen3.8 Max Preview |
|---|---|---|
| APEX-Agentsindex | 47.8% | 63.3% |
| DeepSWEindex | 68.5% | 57.5% |
| FrontierSWEindex | 25.9% | 15.8% |
| Chess Puzzles | 37.0% | 46.0% |
| CritPt | 23.4% | 20.0% |
| DTBench | 91.2% | 92.0% |
| FrontierMath Tier 4 | 39.0% | 46.3% |
| FrontierMath Tiers 1-3 | 72.2% | 74.7% |
| GPQA Diamond | 93.1% | 92.7% |
| LMCA | 52.7% | 46.2% |
| MirrorCode | 54.4% | 52.2% |
| OTIS Mock AIME | 97.2% | 99.4% |
| ProofBench | 87.0% | 58.0% |
| SciCode | 59.5% | 53.2% |
| SimpleQA Verified | 50.6% | 45.8% |
| WebDev Arena | 1674 | 1671 |
Specs and price
| Kimi K3 | Qwen3.8 Max Preview | |
|---|---|---|
| Agent Index | 54.9 (#26) | 53.6 (#30) |
| Agent $/M | $1.39 | Free |
| Input / output $/M | $3.00 / $15.00 | Free / Free |
| Context | 1M | 1M |
| Released | Jul 16, 2026 | Jul 19, 2026 |
| Weights | Open | Closed |
| API hosts | 29 | 1 |
Don’t pick one. Route.
Shogo can run Kimi K3 and Qwen3.8 Max Preview side by side and send each step of an agent to the one that’s cheaper for it.
Try both in Shogo