token.app › Compare › Kimi K2.6 vs GLM 5.2
Kimi K2.6 vs GLM 5.2
GLM 5.2 leads on 4 of 6 shared benchmarks. GLM 5.2 is 2.7× cheaper per token on a blended 3:1 basis. GLM 5.2 accepts the larger context window (1.0M).
Head to head
Blended price uses a 3:1 input:output mix
| Kimi K2.6 | GLM 5.2 | |
|---|---|---|
| Provider | Moonshot AI | Zhipu AI |
| Input $/1M | $0.580 | $0.252 |
| Output $/1M | $2.44 | $0.792 |
| Blended $/1M | $1.04 | $0.387 |
| Context window | 262K | 1.0M |
| Max output | 262K | 128K |
| Released | Apr 2026 | Jun 2026 |
| Licence | Open weights | Open weights |
| GPQA Diamond | 90.8% | 91.9% |
| SWE-bench Verified | 76.7% | 78.7% |
| FrontierMath T1–3 | 57.2% | 59.2% |
| FrontierMath T4 | 25.6% | 29.3% |
| SimpleQA Verified | 38.7% | 38.1% |
| OTIS Mock AIME | 96.1% | 86.4% |
Benchmark scores independently run and published by Epoch AI, 'AI Benchmarking Hub', used under CC BY 4.0. Only benchmarks with a score for BOTH models are compared.
Choose Kimi K2.6 if…
- Higher SimpleQA Verified (38.7% vs 38.1%)
- Higher OTIS Mock AIME (96.1% vs 86.4%)
Choose GLM 5.2 if…
- Costs less per token — $0.387 vs $1.04 blended
- Higher GPQA Diamond (91.9% vs 90.8%)
- Higher SWE-bench Verified (78.7% vs 76.7%)
- Higher FrontierMath T1–3 (59.2% vs 57.2%)
- Higher FrontierMath T4 (29.3% vs 25.6%)
- Larger context window (1.0M)
- Newer model (released Jun 2026)
FAQ
Which is better, Kimi K2.6 or GLM 5.2?
Across the 6 benchmarks both models have independently-run scores for, Kimi K2.6 leads on 2 and GLM 5.2 leads on 4. Benchmarks are one input — price and context window are on this page too.
Is Kimi K2.6 cheaper than GLM 5.2?
GLM 5.2 is cheaper: $0.387 versus $1.04 per million tokens blended at 3:1 input:output. Input alone: $0.580 vs $0.252. Output alone: $2.44 vs $0.792.
What context windows do Kimi K2.6 and GLM 5.2 have?
Kimi K2.6: 262,144 tokens. GLM 5.2: 1,048,576 tokens.
Who makes Kimi K2.6 and GLM 5.2?
Kimi K2.6 is made by Moonshot AI. GLM 5.2 is made by Zhipu AI.