GLM-4.6 Instruct vs Kimi K1.5: which model should you choose?
We compared GLM-4.6 Instruct and Kimi K1.5 on price, context window and 12 benchmarks. Kimi K1.5 has the stronger average benchmark score; Kimi K1.5 is cheaper on a blended 3:1 basis.
GLM-4.6 Instruct
GLM-4.6 Instruct is a multimodal model from Zhipu AI. It offers a 1,000,000-token context window, costs $5.15 per million input tokens and $24.32 per million output tokens, and averages 80.4 across the index's benchmark suite.
- Input
- $5.15 / 1M
- Output
- $24.32 / 1M
- Context
- 1,000,000
- Avg score
- 80.4
- Open weights
- Yes
Kimi K1.5
Kimi K1.5 is a multimodal model from Moonshot AI. It offers a 128,000-token context window, costs $5.19 per million input tokens and $21.20 per million output tokens, and averages 80.7 across the index's benchmark suite.
- Input
- $5.19 / 1M
- Output
- $21.20 / 1M
- Context
- 128,000
- Avg score
- 80.7
- Open weights
- Yes
Specification comparison
| Spec | GLM-4.6 Instruct | Kimi K1.5 | Edge |
|---|---|---|---|
| Input price / 1M | $5.15 | $5.19 | A |
| Output price / 1M | $24.32 | $21.20 | B |
| Context window | 1,000,000 | 128,000 | A |
| Max output | 128,000 | 4,096 | A |
| Average score | 80.4 | 80.7 | B |
| Arena Elo | 1426.6 | 1432.2 | B |
| Open weights | Yes | Yes | Tie |
Benchmark comparison
GLM-4.6 Instruct wins 5, Kimi K1.5 wins 7, and 0 benchmarks are tied. The table shows the modelled score for each model and the gap.
| Benchmark | GLM-4.6 Instruct | Kimi K1.5 | Gap | Winner |
|---|---|---|---|---|
| MMLU-Pro | 80.6 | 82.7 | 2.1 | Kimi K1.5 |
| GPQA Diamond | 75.8 | 74.4 | 1.4 | GLM-4.6 Instruct |
| SWE-bench Verified | 70.5 | 68.2 | 2.3 | GLM-4.6 Instruct |
| HumanEval | 85.3 | 87.1 | 1.8 | Kimi K1.5 |
| MATH-500 | 84.9 | 85.3 | 0.4 | Kimi K1.5 |
| AIME 2025 | 74.5 | 80.8 | 6.3 | Kimi K1.5 |
| LiveCodeBench | 72.6 | 71.1 | 1.5 | GLM-4.6 Instruct |
| IFEval | 87.4 | 87.9 | 0.5 | Kimi K1.5 |
| TruthfulQA | 83.8 | 84.7 | 0.9 | Kimi K1.5 |
| HellaSwag | 90.6 | 87.2 | 3.4 | GLM-4.6 Instruct |
| MMMU | 78.9 | 77.8 | 1.1 | GLM-4.6 Instruct |
| Arena Elo | 1426.6 | 1432.2 | 5.6 | Kimi K1.5 |
Price analysis
On a blended 3:1 input-to-output basis, GLM-4.6 Instruct costs about $9.94 per million tokens and Kimi K1.5 costs about $9.19. Kimi K1.5 is roughly 8% cheaper than GLM-4.6 Instruct. At high volume, that gap compounds quickly, so price should carry real weight unless the quality difference is decisive.
GLM-4.6 Instruct has the larger context window at 1,000,000 tokens, compared with 128,000 for Kimi K1.5. That matters for long documents, large codebases and multi-step agent traces.
Verdict
Across 12 shared benchmarks, GLM-4.6 Instruct wins 5, Kimi K1.5 wins 7, and 0 are tied. On the index average, Kimi K1.5 leads GLM-4.6 Instruct by 0.3 points (80.7 versus 80.4).
The price picture favours Kimi K1.5. The context picture favours GLM-4.6 Instruct. Those two dimensions often matter more than a few benchmark points once a model is good enough for the task.
If you need a single default, start with Kimi K1.5 for quality-sensitive work, and check whether its price holds at your expected volume before committing.
Choose GLM-4.6 Instruct if
- You need the larger 1,000,000-token context window.
- You need the larger 128,000-token output limit.
Choose Kimi K1.5 if
- You want the higher average benchmark score in this index.
- Unit cost matters and you want the cheaper blended price.
FAQ
Is GLM-4.6 Instruct better than Kimi K1.5?
On the index average, Kimi K1.5 leads GLM-4.6 Instruct by 0.3 points (80.7 versus 80.4). The better choice depends on price, context and your task. GLM-4.6 Instruct wins 5 benchmarks, Kimi K1.5 wins 7.
Which is cheaper, GLM-4.6 Instruct or Kimi K1.5?
Kimi K1.5 is cheaper on a blended 3:1 basis at about $9.19 per million tokens, versus $9.94 for GLM-4.6 Instruct.
Which has the larger context window?
GLM-4.6 Instruct has the larger context window at 1,000,000 tokens. Kimi K1.5 has 128,000 tokens.
Are these models open weights?
GLM-4.6 Instruct is open weights; Kimi K1.5 is open weights.
Which should I choose for production?
If you need a single default, start with Kimi K1.5 for quality-sensitive work, and check whether its price holds at your expected volume before committing.