Mistral · Model profile
Mistral Medium 3
Intelligence, Performance & Price Analysis
Source: Canonical slug: mistral-medium-3 · Canonical model registry at build time
Routing verdict
Capable everyday model
Good for routine tasks; route complex reasoning and premium workloads to stronger models.
Mistral Medium 3 summary metrics
- Intelligence
- 12 scoreMistral Medium 3 scores 12 (estimated) on the Artificial Analysis Intelligence Index, placing it above average among other non-reasoning models in a similar price tier (median: 11).
- Speed
- 48.2 output tokens/secMistral Medium 3 generates output at 48.2 tokens per second (based on Mistral's API), which is at the lower end compared to other non-reasoning models in a similar price tier (median: 95.5 t/s).
- Latency
- 1.47s TTFTMistral Medium 3 has a time to first token (TTFT) of 1.47s (based on Mistral's API), which is better than average compared to other non-reasoning models in a similar price tier (median: 1.53s).
- Input Price
- $0.40 / 1M tokensMistral Medium 3 costs $0.40 per 1M input tokens (somewhat higher than average, median: $0.20) and $2.00 per 1M output tokens (at the higher end, median: $0.70), based on Mistral's API.
- Output Price
- $2.00 / 1M tokensMistral Medium 3 costs $0.40 per 1M input tokens (somewhat higher than average, median: $0.20) and $2.00 per 1M output tokens (at the higher end, median: $0.70), based on Mistral's API.
Assessment
Routing verdict and task fit
| Workload | Rating | Notes |
|---|---|---|
| Complex reasoning & agentic workflows | Viable | Intelligence score 12 handles routine reasoning but may struggle with open-ended agentic tasks. |
| High-volume chat & customer-facing | Viable | Output speed may be a bottleneck for real-time chat at scale. |
| Latency-sensitive applications | Optimal | TTFT 1.47s — adequate latency for most interactive use cases. |
| Cost-sensitive pipelines | Viable | Output pricing at $2.00 is premium. Route high-volume simple tasks to cheaper alternatives. |
Evidence
Evidence charts
AA-Omniscience Index
AA-Omniscience Index (higher is better) measures knowledge reliability and hallucination. It rewards correct answers, penalizes hallucinations, and has no penalty for refusing to answer. Scores range from -100 to 100, where 0 means as many correct as incorrect answers, and negative scores mean more incorrect than correct. · Evaluation results measured independently by Artificial Analysis
- Claude Fable 5 (with fallback)40.1
- Gemini 3.5 Flash22.7
- GPT-5.5 (xhigh)20.1
- Grok 4.3 (high)18.3
- Kimi K2.66.4
- Muse Spark4.1
- GLM-5.2 (max)4
- MiniMax-M31.4
- Nemotron 3 Ultra-0.833
- DeepSeek V4 Pro (max)-10
- Mistral Medium 3 (this model)-31.5
- Mistral Large 3-39.4
- DeepSeek V3 (Dec)-41.4
- Llama 4 Maverick-41.8
- Mistral Medium 3.1 (this model)-45.5
- MiMo-V2-Flash-48.5
- gpt-oss-120b (high)-50
- GPT-4.1 mini-50.1
- Mistral Small 3.1-50.3
- Mistral Small 3.2-50.4
| Model | AA-Omniscience Index |
|---|---|
| Claude Fable 5 (with fallback) | 40.1 |
| Gemini 3.5 Flash | 22.7 |
| GPT-5.5 (xhigh) | 20.1 |
| Grok 4.3 (high) | 18.3 |
| Kimi K2.6 | 6.4 |
| Muse Spark | 4.1 |
| GLM-5.2 (max) | 4 |
| MiniMax-M3 | 1.4 |
| Nemotron 3 Ultra | -0.833 |
| DeepSeek V4 Pro (max) | -10 |
| Mistral Medium 3 (this model) | -31.5 |
| Mistral Large 3 | -39.4 |
| DeepSeek V3 (Dec) | -41.4 |
| Llama 4 Maverick | -41.8 |
| Mistral Medium 3.1 (this model) | -45.5 |
| MiMo-V2-Flash | -48.5 |
| gpt-oss-120b (high) | -50 |
| GPT-4.1 mini | -50.1 |
| Mistral Small 3.1 | -50.3 |
| Mistral Small 3.2 | -50.4 |
Published benchmark dataset · Retrieved
Method and source
- Methodology
- Independent test run by Artificial Analysis on dedicated hardware.
