GPT-6.1 Sol vs MiniMax-M3.1-Flash
Full profiles: GPT-6.1 Sol (OpenAI) and MiniMax-M3.1-Flash (MiniMax): every benchmark, price and rank.
Updated · Data from 9 sources
As of 21 Oct 2026, GPT-6.1 Sol (max) leads on quality (69.9 vs 61.9 on the BenchLeader Index), but MiniMax-M3.1-Flash costs 15× less, so it is the better buy unless you need the extra quality. Pick GPT-6.1 Sol for knowledge (78 vs 69); pick MiniMax-M3.1-Flash for reasoning (78 vs 76).
GPT-6.1 Sol benchmarks 
MiniMax-M3.1-Flash benchmarks Which to pick for…
The pick's numbers come first. Category scores on the BenchLeader scale (50 is the average model, 15 points one standard deviation). High confidence means a lead of half a standard deviation or more; under one point is called either.
| Use case | Pick | Why | Confidence |
|---|---|---|---|
| Coding | GPT-6.1 Sol | 72 vs 63 category score; Arena WebDev 1753 vs 1588 | High |
| Reasoning | MiniMax-M3.1-Flash | 78 vs 76 category score; CritPt 22.3% vs 31.7% | Medium |
| Knowledge | GPT-6.1 Sol | 78 vs 69 category score; AA-Omniscience 41.5 vs 15.6 | High |
| Long documents | GPT-6.1 Sol | 67 vs 65 category score; AA-LCR 83.0% vs 79.7% | Medium |
| Images and other media | GPT-6.1 Sol | 66 vs 62 category score; MMMU-Pro 86.0% vs 79.1% | Medium |
| Chat quality (human preference) | – | Only GPT-6.1 Sol has an Arena rating (67 category score) | Not comparable |
| Lowest cost | MiniMax-M3.1-Flash | $0.262 vs $4.00 per 1M blended; agentic coding session $0.011 vs $0.160 | – |
| Fastest first answer | MiniMax-M3.1-Flash | 245.3 s (GPT-6.1 Sol (max)) vs 20.5 s (MiniMax-M3.1-Flash) to the first answer token | – |
| High volume on a budget | Neither flagship | A smaller model is usually the better fit: Cheapest good LLMs, Fastest LLMs | – |
Key differences
- GPT-6.1 Sol (max) leads on quality: 69.9 vs 61.9.
- GPT-6.1 Sol (max) is stronger in agents & tools, coding, composite, human preference, knowledge, long context, maths, multimodal.
- MiniMax-M3.1-Flash is stronger in reasoning.
- MiniMax-M3.1-Flash is 15× cheaper ($0.262 vs $4.00 per 1M blended).
- MiniMax-M3.1-Flash streams 1.9× faster (105 vs 54 tokens per second).
At a glance
| Spec | GPT-6.1 Sol | MiniMax-M3.1-Flash |
|---|---|---|
| Developer | OpenAI | MiniMax |
| Released | 29 Sept 2026 | 19 Oct 2026 |
| Context window (tokens) | 1,050,000 | 1,000,000 |
| Compared at | GPT-6.1 Sol (max) | MiniMax-M3.1-Flash |
| Open weights | No | No |
| Price in / out / cached input per 1M | $2.00 / $10.00 / $0.100 | $0.150 / $0.600 / $0.015 |
Category by category
Category scores on the BenchLeader scale: 50 is the average evaluated model, 15 points is one standard deviation. A gap under one point is called level.
| Category | GPT-6.1 Sol (max) | MiniMax-M3.1-Flash | Leader |
|---|---|---|---|
| Reasoning | 76.0 | 77.6 | MiniMax-M3.1-Flash |
| Coding | 72.1 | 62.5 | GPT-6.1 Sol |
| Agents & tools | 64.6 | – | not comparable |
| Maths | 73.0 | – | not comparable |
| Knowledge | 78.3 | 68.5 | GPT-6.1 Sol |
| Human preference | 67.1 | – | not comparable |
| Multimodal | 66.1 | 62.2 | GPT-6.1 Sol |
| Long context | 66.7 | 64.9 | GPT-6.1 Sol |
| Composite | 87.7 | 66.5 | GPT-6.1 Sol |
Where sources disagree
Across the 21 benchmarks both have, GPT-6.1 Sol leads 18, MiniMax-M3.1-Flash leads 3. Every overall index that rates both puts GPT-6.1 Sol ahead.
| Overall index | GPT-6.1 Sol (max) | MiniMax-M3.1-Flash | Leader |
|---|---|---|---|
| BenchLeader Index | 69.9 | 61.9 | GPT-6.1 Sol |
| AA Intelligence Index v4.3.2 | 51.8 | 42.7 | GPT-6.1 Sol |
| Vals Index | 63.9 | 53.8 | GPT-6.1 Sol |
Each publisher runs its own tasks, harnesses and effort settings, so their overall verdicts can differ; BenchLeader reconciles them on one scale. † measured at another effort setting of the same model (the publisher did not test the one compared here).
