Skip to content

EthenEthenEthen

LoginPlatformTry Ethen

Mistral · Flagships Analysis

Mistral Medium 3.5

Intelligence, Performance & Price Analysis

Back to catalogMore from Mistral

Canonical slug: mistral-medium-3-5 · Canonical model registry at build time

Intelligence

30 score

Speed

140.3 output tokens/sec

Latency

2.02s TTFT

Input Price

$1.50 / 1M tokens

Output Price

$7.50 / 1M tokens

Verbosity

91M Output tokens from Intelligence Index 3 out of 4 units for Verbosity . Compa

Executive Assessment

Routing Verdict & Tradeoffs

Ethen Routing Verdict

Frontier research / complex reasoning

Mistral Medium 3.5 scores 30 on the Artificial Analysis Intelligence Index, placing it well above average among other open weight models of similar size (median: 9). Mistral Medium 3.5 generates output at 140.3 tokens per second (based on Mistral's API), which is above average compared to other open weight models of similar size (median: 88.2 t/s). Mistral Medium 3.5 costs $1.50 per 1M input tokens (at the higher end, median: $0.40) and $7.50 per 1M output tokens (at the higher end, median: $0.84), based on Mistral's API.

Reserve this model for the hardest requests; simpler or repetitive work should stay on cheaper routes.

Task Fit Assessment

WorkloadRatingNotes
Complex reasoning & agentic workflowsoptimalIntelligence score 30 places this model among top performers. Suitable for multi-step analysis and agentic loops.
High-volume chat & customer-facingoptimalOutput speed 140.3 tokens/sec and capable intelligence make this suitable for real-time chat at scale.
Latency-sensitive applicationsoptimalTTFT 2.02s — adequate latency for most interactive use cases.
Cost-sensitive pipelinesviableOutput pricing at $7.50 is premium. Route high-volume simple tasks to cheaper alternatives.

Cost Pressure Analysis

High

Pricing is premium — input $1.50, output $7.50. This model is expensive for high-volume or output-heavy workloads.

Cheaper substitutes: Lower-cost models for repetitive or high-volume work, Cache-backed reuse for repeated prompts

Technical Specifications

Architecture and Limits

SpecificationValueValidation Authority
Model typeOpen weightsinferred
ReasoningYesfaq
Input modalitiesMistral Medium 3.5 supports text and image input.faq
Output modalitiesMistral Medium 3.5 supports text output.faq
Context window260k tokensfaq
Open weights / sourceYes, Mistral Medium 3.5 is open weights. The model weights are publicly available and can be downloaded for self-hosting.faq
ParametersMistral Medium 3.5 has 128 billion parameters.faq
LicenseMistral Medium 3.5 is released under the Other license. This license allows commercial use.faq
API availabilityYes, Mistral Medium 3.5 is available via API through 1 provider.faq

Evidence charts

Profile visualizations

Charts are the same canonical evidence cards previously published for this slug, contained inside the D18D page grammar.

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

Retrieved 2026-07-08

Chart source and provenance are listed in Methodology & sources below.

Retrieval date:
2026-07-08
Methodology:
Independent test run by Artificial Analysis on dedicated hardware.

-40-200204060Claude Fable 5 (with fallback): 4040AClaude Fable 5 (with fal…Gemini 3.5 Flash: 2323GGemini 3.5 FlashGPT-5.5 (xhigh): 2020AIGPT-5.5 (xhigh)Grok 4.3 (high): 1818xGrok 4.3 (high)Kimi K2.6: 6.46.4KKimi K2.6Muse Spark: 4.14.1?Muse SparkGLM-5.2 (max): 44?GLM-5.2 (max)MiniMax-M3: 1.41.4?MiniMax-M3Nemotron 3 Ultra: -0.8-0.8NNemotron 3 UltraDeepSeek V4 Pro (max): -10-10DDeepSeek V4 Pro (max)Mistral Medium 3.5: -36.3-36.3MiMistral Medium 3.5

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

Retrieved 2026-07-08

Chart source and provenance are listed in Methodology & sources below.

Retrieval date:
2026-07-08
Methodology:
Independent test run by Artificial Analysis on dedicated hardware.