- Chart interpretation
- Each bar is one model measured the same way, so this model can be read against the others. The chart lists its source and retrieval date.
Artificial Analysis Intelligence Index by Open Weights / Proprietary
Artificial Analysis Intelligence Index v4.1 incorporates 9 evaluations: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR · Evaluation results measured independently by Artificial Analysis
- Claude Fable 5 (with fallback)59.9
- GPT-5.5 (xhigh)54.8
- GLM-5.2 (max)51.1
- Gemini 3.5 Flash50.2
- MiniMax-M344.4
- DeepSeek V4 Pro (max)44.3
- Kimi K2.644.2
- Muse Spark43.1
- Nemotron 3 Ultra37.8
- Grok 4.3 (high)37.6
- MiMo-V2-Flash24.7
- gpt-oss-120b (high)23.8
- Qwen3 Coder Next21.1
- Mistral Large 315.9
- GPT-4.1 mini14.8
- Mistral Small 3.114.7
- Mistral Medium 3.1 (this model)14.7
- Llama 4 Maverick14.3
- DeepSeek V3 (Dec)14.2
- Ling 2.6 Flash14.1
| Model | Artificial Analysis Intelligence Index by Open Weights / Proprietary |
|---|---|
| Claude Fable 5 (with fallback) | 59.9 |
| GPT-5.5 (xhigh) | 54.8 |
| GLM-5.2 (max) | 51.1 |
| Gemini 3.5 Flash | 50.2 |
| MiniMax-M3 | 44.4 |
| DeepSeek V4 Pro (max) | 44.3 |
| Kimi K2.6 | 44.2 |
| Muse Spark | 43.1 |
| Nemotron 3 Ultra | 37.8 |
| Grok 4.3 (high) | 37.6 |
| MiMo-V2-Flash | 24.7 |
| gpt-oss-120b (high) | 23.8 |
| Qwen3 Coder Next | 21.1 |
| Mistral Large 3 | 15.9 |
| GPT-4.1 mini | 14.8 |
| Mistral Small 3.1 | 14.7 |
| Mistral Medium 3.1 (this model) | 14.7 |
| Llama 4 Maverick | 14.3 |
| DeepSeek V3 (Dec) | 14.2 |
| Ling 2.6 Flash | 14.1 |
Published benchmark dataset · Retrieved
Method and source
- Methodology
- Independent test run by Artificial Analysis on dedicated hardware.
- Benchmark interpretation
- Higher values indicate stronger overall capability. Bars show how models compare on composite intelligence metrics.
Artificial Analysis Intelligence Index
Artificial Analysis Intelligence Index v4.1 incorporates 9 evaluations: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR · Evaluation results measured independently by Artificial Analysis
- Claude Fable 5 (with fallback)59.9
- GPT-5.5 (xhigh)54.8
- GLM-5.2 (max)51.1
- Gemini 3.5 Flash50.2
- MiniMax-M344.4
- DeepSeek V4 Pro (max)44.3
- Kimi K2.644.2
- Muse Spark43.1
- Nemotron 3 Ultra37.8
- Grok 4.3 (high)37.6
- MiMo-V2-Flash24.7
- gpt-oss-120b (high)23.8
- Qwen3 Coder Next21.1
- Mistral Large 315.9
- GPT-4.1 mini14.8
- Mistral Small 3.114.7
- Mistral Medium 3.1 (this model)14.7
- Llama 4 Maverick14.3
- DeepSeek V3 (Dec)14.2
- Ling 2.6 Flash14.1
| Model | Artificial Analysis Intelligence Index |
|---|---|
| Claude Fable 5 (with fallback) | 59.9 |
| GPT-5.5 (xhigh) | 54.8 |
| GLM-5.2 (max) | 51.1 |
| Gemini 3.5 Flash | 50.2 |
| MiniMax-M3 | 44.4 |
| DeepSeek V4 Pro (max) | 44.3 |
| Kimi K2.6 | 44.2 |
| Muse Spark | 43.1 |
| Nemotron 3 Ultra | 37.8 |
| Grok 4.3 (high) | 37.6 |
| MiMo-V2-Flash | 24.7 |
| gpt-oss-120b (high) | 23.8 |
| Qwen3 Coder Next | 21.1 |
| Mistral Large 3 | 15.9 |
| GPT-4.1 mini | 14.8 |
| Mistral Small 3.1 | 14.7 |
| Mistral Medium 3.1 (this model) | 14.7 |
| Llama 4 Maverick | 14.3 |
| DeepSeek V3 (Dec) | 14.2 |
| Ling 2.6 Flash | 14.1 |
Published benchmark dataset · Retrieved
Method and source
- Methodology
- Independent test run by Artificial Analysis on dedicated hardware.
