Model comparison
Kimi K3 vs Qwen3.6 Max Preview
Kimi K3 is the stronger model overall, scoring 59.5 to 51.5 on the Noometry Index. Qwen3.6 Max Preview costs 2.1× less per token, which makes it the better buy when Kimi K3's lead doesn't matter for your workload.
Last verified . 26 shared benchmarks.
Alibaba (Qwen)Summary
- They share 26 benchmarks with published results for both. Kimi K3 scores higher in 8 categories and Qwen3.6 Max Preview in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Kimi K3 leads 63.0 to 41.7.
- The biggest single-benchmark swing is NYT Connections (extended): 93.6% for Kimi K3 and 74.1% for Qwen3.6 Max Preview.
- Qwen3.6 Max Preview is cheaper at $1.30 / $7.80 per million input/output tokens, against $3 / $15 for Kimi K3.
- Kimi K3 accepts more context: 1.05M tokens versus 262K.
- Kimi K3 has downloadable open weights; the other is API-only.
Side by side
| Kimi K3 | Qwen3.6 Max Preview | |
|---|---|---|
| Provider | Moonshot AI | Alibaba (Qwen) |
| Noometry Index | 59.5 | 51.5 |
| Released | 2026-07-16 | 2026-04-20 |
| Weights | Open | Proprietary |
| Context window | 1.05M | 262K |
| Max output | 1.05M | 66K |
| Input $ / M tokens | $3 | $1.30 |
| Output $ / M tokens | $15 | $7.80 |
| Results tracked | 53 | 29 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K3 leads
Kimi K3: 61.0 (#10), Qwen3.6 Max Preview: 48.7 (#54)
| Benchmark | Kimi K3 | Qwen3.6 Max Preview |
|---|---|---|
| LMArena WebDev | 1654 | 1482 |
| LMArena Coding | 1508 | 1471 |
| SWE-bench Verified | — | 76.7% |
| DeepSWE | 68.5% | — |
| FrontierCode | 44.2% | — |
| FrontierSWE | 25.9% | — |
| SciCode | 59.5% | — |
| WeirdML | 82.6% | — |
| ALE-Bench | 1,524 | — |
Agentic & Tool Use Not comparable
Kimi K3: 41.8 (#20), Qwen3.6 Max Preview: —
| Benchmark | Kimi K3 | Qwen3.6 Max Preview |
|---|---|---|
| Vending-Bench 2 | 5,165 | 4,254 |
| APEX-Agents | 50.6% | — |
| τ²-bench Banking | 37.1% | — |
| PostTrainBench | 32% | — |
| GBAEval | 48.3% | — |
| GDP.pdf | 19% | — |
Reasoning Kimi K3 leads
Kimi K3: 63.0 (#17), Qwen3.6 Max Preview: 41.7 (#53)
| Benchmark | Kimi K3 | Qwen3.6 Max Preview |
|---|---|---|
| SimpleBench | 60.7% | 63% |
| NYT Connections (extended) | 93.6% | 74.1% |
| Chess Puzzles | 39% | 20% |
| LMArena Hard Prompts | 1496 | 1457 |
| Mystery Game Puzzles | 26% | 19% |
| DTBench | 91.2% | 87.2% |
| LMCA | 52.7% | 42.5% |
| Epoch Capabilities Index | 157.45 | 149.24 |
| ARC-AGI-2 | 60.4% | — |
| ARC-AGI-1 | 94.5% | — |
| CritPt | 23.4% | — |
| Surface Evolver Bench | 95% | — |
| ForecastBench | 61.1 | — |
Math Kimi K3 leads
Kimi K3: 74.2 (#16), Qwen3.6 Max Preview: 54.1 (#46)
| Benchmark | Kimi K3 | Qwen3.6 Max Preview |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 97.2% | 91.1% |
| LMArena Math | 1491 | 1465 |
| FrontierMath (Tiers 1-3) | 72.2% | — |
| FrontierMath Tier 4 | 39% | — |
| MathArena Final-Answer Competitions | 87.8% | — |
| ProofBench | 87% | — |
| FrontierMath (Feb 2025 set) | — | 23.1% |
| FrontierMath Tier 4 (v1) | — | 4.2% |
Knowledge Kimi K3 leads
Kimi K3: 63.2 (#21), Qwen3.6 Max Preview: 57.6 (#39)
| Benchmark | Kimi K3 | Qwen3.6 Max Preview |
|---|---|---|
| GPQA Diamond | 93.1% | 87.4% |
| SimpleQA Verified | 50.6% | 52% |
| LMArena Expert | 1521 | 1478 |
Multimodal Not comparable
Kimi K3: 37.8 (#70), Qwen3.6 Max Preview: —
| Benchmark | Kimi K3 | Qwen3.6 Max Preview |
|---|---|---|
| Blueprint-Bench 2 | 29.5% | — |
| Furniture Assembly | 34.2% | — |
Multilingual Kimi K3 leads
Kimi K3: 56.3 (#21), Qwen3.6 Max Preview: 54.2 (#48)
| Benchmark | Kimi K3 | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Non-English | 1466 | 1437 |
| LMArena Chinese | 1529 | 1487 |
| LMArena French | 1491 | 1449 |
| LMArena Russian | 1482 | 1445 |
| LMArena Spanish | 1472 | 1454 |
| LMArena German | 1488 | — |
| LMArena Japanese | 1487 | — |
| LMArena Korean | 1458 | — |
Instruction Following Kimi K3 leads
Kimi K3: 77.7 (#14), Qwen3.6 Max Preview: 75.7 (#55)
| Benchmark | Kimi K3 | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Instruction Following | 1483 | 1438 |
Long Context Kimi K3 leads
Kimi K3: 45.8 (#29), Qwen3.6 Max Preview: 44.6 (#61)
| Benchmark | Kimi K3 | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Longer Query | 1494 | 1457 |
Writing & Preference Kimi K3 leads
Kimi K3: 76.6 (#4), Qwen3.6 Max Preview: 63.8 (#60)
| Benchmark | Kimi K3 | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Text | 1476 | 1447 |
| LMArena Creative Writing | 1454 | 1435 |
| LMArena Multi-Turn | 1488 | 1456 |
| EQ-Bench Creative Writing | 2082 | — |
| EQ-Bench 4 | 1339 | — |
Frequently asked questions
Is Kimi K3 better than Qwen3.6 Max Preview?
Kimi K3 is the stronger model overall, scoring 59.5 to 51.5 on the Noometry Index. Qwen3.6 Max Preview costs 2.1× less per token, which makes it the better buy when Kimi K3's lead doesn't matter for your workload.
Which is cheaper, Kimi K3 or Qwen3.6 Max Preview?
Qwen3.6 Max Preview is cheaper. It lists at $1.30 per million input tokens and $7.80 per million output tokens; Kimi K3 lists at $3 and $15.
Is Kimi K3 or Qwen3.6 Max Preview better for coding?
Kimi K3 scores higher on coding benchmarks: 61.0 versus 48.7 in the Noometry coding category.
Which has the bigger context window?
Kimi K3 does, with 1.05M tokens against 262K.
How many benchmarks do Kimi K3 and Qwen3.6 Max Preview share?
26 benchmarks have published results for both models. Kimi K3 has 53 scored results on Noometry and Qwen3.6 Max Preview has 29.