MiniMaxMiniMax-M3.1-Flash
MiniMax-M3.1-Flash is a MiniMax proprietary reasoning model, released 19 Oct 2026. Its best configuration ranks #92 of 775 on the BenchLeader Index at 61.9 ±5.6, in the upper half. The ± is the point: 202 other configurations score within that range, so they and this one cannot be told apart on quality alone — price and speed are what separate them. It scores highest in reasoning (78) and lowest in multimodal (62). At $0.262 per million tokens blended it is cheaper than most ranked models. Output speed of 105 tokens per second puts it faster than most, with a first answer in 20.5 s. Last measured 19 Oct 2026.
- Blended price
- $0.262/M
- $0.150 in · $0.600 out
- Output speed
- 105 tok/s
- measured by Artificial Analysis
- First answer
- 20 s
- Context
- 1M
- Full answer
- 25 s
- median, reasoning included
- Cost per run
- $0.220
- one full Intelligence Index run
- Released
- 19 Oct 2026
- Overall index62
- Reasoning78
- Coding63
- Knowledge69
- Multimodal62
- Long context65
- Composite67
Benchmark results
See all LLM benchmarks. One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.
Reasoning
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| LiveBench 2.0 Reasoningnot in index | 82.9%#34 | LiveBench | |
| Humanity's Last Exam (AA)not in index | 48.0%#34 | Artificial Analysis | |
| CritPt | 22.3%#55 | Artificial Analysis |
Coding
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Arena WebDev | 1588#30 | Arena (LMArena) | |
| LiveBench 2.0 Codingnot in index | 83.9%#25 | LiveBench | |
| SciCode (AA)not in index | 53.4%#76 | Artificial Analysis | |
| Vibe Code Bench v1.1not in index | 73.9%#37 | Vals AI | |
| Terminal-Bench 4.0 (AA)not in index | 25.8%#52 | Artificial Analysis | |
| FrontierCode 1.1 (AA)not in index | 38.6%#29 | Artificial Analysis |
Agents & tools
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| LiveBench Long Agenticnot in index | 34.7%#29 | LiveBench | |
| LiveBench Browsernot in index | 92.0%#3 | LiveBench | |
| GDPval-AA v2.1not in index | 47.9%#58 | Artificial Analysis | |
| Harvey's Legal Agent Benchmarknot in index | 7.5%#16 | Vals AI | |
| Legal Research Benchnot in index | 34.1%#43 | Vals AI | |
| Tax Agent Benchnot in index | 32.1%#18 | Vals AI | |
| Terminal-Bench 4.0 (Vals)not in index | 25.3%#22 | Vals AI | |
| AutomationBenchnot in index | 72.5%#2 | Artificial Analysis | |
| GDP.pdf (AA)not in index | 20.8%#58 | Artificial Analysis | |
| AA-Briefcase v1.1not in index | 1474#34 | Artificial Analysis |
Knowledge
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| LiveBench 2.0 Data Analysisnot in index | 71.4%#34 | LiveBench | |
| LiveBench Researchnot in index | 72.7%#27 | LiveBench | |
| AA-Omniscience | 15.6#79 | Artificial Analysis | |
| AA-Omniscience: accuracynot in index | 56.2%#34 | Artificial Analysis | |
| AA-Omniscience: non-hallucinationnot in index | 7.2%#486 | Artificial Analysis |
Multimodal
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| LiveBench Designnot in index | 74.0%#30 | LiveBench | |
| MMMU-Pro | 79.1%#62 | Artificial Analysis |
Long context
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| AA-LCR | 79.7%#87 | Artificial Analysis |
Composite
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| LiveBench 2.0 | 73.1%#21 | LiveBench | |
| AA Intelligence Index v4.3.2 | 42.7#48 | Artificial Analysis | |
| Vals Indexnot in index | 53.8#15 | Vals AI |
What a task costs
Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache at $0.015 per 1M. Reasoning tokens are not modelled.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.0002 | $0.0002 | 23.4 s |
| Summarize a 30-page report | 12,000 / 600 | $0.0022 | $0.0009 | 26.2 s |
| Code edit | 6,000 / 1,500 | $0.0018 | $0.0012 | 34.8 s |
| Agentic coding session | 60,000 / 4,000 | $0.011 | $0.0053 | 58.7 s |
| Structured extraction | 2,000 / 200 | $0.0004 | $0.0002 | 22.4 s |
More from MiniMax
Compare MiniMax-M3.1-Flash with…
- MiniMax-M3.1-Flash vs Claude Opus 5.5
- MiniMax-M3.1-Flash vs Gemini 4 Argon
- MiniMax-M3.1-Flash vs Muse Wonder Full
- MiniMax-M3.1-Flash vs GPT-6 Astra
- MiniMax-M3.1-Flash vs Claude Fable 5.1
- MiniMax-M3.1-Flash vs GPT-6.1 Sol
- MiniMax-M3.1-Flash vs Claude Sonnet 5.5
- MiniMax-M3.1-Flash vs Claude Fable 5
- MiniMax-M3.1-Flash vs Claude Opus 5
- MiniMax-M3.1-Flash vs GPT-5.6 Sol
See also
Data as of 21 Oct 2026. Compare with another model.
Cite as: BenchLeader, “MiniMax-M3.1-Flash: benchmarks, pricing, speed and rank”, https://www.benchleader.com/models/minimax-m3-1-flash, data as of 21 Oct 2026.