0204060Claude Fable 5 (with fallback): 6060AClaude Fable 5 (with fal…GPT-5.5 (xhigh): 5555AIGPT-5.5 (xhigh)GLM-5.2 (max): 5151?GLM-5.2 (max)Gemini 3.5 Flash: 5050GGemini 3.5 FlashMiniMax-M3: 4444?MiniMax-M3DeepSeek V4 Pro (max): 4444DDeepSeek V4 Pro (max)Kimi K2.6: 4444KKimi K2.6Muse Spark: 4343?Muse SparkNemotron 3 Ultra: 3838NNemotron 3 UltraGrok 4.3 (high): 3838xGrok 4.3 (high)Mistral Medium 3.5: 3030MiMistral Medium 3.5

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

Retrieved 2026-07-08

Chart source and provenance are listed in Methodology & sources below.

Retrieval date:
2026-07-08
Methodology:
Independent test run by Artificial Analysis on dedicated hardware.

0204060Claude Fable 5 (with fallback): 6060AClaude Fable 5 (with fal…GPT-5.5 (xhigh): 5555AIGPT-5.5 (xhigh)GLM-5.2 (max): 5151?GLM-5.2 (max)Gemini 3.5 Flash: 5050GGemini 3.5 FlashMiniMax-M3: 4444?MiniMax-M3DeepSeek V4 Pro (max): 4444DDeepSeek V4 Pro (max)Kimi K2.6: 4444KKimi K2.6Muse Spark: 4343?Muse SparkNemotron 3 Ultra: 3838NNemotron 3 UltraGrok 4.3 (high): 3838xGrok 4.3 (high)Mistral Medium 3.5: 3030MiMistral Medium 3.5

Artificial Analysis Openness Index: Score

Openness Index assesses model openness on a 0 to 100 normalized scale (higher is more open) · Evaluation results measured independently by Artificial Analysis

Retrieved 2026-07-08

Chart source and provenance are listed in Methodology & sources below.

Retrieval date:
2026-07-08
Methodology:
Independent test run by Artificial Analysis on dedicated hardware.

050100K2 Think V2: 8989?K2 Think V2Nemotron 3 Ultra: 8383NNemotron 3 UltraNVIDIA Nemotron 3 Super: 8383NNVIDIA Nemotron 3 SuperDeepSeek V4 Pro (max): 5050DDeepSeek V4 Pro (max)GLM-5.2 (max): 4444?GLM-5.2 (max)Qwen3 Next 80B A3B: 4444QQwen3 Next 80B A3BQwen3 Coder Next: 4242QQwen3 Coder Nextgpt-oss-120b (high): 3939AIgpt-oss-120b (high)Qwen3.5 122B A10B: 3939QQwen3.5 122B A10BMistral Small 4: 3939MiMistral Small 4Mistral Medium 3.5: 3333MiMistral Medium 3.5

Intelligence

Artificial Analysis Intelligence Index · Higher is better · Evaluation results measured independently by Artificial Analysis

Retrieved 2026-07-08

Chart source and provenance are listed in Methodology & sources below.

Retrieval date:
2026-07-08
Methodology:
Independent test run by Artificial Analysis on dedicated hardware.

0204060Claude Fable 5 (with fallback): 6060AClaude Fable 5 (with fal…GPT-5.5 (xhigh): 5555AIGPT-5.5 (xhigh)GLM-5.2 (max): 5151?GLM-5.2 (max)Gemini 3.5 Flash: 5050GGemini 3.5 FlashMiniMax-M3: 4444?MiniMax-M3DeepSeek V4 Pro (max): 4444DDeepSeek V4 Pro (max)Kimi K2.6: 4444KKimi K2.6Muse Spark: 4343?Muse SparkNemotron 3 Ultra: 3838NNemotron 3 UltraGrok 4.3 (high): 3838xGrok 4.3 (high)Mistral Medium 3.5: 3030MiMistral Medium 3.5

Output Speed

Output tokens per second · Higher is better · Evaluation results measured independently by Artificial Analysis

Retrieved 2026-07-08

Chart source and provenance are listed in Methodology & sources below.

Retrieval date:
2026-07-08
Methodology:
Independent test run by Artificial Analysis on dedicated hardware.

0100200300400NVIDIA Nemotron 3 Super: 364364NNVIDIA Nemotron 3 SuperHyperNova 60B 2605: 353353?HyperNova 60B 2605gpt-oss-120b (high): 314314AIgpt-oss-120b (high)Nemotron 3 Ultra: 250250NNemotron 3 UltraGLM-5.2 (max): 218218?GLM-5.2 (max)Gemini 3.5 Flash: 192192GGemini 3.5 FlashMistral Small 4: 177177MiMistral Small 4Ling 2.6 Flash: 177177?Ling 2.6 FlashGrok 4.3 (high): 164164xGrok 4.3 (high)Mistral Medium 3.5: 140140MiMistral Medium 3.5

Speed

Output tokens per second · Higher is better · Evaluation results measured independently by Artificial Analysis

Retrieved 2026-07-08

Chart source and provenance are listed in Methodology & sources below.

Retrieval date:
2026-07-08
Methodology:
Independent test run by Artificial Analysis on dedicated hardware.

088175263350gpt-oss-120b (high): 314314AIgpt-oss-120b (high)Nemotron 3 Ultra: 250250NNemotron 3 UltraGLM-5.2 (max): 218218?GLM-5.2 (max)Gemini 3.5 Flash: 192192GGemini 3.5 FlashGrok 4.3 (high): 164164xGrok 4.3 (high)Mistral Medium 3.5: 140140MiMistral Medium 3.5MiniMax-M3: 9999?MiniMax-M3GPT-5.5 (xhigh): 8888AIGPT-5.5 (xhigh)Kimi K2.6: 7676KKimi K2.6DeepSeek V4 Pro (max): 7272DDeepSeek V4 Pro (max)

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

Retrieved 2026-07-08

Chart source and provenance are listed in Methodology & sources below.

Retrieval date:
2026-07-08
Methodology:
Independent test run by Artificial Analysis on dedicated hardware.

0s2.5s5s7.5s10sDeepSeek V4 Pro (max): 7s7sDDeepSeek V4 Pro (max)Kimi K2.6: 6.6s6.6sKKimi K2.6Devstral 2: 6.6s6.6s?Devstral 2Llama 3.3 70B: 5.8s5.8sMLlama 3.3 70BGPT-5.5 (xhigh): 5.7s5.7sAIGPT-5.5 (xhigh)Qwen3 Coder Next: 5.6s5.6sQQwen3 Coder NextMiniMax-M3: 5s5s?MiniMax-M3Llama 4 Scout: 4.6s4.6sMLlama 4 ScoutQwen3 Next 80B A3B: 4.4s4.4sQQwen3 Next 80B A3BQwen3.5 122B A10B: 3.6s3.6sQQwen3.5 122B A10BMistral Medium 3.5: 3.6s3.6sMiMistral Medium 3.5

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

Retrieved 2026-07-08

Chart source and provenance are listed in Methodology & sources below.

Retrieval date:
2026-07-08
Methodology:
Independent test run by Artificial Analysis on dedicated hardware.

0s25s50s75s100sDeepSeek V4 Pro (max): 61s61sDDeepSeek V4 Pro (max)Kimi K2.6: 58s58sKKimi K2.6MiniMax-M3: 20s20s?MiniMax-M3Qwen3 Next 80B A3B: 17s17sQQwen3 Next 80B A3BQwen3.5 122B A10B: 14s14sQQwen3.5 122B A10BMistral Medium 3.5: 14s14sMiMistral Medium 3.5Mistral Small 4: 11s11sMiMistral Small 4GLM-5.2 (max): 9.2s9.2s?GLM-5.2 (max)Nemotron 3 Ultra: 9.1s9.1sNNemotron 3 Ultragpt-oss-120b (high): 6.4s6.4sAIgpt-oss-120b (high)

Context Window

Context window: tokens limit · Higher is better · Evaluation results measured independently by Artificial Analysis

Retrieved 2026-07-08

Chart source and provenance are listed in Methodology & sources below.

Retrieval date:
2026-07-08
Methodology:
Independent test run by Artificial Analysis on dedicated hardware.

