Model comparison
Kimi K2.5 vs Qwen3.6 Plus
Kimi K2.5 and Qwen3.6 Plus score almost the same on the Noometry Index (48.1 vs 47.5), so choose on price, context window or the category you care about most.
Last verified . 33 shared benchmarks.
Alibaba (Qwen)Summary
- They share 33 benchmarks with published results for both. Kimi K2.5 scores higher in 7 categories and Qwen3.6 Plus in 1 category; 5 gaps are clear of the uncertainty.
- The widest gap is in coding, where Kimi K2.5 leads 48.8 to 40.8.
- The biggest single-benchmark swing is SWE-bench Verified: 73.8% for Kimi K2.5 and 57.9% for Qwen3.6 Plus.
- Kimi K2.5 is cheaper at $0.45 / $2.25 per million input/output tokens, against $0.50 / $3 for Qwen3.6 Plus.
- Qwen3.6 Plus accepts more context: 1M tokens versus 262K.
- Kimi K2.5 has downloadable open weights; the other is API-only.
Side by side
| Kimi K2.5 | Qwen3.6 Plus | |
|---|---|---|
| Provider | Moonshot AI | Alibaba (Qwen) |
| Noometry Index | 48.1 | 47.5 |
| Released | 2026-01-27 | 2026-03-31 |
| Weights | Open | Proprietary |
| Context window | 262K | 1M |
| Max output | 262K | 66K |
| Input $ / M tokens | $0.45 | $0.50 |
| Output $ / M tokens | $2.25 | $3 |
| Results tracked | 51 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2.5 leads
Kimi K2.5: 48.8 (#53), Qwen3.6 Plus: 40.8 (#130)
| Benchmark | Kimi K2.5 | Qwen3.6 Plus |
|---|---|---|
| SWE-bench Verified | 73.8% | 57.9% |
| LMArena WebDev | 1437 | 1461 |
| SciCode | 49% | 40.7% |
| LMArena Coding | 1474 | 1467 |
| ALE-Bench | 821.65 | 670.15 |
| SWE-bench Verified (bash only) | 70.8% | — |
| SWE-bench Multilingual | 67.3% | — |
| WeirdML | 45.6% | — |
Agentic & Tool Use Not comparable
Kimi K2.5: 34.2 (#48), Qwen3.6 Plus: —
| Benchmark | Kimi K2.5 | Qwen3.6 Plus |
|---|---|---|
| Vending-Bench 2 | 1,198 | 5,115 |
| Terminal-Bench | 43.2% | — |
| OSWorld | 63.3% | — |
Reasoning Kimi K2.5 leads
Kimi K2.5: 31.2 (#80), Qwen3.6 Plus: 29.3 (#93)
| Benchmark | Kimi K2.5 | Qwen3.6 Plus |
|---|---|---|
| NYT Connections (extended) | 69.9% | 60.3% |
| CritPt | 3.1% | 2.9% |
| Chess Puzzles | 12% | 17% |
| Thematic Generalization | 69.4% | 59.5% |
| LMArena Hard Prompts | 1453 | 1449 |
| Epoch Capabilities Index | 148.03 | 147.65 |
| ARC-AGI-2 | 11.8% | — |
| SimpleBench | 46.8% | — |
| Kagi LLM Benchmark | 78.5% | — |
| ARC-AGI-1 | 65.3% | — |
| EnigmaEval | 3.4% | — |
| Mystery Game Puzzles | — | 12% |
| DTBench | — | 81.9% |
| LMCA | — | 33.1% |
Math Too close to call
Kimi K2.5: 51.8 (#53), Qwen3.6 Plus: 51.8 (#54)
| Benchmark | Kimi K2.5 | Qwen3.6 Plus |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 92.2% | 93.3% |
| LMArena Math | 1470 | 1450 |
| FrontierMath (Feb 2025 set) | 27.9% | 26.2% |
| FrontierMath Tier 4 (v1) | 4.2% | 8.3% |
| FrontierMath (Tiers 1-3) | — | 38.2% |
| MathArena Final-Answer Competitions | 62.3% | — |
Knowledge Qwen3.6 Plus leads
Kimi K2.5: 53.6 (#56), Qwen3.6 Plus: 56.1 (#45)
| Benchmark | Kimi K2.5 | Qwen3.6 Plus |
|---|---|---|
| GPQA Diamond | 87.6% | 88.4% |
| SimpleQA Verified | 34.3% | 44.1% |
| LMArena Expert | 1466 | 1454 |
| Humanity's Last Exam | 24.4% | — |
| Vectara Hallucination Rate | 14.2% | — |
Multimodal Not comparable
Kimi K2.5: 41.1 (#39), Qwen3.6 Plus: —
| Benchmark | Kimi K2.5 | Qwen3.6 Plus |
|---|---|---|
| LMArena Vision | 1269 | — |
| LMArena Document | 1430 | — |
Multilingual Too close to call
Kimi K2.5: 53.9 (#53), Qwen3.6 Plus: 53.3 (#70)
| Benchmark | Kimi K2.5 | Qwen3.6 Plus |
|---|---|---|
| LMArena Non-English | 1433 | 1424 |
| LMArena Chinese | 1495 | 1477 |
| LMArena French | 1454 | 1455 |
| LMArena German | 1441 | 1452 |
| LMArena Japanese | 1421 | 1389 |
| LMArena Korean | 1410 | 1379 |
| LMArena Russian | 1435 | 1434 |
| LMArena Spanish | 1450 | 1432 |
Instruction Following Too close to call
Kimi K2.5: 75.3 (#64), Qwen3.6 Plus: 75.0 (#74)
| Benchmark | Kimi K2.5 | Qwen3.6 Plus |
|---|---|---|
| LMArena Instruction Following | 1431 | 1425 |
Long Context Kimi K2.5 leads
Kimi K2.5: 52.1 (#7), Qwen3.6 Plus: 45.2 (#49)
| Benchmark | Kimi K2.5 | Qwen3.6 Plus |
|---|---|---|
| CL-bench | 19.3% | 20.3% |
| LMArena Longer Query | 1445 | 1439 |
| Fiction.LiveBench | 86.1% | — |
| CL-bench Life | 13.2% | — |
Writing & Preference Kimi K2.5 leads
Kimi K2.5: 65.1 (#53), Qwen3.6 Plus: 62.2 (#82)
| Benchmark | Kimi K2.5 | Qwen3.6 Plus |
|---|---|---|
| LMArena Text | 1445 | 1437 |
| LMArena Creative Writing | 1423 | 1404 |
| LMArena Multi-Turn | 1444 | 1438 |
| EQ-Bench Creative Writing | 1579 | — |
Frequently asked questions
Is Kimi K2.5 better than Qwen3.6 Plus?
Kimi K2.5 and Qwen3.6 Plus score almost the same on the Noometry Index (48.1 vs 47.5), so choose on price, context window or the category you care about most.
Which is cheaper, Kimi K2.5 or Qwen3.6 Plus?
Kimi K2.5 is cheaper. It lists at $0.45 per million input tokens and $2.25 per million output tokens; Qwen3.6 Plus lists at $0.50 and $3.
Is Kimi K2.5 or Qwen3.6 Plus better for coding?
Kimi K2.5 scores higher on coding benchmarks: 48.8 versus 40.8 in the Noometry coding category.
Which has the bigger context window?
Qwen3.6 Plus does, with 1M tokens against 262K.
How many benchmarks do Kimi K2.5 and Qwen3.6 Plus share?
33 benchmarks have published results for both models. Kimi K2.5 has 51 scored results on Noometry and Qwen3.6 Plus has 37.