- Benchmark interpretation
- Higher values indicate stronger overall capability. Bars show how models compare on composite intelligence metrics.
Intelligence
Artificial Analysis Intelligence Index · Higher is better · Evaluation results measured independently by Artificial Analysis
- Claude Fable 5 (with fallback)59.9
- GPT-5.5 (xhigh)54.8
- GLM-5.2 (max)51.1
- Gemini 3.5 Flash50.2
- MiniMax-M344.4
- DeepSeek V4 Pro (max)44.3
- Kimi K2.644.2
- Muse Spark43.1
- Nemotron 3 Ultra37.8
- Grok 4.3 (high)37.6
- gpt-oss-120b (high)23.8
- Mistral Medium 3 (this model)12.5
| Model | Intelligence |
|---|---|
| Claude Fable 5 (with fallback) | 59.9 |
| GPT-5.5 (xhigh) | 54.8 |
| GLM-5.2 (max) | 51.1 |
| Gemini 3.5 Flash | 50.2 |
| MiniMax-M3 | 44.4 |
| DeepSeek V4 Pro (max) | 44.3 |
| Kimi K2.6 | 44.2 |
| Muse Spark | 43.1 |
| Nemotron 3 Ultra | 37.8 |
| Grok 4.3 (high) | 37.6 |
| gpt-oss-120b (high) | 23.8 |
| Mistral Medium 3 (this model) | 12.5 |
Published benchmark dataset · Retrieved
Method and source
- Methodology
- Independent test run by Artificial Analysis on dedicated hardware.
- Benchmark interpretation
- Higher values indicate stronger overall capability. Bars show how models compare on composite intelligence metrics.
Output Speed
Output tokens per second · Higher is better · Evaluation results measured independently by Artificial Analysis
- gpt-oss-120b (high)314 t/s
- Nemotron 3 Ultra250 t/s
- GLM-5.2 (max)218 t/s
- Gemini 3.5 Flash192 t/s
- GPT-4.1 nano188 t/s
- Ling 2.6 Flash177 t/s
- Mistral Small 3.1171 t/s
- Grok 4.3 (high)164 t/s
- Mistral Small 3.2147 t/s
- Llama 4 Maverick118 t/s
- Llama 4 Scout109 t/s
- MiniMax-M399 t/s
- Ministral 3 8B93 t/s
- Mistral Medium 3.1 (this model)89 t/s
- Qwen3 Coder Next89 t/s
- GPT-5.5 (xhigh)88 t/s
- GPT-4.1 mini86 t/s
- Llama 3.3 70B86 t/s
- Ministral 3 14B78 t/s
- Kimi K2.676 t/s
| Model | Output Speed |
|---|---|
| gpt-oss-120b (high) | 314 t/s |
| Nemotron 3 Ultra | 250 t/s |
| GLM-5.2 (max) | 218 t/s |
| Gemini 3.5 Flash | 192 t/s |
| GPT-4.1 nano | 188 t/s |
| Ling 2.6 Flash | 177 t/s |
| Mistral Small 3.1 | 171 t/s |
| Grok 4.3 (high) | 164 t/s |
| Mistral Small 3.2 | 147 t/s |
| Llama 4 Maverick | 118 t/s |
| Llama 4 Scout | 109 t/s |
| MiniMax-M3 | 99 t/s |
| Ministral 3 8B | 93 t/s |
| Mistral Medium 3.1 (this model) | 89 t/s |
| Qwen3 Coder Next | 89 t/s |
| GPT-5.5 (xhigh) | 88 t/s |
| GPT-4.1 mini | 86 t/s |
| Llama 3.3 70B | 86 t/s |
| Ministral 3 14B | 78 t/s |
| Kimi K2.6 | 76 t/s |
Published benchmark dataset · Retrieved
Method and source
- Methodology
- Independent test run by Artificial Analysis on dedicated hardware.