02.5M5M7.5M10MLlama 4 Scout: 10M10MMLlama 4 ScoutGemini 3.5 Flash: 1M1MGGemini 3.5 FlashClaude Fable 5 (with fallback): 1M1MAClaude Fable 5 (with fal…GLM-5.2 (max): 1M1M?GLM-5.2 (max)DeepSeek V4 Pro (max): 1M1MDDeepSeek V4 Pro (max)Grok 4.3 (high): 1M1MxGrok 4.3 (high)MiniMax-M3: 1M1M?MiniMax-M3NVIDIA Nemotron 3 Super: 1M1MNNVIDIA Nemotron 3 SuperGPT-5.5 (xhigh): 922k922kAIGPT-5.5 (xhigh)Nemotron 3 Ultra: 262k262kNNemotron 3 UltraMistral Medium 3.5: 256k256kMiMistral Medium 3.5

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

Retrieved 2026-07-08

Chart source and provenance are listed in Methodology & sources below.

Retrieval date:
2026-07-08
Methodology:
Independent test run by Artificial Analysis on dedicated hardware.

00.51Claude Fable 5 (with fallback): 0.40.4AClaude Fable 5 (with fal…GPT-5.5 (xhigh): 0.10.1AIGPT-5.5 (xhigh)Gemini 3.5 Flash: 0.10.1GGemini 3.5 FlashMistral Medium 3.5: 0.10.1MiMistral Medium 3.5GLM-5.2 (max): 00?GLM-5.2 (max)Kimi K2.6: 00KKimi K2.6Nemotron 3 Ultra: 00NNemotron 3 UltraQwen3.5 122B A10B: 00QQwen3.5 122B A10BQwen3 Coder Next: 00QQwen3 Coder NextMiniMax-M3: 00?MiniMax-M3

Cost per Task

Weighted average cost (USD) per Intelligence Index task · Lower is better · Evaluation results measured independently by Artificial Analysis

Retrieved 2026-07-08

Chart source and provenance are listed in Methodology & sources below.

Retrieval date:
2026-07-08
Methodology:
Independent test run by Artificial Analysis on dedicated hardware.

$0.00$1.00$2.00$3.00$4.00$5.00Claude Fable 5 (with fallback): $2.75$2.75AClaude Fable 5 (with fal…Mistral Medium 3.5: $1.20$1.20MiMistral Medium 3.5GPT-5.5 (xhigh): $0.86$0.86AIGPT-5.5 (xhigh)Gemini 3.5 Flash: $0.59$0.59GGemini 3.5 FlashGLM-5.2 (max): $0.37$0.37?GLM-5.2 (max)Kimi K2.6: $0.35$0.35KKimi K2.6Nemotron 3 Ultra: $0.24$0.24NNemotron 3 UltraGrok 4.3 (high): $0.14$0.14xGrok 4.3 (high)MiniMax-M3: $0.12$0.12?MiniMax-M3gpt-oss-120b (high): $0.06$0.06AIgpt-oss-120b (high)

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

Retrieved 2026-07-08

Chart source and provenance are listed in Methodology & sources below.

Retrieval date:
2026-07-08
Methodology:
Independent test run by Artificial Analysis on dedicated hardware.

0200400600Claude Fable 5 (with fallback): 508508AClaude Fable 5 (with fal…GPT-5.5 (xhigh): 132132AIGPT-5.5 (xhigh)Gemini 3.5 Flash: 114114GGemini 3.5 FlashMistral Medium 3.5: 5454MiMistral Medium 3.5Qwen3 Coder Next: 3939QQwen3 Coder NextNemotron 3 Ultra: 3434NNemotron 3 UltraGLM-5.2 (max): 3333?GLM-5.2 (max)Qwen3.5 122B A10B: 3333QQwen3.5 122B A10BKimi K2.6: 2525KKimi K2.6Qwen3 Next 80B A3B: 1616QQwen3 Next 80B A3B

Pricing: Cache Hit, Input, and Output

Price (USD per M Tokens) · Evaluation results measured independently by Artificial Analysis

Retrieved 2026-07-08

Chart source and provenance are listed in Methodology & sources below.

Retrieval date:
2026-07-08
Methodology:
Independent test run by Artificial Analysis on dedicated hardware.

