MistralMistral Large 3
- Released
- Dec 2, 2025
- Tracked since
- 2026-07-23
Intelligence index9.3Ranks 394 of 664 models with this metric
Coding index20.1Ranks 204 of 259 models with this metric
Agentic index1Ranks 133 of 156 models with this metric
Capability profile
5 axes vs. site averageMistral Large 3
Site average
Pricing
per 1M tokens- Input
- $0.500
- Output
- $1.50
- Cache read
- $0.050
Performance
- Output throughput
- 76 tokens/sec
- Time to first token
- 1.09s
- First answer token
- 1.09s
- End-to-end response
- 7.63s
History
6Intelligence index
15.9→9.3
Output
Unchanged across 62 days of records
Output throughput
51→76
Cheaper at this level
Models with a comparable intelligence index and a lower output price- Gemma 4 E4B (Reasoning)
GoogleIntelligence 8.9$0.100−93% - Granite 4.2 3B
IBMIntelligence 9.1$0.120−92% - Qwen3.5 4B (Reasoning)
AlibabaIntelligence 13.1$0.150−90% - Qwen3.5 4B (Non-reasoning)AlibabaIntelligence 10.8$0.150−90%
- gpt-oss-20b (high)
OpenAIIntelligence 9$0.180−88%