MistralMistral Small 4 (Non-reasoning)
- Released
- Mar 16, 2026
- Tracked since
- 2026-07-23
Intelligence index9Ranks 404 of 664 models with this metric
Coding index—Not tested
Agentic index—Not tested
Capability profile
5 axes vs. site averageMistral Small 4 (Non-reasoning)
Site average
Some dimensions have no data yet — marked on the chart
Pricing
per 1M tokens- Input
- $0.150
- Output
- $0.600
- Cache read
- $0.010
Performance
- Output throughput
- 144 tokens/sec
- Time to first token
- 770ms
- First answer token
- 770ms
- End-to-end response
- 4.23s
History
2Intelligence index
12.4→9
Output
Unchanged across 62 days of records
Output throughput
150→144
Cheaper at this level
Models with a comparable intelligence index and a lower output price- Gemma 4 E4B (Reasoning)
GoogleIntelligence 8.9$0.100−83% - Granite 4.2 3B
IBMIntelligence 9.1$0.120−80% - Qwen3.5 4B (Reasoning)
AlibabaIntelligence 13.1$0.150−75% - Qwen3.5 4B (Non-reasoning)AlibabaIntelligence 10.8$0.150−75%
- Sarvam 105B (high)SarvamIntelligence 8.8$0.170−72%