- Output speed context
- Speed should be read together with latency and cost; fast output does not always mean better user-perceived performance.
Speed
Output tokens per second · Higher is better · Evaluation results measured independently by Artificial Analysis
- gpt-oss-120b (high)314 t/s
- Nemotron 3 Ultra250 t/s
- GLM-5.2 (max)218 t/s
- Gemini 3.5 Flash192 t/s
- Grok 4.3 (high)164 t/s
- MiniMax-M399 t/s
- GPT-5.5 (xhigh)88 t/s
- Kimi K2.676 t/s
- DeepSeek V4 Pro (max)72 t/s
- Claude Fable 5 (with fallback)71 t/s
- Mistral Medium 3 (this model)48 t/s
| Model | Speed |
|---|---|
| gpt-oss-120b (high) | 314 t/s |
| Nemotron 3 Ultra | 250 t/s |
| GLM-5.2 (max) | 218 t/s |
| Gemini 3.5 Flash | 192 t/s |
| Grok 4.3 (high) | 164 t/s |
| MiniMax-M3 | 99 t/s |
| GPT-5.5 (xhigh) | 88 t/s |
| Kimi K2.6 | 76 t/s |
| DeepSeek V4 Pro (max) | 72 t/s |
| Claude Fable 5 (with fallback) | 71 t/s |
| Mistral Medium 3 (this model) | 48 t/s |
Published benchmark dataset · Retrieved
Method and source
- Methodology
- Independent test run by Artificial Analysis on dedicated hardware.
- Output speed context
- Speed should be read together with latency and cost; fast output does not always mean better user-perceived performance.
End-to-End Response Time
Seconds to output 500 tokens, including reasoning model 'thinking' time · Lower is better · Evaluation results measured independently by Artificial Analysis
- GPT-4.1 nano2.65 s
- Mistral Small 3.12.92 s
- Mistral Small 3.23.39 s
- Ling 2.6 Flash2.82 s
- Llama 4 Maverick4.24 s
- Llama 4 Scout4.61 s
- Ministral 3 8B5.35 s
- GPT-4.1 mini5.84 s
- Mistral Medium 3.1 (this model)5.64 s
- Ministral 3 14B6.4 s
- Llama 3.3 70B5.85 s
- Qwen3 Coder Next5.65 s
- gpt-oss-120b (high)1.59 s
- Mistral Large 39.43 s
- Mistral Medium 3 (this model)10.38 s
- Nemotron 3 Ultra2 s
- GLM-5.2 (max)2.3 s
- Grok 4.3 (high)3.05 s
- MiniMax-M35.05 s
- Gemini 3.5 Flash2.6 s
| Model | End-to-End Response Time |
|---|---|
| GPT-4.1 nano | 2.65 s |
| Mistral Small 3.1 | 2.92 s |
| Mistral Small 3.2 | 3.39 s |
| Ling 2.6 Flash | 2.82 s |
| Llama 4 Maverick | 4.24 s |
| Llama 4 Scout | 4.61 s |
| Ministral 3 8B | 5.35 s |
| GPT-4.1 mini | 5.84 s |
| Mistral Medium 3.1 (this model) | 5.64 s |
| Ministral 3 14B | 6.4 s |
| Llama 3.3 70B | 5.85 s |
| Qwen3 Coder Next | 5.65 s |
| gpt-oss-120b (high) | 1.59 s |
| Mistral Large 3 | 9.43 s |
| Mistral Medium 3 (this model) | 10.38 s |
| Nemotron 3 Ultra | 2 s |
| GLM-5.2 (max) | 2.3 s |
| Grok 4.3 (high) | 3.05 s |
| MiniMax-M3 | 5.05 s |
| Gemini 3.5 Flash | 2.6 s |
Published benchmark dataset · Retrieved
Method and source
- Methodology
- Independent test run by Artificial Analysis on dedicated hardware.
- Chart interpretation
- Each bar is one model measured the same way, so this model can be read against the others. The chart lists its source and retrieval date.
