Up to four models
Kimi K2.5 vs Qwen 3.5 Plus (hosted 397B-A17B)
On the index (GPT-4 = 100), Kimi K2.5 scores 145 and Qwen 3.5 Plus (hosted 397B-A17B) 141. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
Kimi K2.5
145130–161
WeightsOpen
ReleasedJan 2026
Price in / out$0.50 / $2.5
Context262K
Core tests taken5 of 9
141124–158
WeightsClosed
ReleasedFeb 2026
Price in / out–
Context–
Core tests taken1 of 9
Kimi K2.5 and Qwen 3.5 Plus (hosted 397B-A17B) are too close to call (4 points apart, within the uncertainty), ahead on 1 of 1 shared core tests.
Test by testthird-party results
Kimi K2.5
Qwen 3.5 Plus (hosted 397B-A17B)
Every result as a table
| Test | Kimi K2.5 | Qwen 3.5 Plus (hosted 397B-A17B) |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 87.6% | 84.9% |
| GPQA Diamond (Vals AI) | 84.1% | 87.4% |
| MMLU Pro | 85.9% | 87.2% |
| MMMU Pro | 84.3% | 22.8% |
| CL-bench | 19.3% | 19.8% |
| SimpleQA Verified | 34.3% | 25.4% |
| Maths | ||
| AIME-style maths (OTIS mock) | 92.2% | 86.7% |
| FrontierMath (2025 set) | 27.9% | 21.0% |
| FrontierMath tier 4 (2025 set) | 4.2% | 2.1% |
| Coding | ||
| LiveCodeBench | 83.9% | 85.3% |
| SWE-bench | 70.0% | 71.2% |
| Vibe Code Bench v1.1 | 17.5% | 15.7% |
| Professional work | ||
| CorpFin v2 | 68.3% | 65.3% |
| MortgageTax | 66.5% | 60.8% |
Tests at least two of these models have taken. Bold rows are the core tests.