MiniMaxopen-weight
Released: 2026-10-19Artificial AnalysisMiniMax M3.1 Flash
OpenRouter ranked #12 foundation model processing 3.38T tokens weekly. Deployed by minimax.
Intelligence Index
29.1/ 100
Artificial Analysis Intelligence Index (independent composite)Throughput Speed
147tok/sec
Output streaming throughputTime to First Answer
50s
Time to first answer token, including any thinkingCost to Run the Index
0.49USD
Artificial Analysis cost of the full Index runMeasured results · Artificial Analysis
Independent evaluations of MiniMax M3.1 Flash. Values are reported as published; nothing here is estimated or derived. Snapshot 2026-11-15.
- Intelligence Index
- 29.1
- Cost to run the Index
- $0.49
- Time per task
- 15.7 min
- Omniscience index
- -6.4
- Reasoning model
- Yes
- Cached-input price
- $0.015 / 1M
Reasoning & knowledge
- AA-Omniscience Accuracy45.1%
- CritPt22.3%
- CritPt v2 (Hard)32.5%
- HLE-Diamond28.1%
- Humanity's Last Exam48.0%
Coding & terminal agents
- FrontierCode 1.138.6%
- FrontierCode-AA 2.020.8%
- SciCode53.4%
- Terminal-Bench 4.025.8%
- Terminal-Bench-Science 0.13.3%
Agentic work
- AA-Briefcase v1.1 (Elo)1474 Elo
- AutomationBench-AA72.5%
- GDPval-AA (normalized Elo)1465 Elo
- Multimodal Knowledge Agent (MKA)33.5%
Long context & documents
Health & safety
Headline Evaluation Breakdown
Six independently measured evaluations (Artificial Analysis)Reasoning · CritPt v2 (Hard)32.5%
Coding & agents · Terminal-Bench 4.025.8%
Long context · AA-LCR79.7%
Knowledge · Humanity's Last Exam48.0%
Sourced Benchmark Evaluations (18)
Verified performance across authoritative benchmarks with provenance tracking.| Benchmark | Status | Score | Trust | Date | Source Type | Provenance |
|---|---|---|---|---|---|---|
| HLE-Diamond | Active | 28.1% | 93 | 2026-11-15 | independent | Source ↗ |
| VIALS-AA | Active | 29.8% | 93 | 2026-11-15 | independent | Source ↗ |
| AutomationBench-AA | Active | 72.5% | 93 | 2026-11-15 | independent | Source ↗ |
| Multimodal Knowledge Agent (MKA) | Active | 33.5% | 93 | 2026-11-15 | independent | Source ↗ |
| MLCR-AA (Medical Long Context Reasoning) | Active | 16.7% | 93 | 2026-11-15 | independent | Source ↗ |
| GDP.pdf | Active | 20.8% | 93 | 2026-11-15 | independent | Source ↗ |
| FrontierCode-AA 2.0 | Active | 20.8% | 93 | 2026-11-15 | independent | Source ↗ |
| AA-Omniscience (Non-Hallucination) | Active | 6.3% | 93 | 2026-11-15 | independent | Source ↗ |
| AA-Omniscience (Accuracy) | Active | 45.1% | 93 | 2026-11-15 | independent | Source ↗ |
| FrontierCode | Active | 38.6% | 98 | 2026-11-15 | independent | Source ↗ |
| CritPt v2 (Hard) | Active | 32.5% | 93 | 2026-11-15 | independent | Source ↗ |
| CritPt | Active | 22.3% | 93 | 2026-11-15 | independent | Source ↗ |
| AA-LCR (Long Context Reasoning) | Active | 79.7% | 93 | 2026-11-15 | independent | Source ↗ |
| Terminal-Bench-Science 0.1 | Active | 3.3% | 93 | 2026-11-15 | independent | Source ↗ |
| Terminal-Bench 4.0 | Active | 25.8% | 93 | 2026-11-15 | independent | Source ↗ |
| SciCode | Active | 53.4% | 93 | 2026-11-15 | independent | Source ↗ |
| MMMU-Pro | Active | 79.1% | 93 | 2026-11-15 | independent | Source ↗ |
| Humanity's Last Exam | Active | 48% | 93 | 2026-11-15 | independent | Source ↗ |
Local Hardware Execution (Ollama)Hardware Compatible
# 1. Pull and execute model locally with Ollama
ollama run minimax-m3-1-flash
# 2. Or invoke via local OpenAI-compatible endpoint
curl http://localhost:11434/v1/chat/completions \
-H "Content-Type: application/json" \
-d '{
"model": "minimax-m3-1-flash",
"messages": [{"role": "user", "content": "Analyze reasoning chains on AIME 2026"}]
}'Evaluation & Sourcing Notes
Scores listed for MiniMax M3.1 Flash 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.