Latency: Time To First Answer Token
Seconds to first answer token received · Accounts for reasoning model 'thinking' time · Evaluation results measured independently by Artificial Analysis
- GPT-4.1 nano0 s
- Mistral Small 3.20 s
- Mistral Small 3.10 s
- Ministral 3 8B0 s
- Llama 4 Scout0 s
- Ministral 3 14B0 s
- Llama 4 Maverick0 s
- GPT-4.1 mini0 s
- Mistral Large 30 s
- Ling 2.6 Flash0 s
- Mistral Medium 3 (this model)0 s
- Mistral Medium 3.1 (this model)0 s
- Llama 3.3 70B0 s
- Qwen3 Coder Next0 s
- gpt-oss-120b (high)6.37 s
- Nemotron 3 Ultra9.09 s
- GLM-5.2 (max)9.19 s
- Grok 4.3 (high)0 s
- MiniMax-M320.19 s
- Gemini 3.5 Flash0 s
| Model | Latency: Time To First Answer Token |
|---|---|
| GPT-4.1 nano | 0 s |
| Mistral Small 3.2 | 0 s |
| Mistral Small 3.1 | 0 s |
| Ministral 3 8B | 0 s |
| Llama 4 Scout | 0 s |
| Ministral 3 14B | 0 s |
| Llama 4 Maverick | 0 s |
| GPT-4.1 mini | 0 s |
| Mistral Large 3 | 0 s |
| Ling 2.6 Flash | 0 s |
| Mistral Medium 3 (this model) | 0 s |
| Mistral Medium 3.1 (this model) | 0 s |
| Llama 3.3 70B | 0 s |
| Qwen3 Coder Next | 0 s |
| gpt-oss-120b (high) | 6.37 s |
| Nemotron 3 Ultra | 9.09 s |
| GLM-5.2 (max) | 9.19 s |
| Grok 4.3 (high) | 0 s |
| MiniMax-M3 | 20.19 s |
| Gemini 3.5 Flash | 0 s |
Published benchmark dataset · Retrieved
Method and source
- Methodology
- Independent test run by Artificial Analysis on dedicated hardware.
- Latency considerations
- Latency includes thinking / reasoning time when applicable. Lower is better for interactive use cases.
Context Window
Context window: tokens limit · Higher is better · Evaluation results measured independently by Artificial Analysis
- Llama 4 Scout10M
- Gemini 3.5 Flash1M
- Claude Fable 5 (with fallback)1M
- GLM-5.2 (max)1M
- DeepSeek V4 Pro (max)1M
- Grok 4.3 (high)1M
- MiniMax-M31M
- GPT-4.1 mini1M
- Llama 4 Maverick1M
- GPT-4.1 nano1M
- GPT-5.5 (xhigh)922k
- Nemotron 3 Ultra262.1k
- Muse Spark262.1k
- Ling 2.6 Flash262.1k
- Kimi K2.6256k
- MiMo-V2-Flash256k
- Qwen3 Coder Next256k
- Mistral Large 3256k
- Ministral 3 14B256k
- Ministral 3 8B256k
| Model | Context Window |
|---|---|
| Llama 4 Scout | 10M |
| Gemini 3.5 Flash | 1M |
| Claude Fable 5 (with fallback) | 1M |
| GLM-5.2 (max) | 1M |
| DeepSeek V4 Pro (max) | 1M |
| Grok 4.3 (high) | 1M |
| MiniMax-M3 | 1M |
| GPT-4.1 mini | 1M |
| Llama 4 Maverick | 1M |
| GPT-4.1 nano | 1M |
| GPT-5.5 (xhigh) | 922k |
| Nemotron 3 Ultra | 262.1k |
| Muse Spark | 262.1k |
| Ling 2.6 Flash | 262.1k |
| Kimi K2.6 | 256k |
| MiMo-V2-Flash | 256k |
| Qwen3 Coder Next | 256k |
| Mistral Large 3 | 256k |
| Ministral 3 14B | 256k |
| Ministral 3 8B | 256k |
Published benchmark dataset · Retrieved
Method and source
- Methodology
- Independent test run by Artificial Analysis on dedicated hardware.
- Context window sizing
- Larger context windows enable complex multi-turn tasks but may increase latency and cost for long inputs.
Cost per Intelligence Index Task
Weighted average cost (USD) per Artificial Analysis Intelligence Index task, segmented by token type. Lower is better · Evaluation results measured independently by Artificial Analysis
- Llama 4 Scout0.000824
- DeepSeek V3 (Dec)0.00202
- Llama 4 Maverick0.00178
- Mistral Small 3.10.00143
- DeepSeek V4 Pro (max)0.0063
- GPT-4.1 mini0.00473
- Mistral Large 30.00455
- gpt-oss-120b (high)0.00454
- Llama 3.3 70B0.0012
- Mistral Small 3.20.00242
- MiniMax-M30.0139
- Grok 4.3 (high)0.0101
- Mistral Medium 3.1 (this model)0.0101
- Ministral 3 14B0.00235
- Ministral 3 8B0.00235
- Nemotron 3 Ultra0.0209
- Qwen3 Coder Next0.0184
- Kimi K2.60.0216
- MiMo-V2-Flash0.00812
- GLM-5.2 (max)0.0268
| Model | Cost per Intelligence Index Task |
|---|---|
| Llama 4 Scout | 0.000824 |
| DeepSeek V3 (Dec) | 0.00202 |
| Llama 4 Maverick | 0.00178 |
| Mistral Small 3.1 | 0.00143 |
| DeepSeek V4 Pro (max) | 0.0063 |
| GPT-4.1 mini | 0.00473 |
| Mistral Large 3 | 0.00455 |
| gpt-oss-120b (high) | 0.00454 |
| Llama 3.3 70B | 0.0012 |
| Mistral Small 3.2 | 0.00242 |
| MiniMax-M3 | 0.0139 |
| Grok 4.3 (high) | 0.0101 |
| Mistral Medium 3.1 (this model) | 0.0101 |
| Ministral 3 14B | 0.00235 |
| Ministral 3 8B | 0.00235 |
| Nemotron 3 Ultra | 0.0209 |
| Qwen3 Coder Next | 0.0184 |
| Kimi K2.6 | 0.0216 |
| MiMo-V2-Flash | 0.00812 |
| GLM-5.2 (max) | 0.0268 |
Published benchmark dataset · Retrieved
Method and source
- Methodology
- Independent test run by Artificial Analysis on dedicated hardware.
- Benchmark interpretation
- Higher values indicate stronger overall capability. Bars show how models compare on composite intelligence metrics.
- Cost pressure
- Ethen Gateway should route away from this model when the task is simple, repetitive, or likely to generate many output tokens.
Cost per Task
Weighted average cost (USD) per Intelligence Index task · Lower is better · Evaluation results measured independently by Artificial Analysis
- DeepSeek V4 Pro (max)$0.045
- gpt-oss-120b (high)$0.061
- MiniMax-M3$0.125
- Grok 4.3 (high)$0.139
- Nemotron 3 Ultra$0.244
- Kimi K2.6$0.346
- GLM-5.2 (max)$0.370
- Gemini 3.5 Flash$0.586
- GPT-5.5 (xhigh)$0.863
- Claude Fable 5 (with fallback)$2.75
| Model | Cost per Task |
|---|---|
| DeepSeek V4 Pro (max) | $0.045 |
| gpt-oss-120b (high) | $0.061 |
| MiniMax-M3 | $0.125 |
| Grok 4.3 (high) | $0.139 |
| Nemotron 3 Ultra | $0.244 |
| Kimi K2.6 | $0.346 |
| GLM-5.2 (max) | $0.370 |
| Gemini 3.5 Flash | $0.586 |
| GPT-5.5 (xhigh) | $0.863 |
| Claude Fable 5 (with fallback) | $2.75 |
Published benchmark dataset · Retrieved
Method and source
- Methodology
- Independent test run by Artificial Analysis on dedicated hardware.
- Cost pressure
- Ethen Gateway should route away from this model when the task is simple, repetitive, or likely to generate many output tokens.
