Kimi K1.5 vs Mistral Large 3: which model should you choose?
We compared Kimi K1.5 and Mistral Large 3 on price, context window and 12 benchmarks. Mistral Large 3 has the stronger average benchmark score; Kimi K1.5 is cheaper on a blended 3:1 basis.
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
Mistral Large 3
Mistral Large 3 is a multimodal model from Mistral AI. It offers a 128,000-token context window, costs $5.41 per million input tokens and $23.83 per million output tokens, and averages 81.7 across the index's benchmark suite.
- Input
- $5.41 / 1M
- Output
- $23.83 / 1M
- Context
- 128,000
- Avg score
- 81.7
- Open weights
- Yes
Specification comparison
| Spec | Kimi K1.5 | Mistral Large 3 | Edge |
|---|---|---|---|
| Input price / 1M | $5.19 | $5.41 | A |
| Output price / 1M | $21.20 | $23.83 | A |
| Context window | 128,000 | 128,000 | Tie |
| Max output | 4,096 | 4,096 | Tie |
| Average score | 80.7 | 81.7 | B |
| Arena Elo | 1432.2 | 1448.6 | B |
| Open weights | Yes | Yes | Tie |
Benchmark comparison
Kimi K1.5 wins 4, Mistral Large 3 wins 8, and 0 benchmarks are tied. The table shows the modelled score for each model and the gap.
| Benchmark | Kimi K1.5 | Mistral Large 3 | Gap | Winner |
|---|---|---|---|---|
| MMLU-Pro | 82.7 | 84.6 | 1.9 | Mistral Large 3 |
| GPQA Diamond | 74.4 | 79.6 | 5.2 | Mistral Large 3 |
| SWE-bench Verified | 68.2 | 71.3 | 3.1 | Mistral Large 3 |
| HumanEval | 87.1 | 88.6 | 1.5 | Mistral Large 3 |
| MATH-500 | 85.3 | 84.1 | 1.2 | Kimi K1.5 |
| AIME 2025 | 80.8 | 78.3 | 2.5 | Kimi K1.5 |
| LiveCodeBench | 71.1 | 74.4 | 3.3 | Mistral Large 3 |
| IFEval | 87.9 | 89.8 | 1.9 | Mistral Large 3 |
| TruthfulQA | 84.7 | 83.7 | 1.0 | Kimi K1.5 |
| HellaSwag | 87.2 | 88.2 | 1.0 | Mistral Large 3 |
| MMMU | 77.8 | 76.2 | 1.6 | Kimi K1.5 |
| Arena Elo | 1432.2 | 1448.6 | 16.4 | Mistral Large 3 |
Price analysis
On a blended 3:1 input-to-output basis, Kimi K1.5 costs about $9.19 per million tokens and Mistral Large 3 costs about $10.02. Kimi K1.5 is roughly 8% cheaper than Mistral Large 3. At high volume, that gap compounds quickly, so price should carry real weight unless the quality difference is decisive.
Both models list a 128,000-token context window. That is enough for long documents, large codebases and multi-step agent traces.
Verdict
Across 12 shared benchmarks, Kimi K1.5 wins 4, Mistral Large 3 wins 8, and 0 are tied. On the index average, Mistral Large 3 leads Kimi K1.5 by 1.0 points (81.7 versus 80.7).
The price picture favours Kimi K1.5. The context picture is effectively a tie. 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 Mistral Large 3 for quality-sensitive work and Kimi K1.5 for high-volume, well-scoped tasks. Run both on a sample of your own traffic before locking in a choice.
Choose Kimi K1.5 if
- Unit cost matters and you want the cheaper blended price.
Choose Mistral Large 3 if
- You want the higher average benchmark score in this index.
FAQ
Is Kimi K1.5 better than Mistral Large 3?
On the index average, Mistral Large 3 leads Kimi K1.5 by 1.0 points (81.7 versus 80.7). The better choice depends on price, context and your task. Kimi K1.5 wins 4 benchmarks, Mistral Large 3 wins 8.
Which is cheaper, Kimi K1.5 or Mistral Large 3?
Kimi K1.5 is cheaper on a blended 3:1 basis at about $9.19 per million tokens, versus $10.02 for Mistral Large 3.
Which has the larger context window?
Both models list a 128,000-token context window.
Are these models open weights?
Kimi K1.5 is open weights; Mistral Large 3 is open weights.
Which should I choose for production?
If you need a single default, start with Mistral Large 3 for quality-sensitive work and Kimi K1.5 for high-volume, well-scoped tasks. Run both on a sample of your own traffic before locking in a choice.