LLM Comparison
Mistral Small 4 vs Sonar Reasoning Pro
Side-by-side specs, pricing & capabilities · Updated October 2026
Price vs Intelligence
Add to comparison
2/6 modelsSame tier:
| Organization | ||
| OpenTools Score | 17 44.3 | 49 9.8 |
| Family | Mistral | Sonar |
| Status | Current | Current |
| Release Date | Mar 2026 | Mar 2025 |
| Context Window | 262K tokens | 128K tokens |
| Input Price | $0.15/M tokens | $2.00/M tokens |
| Output Price | $0.60/M tokens | $8.00/M tokens |
| Pricing Notes | Cache read: $0.0150/M tokens | — |
| Capabilities | textvisioncodetool-use | textvisioncodeextended-thinking |
| API Identifier | mistralai/mistral-small-2603 | perplexity/sonar-reasoning-pro |
| Benchmarks | ||
| MMLU-Pro | 68.5mistral | — |
| HumanEval | 78.5mistral | — |
| MGSM | 72.3mistral | — |
| GPQA Diamond | 58.8mistral | 62.3perplexity |
| LiveCodeBench | 64mistral | — |
| Artificial Analysis Intelligence Index v4.3 | 11.4511artificial-analysis | — |
| SciCode | 38.7731artificial-analysis | — |
| Terminal-Bench 2.1 | 20.9738artificial-analysis | — |
| MATH-500 | — | 92.1perplexity |
| AIME | — | 77perplexity |
| MMLU Pro | — | 79perplexity |
| View Mistral Small 4 | View Sonar Reasoning Pro | |
Cost Calculator
Enter your expected monthly token usage to compare costs.
| Model | Input | Output | Total / mo | vs Best |
|---|---|---|---|---|
| Mistral Small 4Cheapest | $0.15 | $0.30 | $0.45 | — |
| Sonar Reasoning Pro | $2.00 | $4.00 | $6.00 | +1233% |
Mistral AI
Mistral Small 4
Mistral Small 4 is Mistral's Apache-2.0 open-weight hybrid model for instruction following, reasoning, and coding. It has 119B total parameters, 6.5B active parameters, and a 256K-token context window.
Perplexity AI
Sonar Reasoning Pro
Sonar Reasoning Pro is a multimodal llm from Perplexity AI. Supports up to 128,000 token context window. Achieves 83.0% on MMLU. Available from $2.00/M input tokens.
More Comparisons
Looking for more AI models?
Browse All LLMs