Cost to Run Artificial Analysis Intelligence Index
Cost (USD) to run all evaluations in the Artificial Analysis Intelligence Index · Evaluation results measured independently by Artificial Analysis
- Llama 4 Scout2.7
- DeepSeek V3 (Dec)2.9
- Mistral Small 3.11.5
- Llama 4 Maverick4
- GPT-4.1 mini8.3
- Mistral Large 38.4
- Llama 3.3 70B2.7
- gpt-oss-120b (high)3.5
- Ministral 3 8B2.8
- Ministral 3 14B3
- Mistral Small 3.22.5
- Mistral Medium 3.1 (this model)17.3
- DeepSeek V4 Pro (max)7.2
- MiniMax-M314.5
- Qwen3 Coder Next38.5
- Grok 4.3 (high)12.5
- MiMo-V2-Flash11.4
- Nemotron 3 Ultra33.5
- GLM-5.2 (max)32.9
- Kimi K2.625
| Model | Cost to Run Artificial Analysis Intelligence Index |
|---|---|
| Llama 4 Scout | 2.7 |
| DeepSeek V3 (Dec) | 2.9 |
| Mistral Small 3.1 | 1.5 |
| Llama 4 Maverick | 4 |
| GPT-4.1 mini | 8.3 |
| Mistral Large 3 | 8.4 |
| Llama 3.3 70B | 2.7 |
| gpt-oss-120b (high) | 3.5 |
| Ministral 3 8B | 2.8 |
| Ministral 3 14B | 3 |
| Mistral Small 3.2 | 2.5 |
| Mistral Medium 3.1 (this model) | 17.3 |
| DeepSeek V4 Pro (max) | 7.2 |
| MiniMax-M3 | 14.5 |
| Qwen3 Coder Next | 38.5 |
| Grok 4.3 (high) | 12.5 |
| MiMo-V2-Flash | 11.4 |
| Nemotron 3 Ultra | 33.5 |
| GLM-5.2 (max) | 32.9 |
| Kimi K2.6 | 25 |
Published benchmark dataset · Retrieved
Method and source
- Methodology
- Independent test run by Artificial Analysis on dedicated hardware.
- Benchmark interpretation
- Higher values indicate stronger overall capability. Bars show how models compare on composite intelligence metrics.
- Cost pressure
- Ethen Gateway should route away from this model when the task is simple, repetitive, or likely to generate many output tokens.
Pricing: Cache Hit, Input, and Output
Price (USD per M Tokens) · Evaluation results measured independently by Artificial Analysis
- Input
- Output
- Cache Hit
- Ministral 3 8B$0.300
- MiMo-V2-Flash$0.400
- Mistral Small 3.1$0.400
- Ling 2.6 Flash$0.420
- Ministral 3 14B$0.400
- Mistral Small 3.2$0.400
- GPT-4.1 nano$0.525
- gpt-oss-120b (high)$0.900
- Llama 4 Scout$0.830
- Llama 4 Maverick$1.47
- DeepSeek V3 (Dec)$1.29
- Llama 3.3 70B$1.87
- DeepSeek V4 Pro (max)$1.31
- MiniMax-M3$1.56
- Qwen3 Coder Next$1.90
- Mistral Large 3$2.00
- GPT-4.1 mini$2.10
- Mistral Medium 3 (this model)$2.40
- Mistral Medium 3.1 (this model)$2.40
- Nemotron 3 Ultra$3.60
| Model | Input | Output | Cache Hit | Total |
|---|---|---|---|---|
| Ministral 3 8B | $0.150 | $0.150 | Not published | $0.300 |
| MiMo-V2-Flash | $0.100 | $0.300 | Not published | $0.400 |
| Mistral Small 3.1 | $0.100 | $0.300 | Not published | $0.400 |
| Ling 2.6 Flash | $0.100 | $0.300 | $0.020 | $0.420 |
| Ministral 3 14B | $0.200 | $0.200 | Not published | $0.400 |
| Mistral Small 3.2 | $0.100 | $0.300 | Not published | $0.400 |
| GPT-4.1 nano | $0.100 | $0.400 | $0.025 | $0.525 |
| gpt-oss-120b (high) | $0.150 | $0.600 | $0.150 | $0.900 |
| Llama 4 Scout | $0.170 | $0.660 | Not published | $0.830 |
| Llama 4 Maverick | $0.350 | $0.850 | $0.270 | $1.47 |
| DeepSeek V3 (Dec) | $0.400 | $0.890 | Not published | $1.29 |
| Llama 3.3 70B | $0.580 | $0.710 | $0.580 | $1.87 |
| DeepSeek V4 Pro (max) | $0.435 | $0.870 | $0.0036 | $1.31 |
| MiniMax-M3 | $0.300 | $1.20 | $0.060 | $1.56 |
| Qwen3 Coder Next | $0.350 | $1.20 | $0.350 | $1.90 |
| Mistral Large 3 | $0.500 | $1.50 | Not published | $2.00 |
| GPT-4.1 mini | $0.400 | $1.60 | $0.100 | $2.10 |
| Mistral Medium 3 (this model) | $0.400 | $2.00 | Not published | $2.40 |
| Mistral Medium 3.1 (this model) | $0.400 | $2.00 | Not published | $2.40 |
| Nemotron 3 Ultra | $0.675 | $2.67 | $0.250 | $3.60 |
Published benchmark dataset · Retrieved
Method and source
- Methodology
- Independent test run by Artificial Analysis on dedicated hardware.