Price, speed and latency
List prices blended at three input tokens per output token. Per-task prices use the token counts on the methodology page; suite cost is what Artificial Analysis paid to run its whole Intelligence Index.
| Measure | GPT-6.1 Sol (max) | MiniMax-M3.1-Flash |
|---|---|---|
| Blended price per 1M tokens | $4.00 | $0.262 |
| Input / output per 1M | $2.00 / $10.00 | $0.150 / $0.600 |
| Cached input per 1M | $0.100 | $0.015 |
| Price per task: chat reply | $0.0038 | $0.0002 |
| Price per task: summarize a 30-page report | $0.030 | $0.0022 |
| Price per task: code edit | $0.027 | $0.0018 |
| Price per task: agentic coding session | $0.160 | $0.011 |
| Price per task: structured extraction | $0.0060 | $0.0004 |
| Cost to run a full benchmark suite | $0.724 | $0.220 |
| Output speed | 54 tok/s | 105 tok/s |
| Time to first answer | 245.3 s | 20.5 s |
| Time to a complete answer | 254.6 s | 25.3 s |
Per token is not per task: on Artificial Analysis' full suite GPT-6.1 Sol (max) cost $0.724 and MiniMax-M3.1-Flash $0.220, because MiniMax-M3.1-Flash used about 4.6× as many tokens for the same work, which a per-token price hides.
Each model is compared at its best-ranked reasoning-effort setting. GPT-6.1 Sol (max) scores 69.9 and takes 245 s to its first answer token; GPT-6.1 Sol (high) scores 67.7 in 28 s, GPT-6.1 Sol (xhigh) scores 67.7 in 96 s. MiniMax-M3.1-Flash scores 61.9 and takes 20 s to its first answer token. Higher effort means more thinking before the answer: better scores, longer waits and more tokens billed. How reasoning effort changes scores and cost.
Every benchmark
95 benchmarks, grouped by category; each name links to the board and its leaders. † measured at another effort setting of the same model, shown for reference and not counted as a win.
| Metric | Publisher | GPT-6.1 Sol (max) | MiniMax-M3.1-Flash |
|---|---|---|---|
| BenchLeader Index | BenchLeader | 69.9 | 61.9 |
| Agents & tools score | BenchLeader | 64.6 | – |
| Coding score | BenchLeader | 72.1 | 62.5 |
| Composite score | BenchLeader | 87.7 | 66.5 |
| Human preference score | BenchLeader | 67.1 | – |
| Knowledge score | BenchLeader | 78.3 | 68.5 |
| Long context score | BenchLeader | 66.7 | 64.9 |
| Maths score | BenchLeader | 73.0 | – |
| Multimodal score | BenchLeader | 66.1 | 62.2 |
| Reasoning score | BenchLeader | 76.0 | 77.6 |
| Blended price $/M | BenchLeader | $4.00 | $0.262 |
| Output speed | BenchLeader | 54 tok/s | 105 tok/s |
| Time to first answer | BenchLeader | 245.3 s | 20.5 s |
| Context window | BenchLeader | 1,050,000 tokens | 1,000,000 tokens |
| Reasoning | |||
| GPQA Diamond | Epoch AI Benchmarking Hub | 95.4% | – |
| Arena Hard Prompts | Arena (LMArena) | 1502 | – |
| LiveBench 2.0 Reasoning | LiveBench | 92.6%† | 82.9% |
| LiveBench 1.0 Reasoning | LiveBench | 92.6% | – |
| Humanity's Last Exam (AA) | Artificial Analysis | 52.9% | 48.0% |
| ARC-AGI-1 | ARC Prize | 96.5% | – |
| ARC-AGI-2 | ARC Prize | 94.2% | – |
| ARC-AGI-3 | ARC Prize | 96.2% | – |
| CritPt | Artificial Analysis | 31.7% | 22.3% |
| MysteryMechanism | Vals AI | 46.4% | – |
| Chess Puzzles | Epoch AI Benchmarking Hub | 68.0% | – |
| Mystery Game Puzzles | Epoch AI Benchmarking Hub | 80.0% | – |
| LMCA | Epoch AI Benchmarking Hub | 62.8% | – |
| DTBench | Epoch AI Benchmarking Hub | 96.5% | – |
| Coding | |||
| SciCode | SciCode | 54.2% | – |
| FrontierCode | Cognition | 50.2%† | – |
| Arena Coding | Arena (LMArena) | 1534 | – |
| Arena WebDev | Arena (LMArena) | 1753 | 1588 |
| LiveBench 2.0 Coding | LiveBench | 96.0%† | 83.9% |
| LiveBench 1.0 Coding | LiveBench | 80.4% | – |
| SciCode (AA) | Artificial Analysis | 54.2% | 53.4% |
| IOI | Vals AI | 96.9% | – |
| Code Migration | Vals AI | 65.1% | – |
| ProgramBench | Vals AI | 3.0% | – |
| Vibe Code Bench v1.1 | Vals AI | 88.9% | 73.9% |
Show all 95 benchmarks
| Metric | Publisher | GPT-6.1 Sol (max) | MiniMax-M3.1-Flash |
|---|---|---|---|
| Coding | |||
| ALE-Bench | Epoch AI Benchmarking Hub | 2743.8 | – |
| Terminal-Bench 4.0 (AA) | Artificial Analysis | 56.1% | 25.8% |
| Startrise Frontend | Startrise | 78.6%† | – |
| FrontierCode 1.1 (AA) | Artificial Analysis | 49.1% | 38.6% |
| Agents & tools | |||
| Terminal-Bench | Terminal-Bench | 58.2% | – |
| APEX-Agents | Mercor | 60.0% | – |
| