Mistral AIopen-weight
Released: 2026-04-29Artificial Analysis

Mistral Medium 3.5

Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex...

Intelligence Index
4.6/ 100
Artificial Analysis Intelligence Index (independent composite)
Throughput Speed
147tok/sec
Output streaming throughput
Time to First Answer
24s
Time to first answer token, including any thinking
Cost to Run the Index
1.04USD
Artificial Analysis cost of the full Index run

Measured results · Artificial Analysis

Independent evaluations of Mistral Medium 3.5. Values are reported as published; nothing here is estimated or derived. Snapshot 2026-11-15.

Intelligence Index
4.7
Cost to run the Index
$1.04
Time per task
4.5 min
Omniscience index
-38.7
Reasoning model
Yes
Cached-input price
$0.15 / 1M

Agentic work

Multimodal & science

Full analysis on Artificial Analysis

Headline Evaluation Breakdown

Six independently measured evaluations (Artificial Analysis)
Reasoning · CritPt v2 (Hard)0.5%
0
Long context · AA-LCR69.3%
Knowledge · Humanity's Last Exam13.8%
Instruction following · IFBench68.8%

Sourced Benchmark Evaluations (23)

Verified performance across authoritative benchmarks with provenance tracking.
BenchmarkStatusScoreTrustDateSource TypeProvenance
AA-LCR (Long Context Reasoning)Active69.3%
93
2026-11-15independentSource ↗
EnterpriseOps-Gym-AAActive33.7%
93
2026-11-15independentSource ↗
AA-AnalystAgentActive12.5%
93
2026-11-15independentSource ↗
AutomationBench-AAActive6.3%
93
2026-11-15independentSource ↗
MLCR-AA (Medical Long Context Reasoning)Active10%
93
2026-11-15independentSource ↗
GDP.pdfActive2.8%
93
2026-11-15independentSource ↗
FrontierCode-AA 2.0Active1.8%
93
2026-11-15independentSource ↗
AA-Omniscience (Non-Hallucination)Active19.8%
93
2026-11-15independentSource ↗
AA-Omniscience (Accuracy)Active23%
93
2026-11-15independentSource ↗
HLE-DiamondActive4.7%
93
2026-11-15independentSource ↗
CritPt v2 (Hard)Active0.5%
93
2026-11-15independentSource ↗
CritPtActive0%
93
2026-11-15independentSource ↗
GPQANearing Saturation74.8%
78
2026-11-15independentSource ↗
Terminal-Bench-Science 0.1Active0%
93
2026-11-15independentSource ↗
Terminal-Bench 4.0Active0%
93
2026-11-15independentSource ↗
Terminal-Bench 2.1Active50.6%
93
2026-11-15independentSource ↗
Terminal-Bench HardActive33.3%
93
2026-11-15independentSource ↗
τ³-BankingActive15.1%
93
2026-11-15independentSource ↗
τ²-Bench TelecomActive94.2%
93
2026-11-15independentSource ↗
SciCodeActive40.2%
93
2026-11-15independentSource ↗
IFBenchActive68.8%
93
2026-11-15independentSource ↗
MMMU-ProActive64.9%
93
2026-11-15independentSource ↗
Humanity's Last ExamActive13.8%
93
2026-11-15independentSource ↗
Local Hardware Execution (Ollama)Hardware Compatible
# 1. Pull and execute model locally with Ollama
ollama run mistral-mistral-medium-3-5

# 2. Or invoke via local OpenAI-compatible endpoint
curl http://localhost:11434/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "mistral-mistral-medium-3-5",
    "messages": [{"role": "user", "content": "Analyze reasoning chains on AIME 2026"}]
  }'

Evaluation & Sourcing Notes

Scores listed for Mistral Medium 3.5 represent verified evaluations extracted from official research papers, independent evaluation suites (HELM, LMSYS, OpenCompass, LiveBench), and verified audit reports.

All benchmarks marked as saturated or deprecated reflect historical performance where the benchmark no longer provides active discriminative power.