Mistral AIopen-weight
Released: 2026-03-16Artificial Analysis

Mistral Small 4

Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a single system. It combines strong reasoning from...

Intelligence Index
4.3/ 100
Artificial Analysis Intelligence Index (independent composite)
Throughput Speed
142tok/sec
Output streaming throughput
Time to First Answer
13s
Time to first answer token, including any thinking
Cost to Run the Index
0.04USD
Artificial Analysis cost of the full Index run

Measured results · Artificial Analysis

Independent evaluations of Mistral Small 4 (Reasoning configuration). Values are reported as published; nothing here is estimated or derived. Snapshot 2026-11-15.

Intelligence Index
4.3
Cost to run the Index
$0.04
Time per task
1.7 min
Omniscience index
-31.0
Reasoning model
Yes
Cached-input price
$0.015 / 1M

Agentic work

Multimodal & science

Reasoning-effort variants evaluated

VariantIntelligence IndexCost to run IndexOutput speed (tok/s)
Reasoning4.3$0.04141.9
Non-reasoning——120.5
Full analysis on Artificial Analysis

Sourced Benchmark Evaluations (22)

Verified performance across authoritative benchmarks with provenance tracking.
BenchmarkStatusScoreTrustDateSource TypeProvenance
AA-LCR (Long Context Reasoning)Active49.7%
93
2026-11-15independentSource ↗
AA-AnalystAgentActive1.3%
93
2026-11-15independentSource ↗
AutomationBench-AAActive1%
93
2026-11-15independentSource ↗
MLCR-AA (Medical Long Context Reasoning)Active1.7%
93
2026-11-15independentSource ↗
GDP.pdfActive0%
93
2026-11-15independentSource ↗
FrontierCode-AA 2.0Active0%
93
2026-11-15independentSource ↗
AA-Omniscience (Non-Hallucination)Active33.4%
93
2026-11-15independentSource ↗
AA-Omniscience (Accuracy)Active21.4%
93
2026-11-15independentSource ↗
HLE-DiamondActive4.4%
93
2026-11-15independentSource ↗
CritPt v2 (Hard)Active0%
93
2026-11-15independentSource ↗
CritPtActive0.3%
93
2026-11-15independentSource ↗
GPQANearing Saturation76.9%
78
2026-11-15independentSource ↗
Terminal-Bench-Science 0.1Active0%
93
2026-11-15independentSource ↗
Terminal-Bench 4.0Active0%
93
2026-11-15independentSource ↗
Terminal-Bench 2.1Active21%
93
2026-11-15independentSource ↗
Terminal-Bench HardActive17.4%
93
2026-11-15independentSource ↗
τ³-BankingActive4.9%
93
2026-11-15independentSource ↗
τ²-Bench TelecomActive41.2%
93
2026-11-15independentSource ↗
SciCodeActive38.8%
93
2026-11-15independentSource ↗
IFBenchActive48.2%
93
2026-11-15independentSource ↗
MMMU-ProActive56.8%
93
2026-11-15independentSource ↗
Humanity's Last ExamActive9.9%
93
2026-11-15independentSource ↗
Local Hardware Execution (Ollama)Hardware Compatible
# 1. Pull and execute model locally with Ollama
ollama run mistral-mistral-small-4

# 2. Or invoke via local OpenAI-compatible endpoint
curl http://localhost:11434/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "mistral-mistral-small-4",
    "messages": [{"role": "user", "content": "Analyze reasoning chains on AIME 2026"}]
  }'

Evaluation & Sourcing Notes

Scores listed for Mistral Small 4 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.