0250k500k750k1MClaude Fable 5 (with fallback): 6161AClaude Fable 5 (with fal…GPT-5.5 (xhigh): 3636AIGPT-5.5 (xhigh)Gemini 3.5 Flash: 1111GGemini 3.5 FlashMistral Medium 3.5: 9.29.2MiMistral Medium 3.5Qwen3 Next 80B A3B: 6.56.5QQwen3 Next 80B A3BGLM-5.2 (max): 6.16.1?GLM-5.2 (max)Kimi K2.6: 5.15.1KKimi K2.6Grok 4.3 (high): 44xGrok 4.3 (high)Qwen3.5 122B A10B: 3.63.6QQwen3.5 122B A10BNemotron 3 Ultra: 3.63.6NNemotron 3 Ultracache Hitinputoutput

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

Retrieved 2026-07-08

Chart source and provenance are listed in Methodology & sources below.

Retrieval date:
2026-07-08
Methodology:
Independent test run by Artificial Analysis on dedicated hardware.

02468DeepSeek V4 Pro (max): 6.86.8DDeepSeek V4 Pro (max)Claude Fable 5 (with fallback): 4.84.8AClaude Fable 5 (with fal…MiniMax-M3: 3.93.9?MiniMax-M3GPT-5.5 (xhigh): 33AIGPT-5.5 (xhigh)Mistral Medium 3.5: 2.92.9MiMistral Medium 3.5GLM-5.2 (max): 2.82.8?GLM-5.2 (max)Qwen3 Next 80B A3B: 2.82.8QQwen3 Next 80B A3BQwen3 Coder Next: 2.62.6QQwen3 Coder NextGemini 3.5 Flash: 2.22.2GGemini 3.5 Flashgpt-oss-120b (high): 1.91.9AIgpt-oss-120b (high)

Model Size: Total and Active Parameters

Comparison between total model parameters and parameters active during inference · Evaluation results measured independently by Artificial Analysis

Retrieved 2026-07-08

Chart source and provenance are listed in Methodology & sources below.

Retrieval date:
2026-07-08
Methodology:
Independent test run by Artificial Analysis on dedicated hardware.

0250k500k750k1MDeepSeek V4 Pro (max): 1.6k1.6kDDeepSeek V4 Pro (max)Kimi K2.6: 1k1kKKimi K2.6GLM-5.2 (max): 753753?GLM-5.2 (max)Nemotron 3 Ultra: 550550NNemotron 3 UltraMiniMax-M3: 428428?MiniMax-M3Mistral Medium 3.5: 128128MiMistral Medium 3.5Qwen3.5 122B A10B: 125125QQwen3.5 122B A10BDevstral 2: 125125?Devstral 2NVIDIA Nemotron 3 Super: 121121NNVIDIA Nemotron 3 SuperMistral Small 4: 119119MiMistral Small 4passive Paramsactive Params

Output Tokens per Intelligence Index Task

Weighted average number of output tokens used to run one task in the Artificial Analysis Intelligence Index · Evaluation results measured independently by Artificial Analysis

Retrieved 2026-07-08

Chart source and provenance are listed in Methodology & sources below.

Retrieval date:
2026-07-08
Methodology:
Independent test run by Artificial Analysis on dedicated hardware.

05000100001500020000Qwen3 Coder Next: 1535515355QQwen3 Coder NextLing 2.6 Flash: 1307013070?Ling 2.6 FlashMiniMax-M3: 1162311623?MiniMax-M3Gemini 3.5 Flash: 98199819GGemini 3.5 FlashNemotron 3 Ultra: 77977797NNemotron 3 UltraClaude Fable 5 (with fallback): 76967696AClaude Fable 5 (with fal…gpt-oss-120b (high): 75717571AIgpt-oss-120b (high)NVIDIA Nemotron 3 Super: 74427442NNVIDIA Nemotron 3 SuperDeepSeek V4 Pro (max): 72437243DDeepSeek V4 Pro (max)Mistral Medium 3.5: 70497049MiMistral Medium 3.5

Methodology

Methodology & Provenance

This page is rendered from the normalized profile and page JSON for Mistral Medium 3.5.

Benchmark values are preserved as normalized; only layout, disclosure ordering, and typography are adjusted for readability.

Frequently Asked Questions

Model FAQs & Technical Disclosures

Mistral Medium 3.5 was released on April 29, 2026.

Related

Related

Provider

Mistral

Other Mistral models in the catalog.

Open

Directory

Leaderboards

Certified metric ranks, when published.

Open