- Chart interpretation
- Each bar is one model measured the same way, so this model can be read against the others. The chart lists its source and retrieval date.
Time per Intelligence Index Task
Weighted average decode time (minutes) per task; excludes TTFT and overhead time · Lower is better · Evaluation results measured independently by Artificial Analysis
- Llama 4 Scout0.198
- Llama 4 Maverick0.3
- Llama 3.3 70B0.321
- Mistral Small 3.10.447
- GPT-4.1 nano0.559
- GPT-4.1 mini0.575
- Mistral Small 3.20.87
- Mistral Large 30.924
- Mistral Medium 3.1 (this model)0.935
- Ling 2.6 Flash1.1
- Nemotron 3 Ultra1.4
- Grok 4.3 (high)1.6
- gpt-oss-120b (high)1.9
- Gemini 3.5 Flash2.2
- Ministral 3 14B2.2
- Ministral 3 8B2.5
- Qwen3 Coder Next2.6
- GLM-5.2 (max)2.8
- GPT-5.5 (xhigh)3
- MiniMax-M33.9
| Model | Time per Intelligence Index Task |
|---|---|
| Llama 4 Scout | 0.198 |
| Llama 4 Maverick | 0.3 |
| Llama 3.3 70B | 0.321 |
| Mistral Small 3.1 | 0.447 |
| GPT-4.1 nano | 0.559 |
| GPT-4.1 mini | 0.575 |
| Mistral Small 3.2 | 0.87 |
| Mistral Large 3 | 0.924 |
| Mistral Medium 3.1 (this model) | 0.935 |
| Ling 2.6 Flash | 1.1 |
| Nemotron 3 Ultra | 1.4 |
| Grok 4.3 (high) | 1.6 |
| gpt-oss-120b (high) | 1.9 |
| Gemini 3.5 Flash | 2.2 |
| Ministral 3 14B | 2.2 |
| Ministral 3 8B | 2.5 |
| Qwen3 Coder Next | 2.6 |
| GLM-5.2 (max) | 2.8 |
| GPT-5.5 (xhigh) | 3 |
| MiniMax-M3 | 3.9 |
Published benchmark dataset · Retrieved
Method and source
- Methodology
- Independent test run by Artificial Analysis on dedicated hardware.
- Benchmark interpretation
- Higher values indicate stronger overall capability. Bars show how models compare on composite intelligence metrics.
Specifications
Architecture and limits
| Specification | Value | Source |
|---|---|---|
| Model type | Proprietary | faq |
| Reasoning | No | faq |
| Input modalities | Mistral Medium 3 supports text and image input. | faq |
| Output modalities | Mistral Medium 3 supports text output. | faq |
| Context window | 130k tokens | faq |
| Open weights / source | No, Mistral Medium 3 is proprietary. The model weights are not publicly available. | faq |
| Parameters | Mistral Medium 3 is a proprietary model and Mistral has not disclosed the model size or parameter count. | faq |
| API availability | Yes, Mistral Medium 3 is available via API through 2 providers. | faq |
Method
Methodology & Provenance
This page is rendered from the normalized profile and page JSON for Mistral Medium 3.
Benchmark values are preserved as normalized; only layout, disclosure ordering, and typography are adjusted for readability.
Questions
Model FAQ and technical disclosures
Models
Related
- 01MistralOther Mistral models in the catalog.
- 02LeaderboardsCertified metric ranks, when published.