Mistral AIopen-weight
Released: 2025-12-02Artificial AnalysisMinistral 3 8B
Ministral 3 8B from Mistral, tracked on the Artificial Analysis Intelligence Index.
Intelligence Index
—/ 100
Artificial Analysis Intelligence Index (independent composite)Throughput Speed
83tok/sec
Output streaming throughputTime to First Answer
1.8s
Time to first answer token, including any thinkingCost to Run the Index
—USD
Artificial Analysis cost of the full Index runMeasured results · Artificial Analysis
Independent evaluations of Ministral 3 8B. Values are reported as published; nothing here is estimated or derived. Snapshot 2026-11-15.
- Intelligence Index
- —
- Cost to run the Index
- —
- Time per task
- —
- Omniscience index
- —
- Reasoning model
- No
- Cached-input price
- $0.015 / 1M
Reasoning & knowledge
- AIME 202531.7%
- CritPt0.0%
- GPQA Diamond47.1%
- HLE-Diamond4.4%
- Humanity's Last Exam4.3%
- IFBench29.1%
Coding & terminal agents
- LiveCodeBench30.3%
- SciCode20.7%
- Terminal-Bench 2.14.1%
- Terminal-Bench 4.00.0%
- Terminal-Bench Hard4.5%
Agentic work
- AA-Briefcase v1.1 (Elo)78 Elo
- AutomationBench-AA0.5%
- GDPval-AA (normalized Elo)221 Elo
- τ²-Bench Telecom26.6%
- τ³-Banking3.7%
Long context & documents
Multimodal & science
- MMMU-Pro46.0%
Headline Evaluation Breakdown
Six independently measured evaluations (Artificial Analysis)0
Math · AIME 202531.7%
Long context · AA-LCR25.7%
Knowledge · Humanity's Last Exam4.3%
Instruction following · IFBench29.1%
Sourced Benchmark Evaluations (18)
Verified performance across authoritative benchmarks with provenance tracking.| Benchmark | Status | Score | Trust | Date | Source Type | Provenance |
|---|---|---|---|---|---|---|
| Terminal-Bench Hard | Active | 4.5% | 93 | 2026-11-15 | independent | Source ↗ |
| AutomationBench-AA | Active | 0.5% | 93 | 2026-11-15 | independent | Source ↗ |
| MLCR-AA (Medical Long Context Reasoning) | Active | 0% | 93 | 2026-11-15 | independent | Source ↗ |
| GDP.pdf | Active | 0.8% | 93 | 2026-11-15 | independent | Source ↗ |
| HLE-Diamond | Active | 4.4% | 93 | 2026-11-15 | independent | Source ↗ |
| CritPt | Active | 0% | 93 | 2026-11-15 | independent | Source ↗ |
| AA-LCR (Long Context Reasoning) | Active | 25.7% | 93 | 2026-11-15 | independent | Source ↗ |
| Terminal-Bench 4.0 | Active | 0% | 93 | 2026-11-15 | independent | Source ↗ |
| Terminal-Bench 2.1 | Active | 4.1% | 93 | 2026-11-15 | independent | Source ↗ |
| AIME | Nearing Saturation | 31.7% | 75 | 2026-11-15 | independent | Source ↗ |
| τ³-Banking | Active | 3.7% | 93 | 2026-11-15 | independent | Source ↗ |
| τ²-Bench Telecom | Active | 26.6% | 93 | 2026-11-15 | independent | Source ↗ |
| SciCode | Active | 20.7% | 93 | 2026-11-15 | independent | Source ↗ |
| IFBench | Active | 29.1% | 93 | 2026-11-15 | independent | Source ↗ |
| MMMU-Pro | Active | 46% | 93 | 2026-11-15 | independent | Source ↗ |
| LiveCodeBench | Saturated | 30.3% | 39 | 2026-11-15 | independent | Source ↗ |
| Humanity's Last Exam | Active | 4.3% | 93 | 2026-11-15 | independent | Source ↗ |
| GPQA | Nearing Saturation | 47.1% | 78 | 2026-11-15 | independent | Source ↗ |
Local Hardware Execution (Ollama)Hardware Compatible
# 1. Pull and execute model locally with Ollama
ollama run mistral-ministral-3-8b
# 2. Or invoke via local OpenAI-compatible endpoint
curl http://localhost:11434/v1/chat/completions \
-H "Content-Type: application/json" \
-d '{
"model": "mistral-ministral-3-8b",
"messages": [{"role": "user", "content": "Analyze reasoning chains on AIME 2026"}]
}'Evaluation & Sourcing Notes
Scores listed for Ministral 3 8B 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.