Mistral AIopen-weight
Released: 2026-03-16Artificial AnalysisMistral 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 throughputTime to First Answer
13s
Time to first answer token, including any thinkingCost to Run the Index
0.04USD
Artificial Analysis cost of the full Index runMeasured 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
Reasoning & knowledge
- AA-Omniscience Accuracy21.4%
- CritPt0.3%
- CritPt v2 (Hard)0.0%
- GPQA Diamond76.9%
- HLE-Diamond4.4%
- Humanity's Last Exam9.9%
- IFBench48.2%
Coding & terminal agents
- FrontierCode-AA 2.00.0%
- SciCode38.8%
- Terminal-Bench 2.121.0%
- Terminal-Bench 4.00.0%
- Terminal-Bench Hard17.4%
- Terminal-Bench-Science 0.10.0%
Agentic work
- AA-AnalystAgent1.3%
- AA-Briefcase v1.1 (Elo)242 Elo
- AutomationBench-AA1.0%
- GDPval-AA (normalized Elo)369 Elo
- τ²-Bench Telecom41.2%
- τ³-Banking5.0%
Long context & documents
Multimodal & science
- MMMU-Pro56.8%
Health & safety
Reasoning-effort variants evaluated
| Variant | Intelligence Index | Cost to run Index | Output speed (tok/s) |
|---|---|---|---|
| Reasoning | 4.3 | $0.04 | 141.9 |
| Non-reasoning | — | — | 120.5 |
Sourced Benchmark Evaluations (22)
Verified performance across authoritative benchmarks with provenance tracking.| Benchmark | Status | Score | Trust | Date | Source Type | Provenance |
|---|---|---|---|---|---|---|
| AA-LCR (Long Context Reasoning) | Active | 49.7% | 93 | 2026-11-15 | independent | Source ↗ |
| AA-AnalystAgent | Active | 1.3% | 93 | 2026-11-15 | independent | Source ↗ |
| AutomationBench-AA | Active | 1% | 93 | 2026-11-15 | independent | Source ↗ |
| MLCR-AA (Medical Long Context Reasoning) | Active | 1.7% | 93 | 2026-11-15 | independent | Source ↗ |
| GDP.pdf | Active | 0% | 93 | 2026-11-15 | independent | Source ↗ |
| FrontierCode-AA 2.0 | Active | 0% | 93 | 2026-11-15 | independent | Source ↗ |
| AA-Omniscience (Non-Hallucination) | Active | 33.4% | 93 | 2026-11-15 | independent | Source ↗ |
| AA-Omniscience (Accuracy) | Active | 21.4% | 93 | 2026-11-15 | independent | Source ↗ |
| HLE-Diamond | Active | 4.4% | 93 | 2026-11-15 | independent | Source ↗ |
| CritPt v2 (Hard) | Active | 0% | 93 | 2026-11-15 | independent | Source ↗ |
| CritPt | Active | 0.3% | 93 | 2026-11-15 | independent | Source ↗ |
| GPQA | Nearing Saturation | 76.9% | 78 | 2026-11-15 | independent | Source ↗ |
| Terminal-Bench-Science 0.1 | Active | 0% | 93 | 2026-11-15 | independent | Source ↗ |
| Terminal-Bench 4.0 | Active | 0% | 93 | 2026-11-15 | independent | Source ↗ |
| Terminal-Bench 2.1 | Active | 21% | 93 | 2026-11-15 | independent | Source ↗ |
| Terminal-Bench Hard | Active | 17.4% | 93 | 2026-11-15 | independent | Source ↗ |
| τ³-Banking | Active | 4.9% | 93 | 2026-11-15 | independent | Source ↗ |
| τ²-Bench Telecom | Active | 41.2% | 93 | 2026-11-15 | independent | Source ↗ |
| SciCode | Active | 38.8% | 93 | 2026-11-15 | independent | Source ↗ |
| IFBench | Active | 48.2% | 93 | 2026-11-15 | independent | Source ↗ |
| MMMU-Pro | Active | 56.8% | 93 | 2026-11-15 | independent | Source ↗ |
| Humanity's Last Exam | Active | 9.9% | 93 | 2026-11-15 | independent | Source ↗ |
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.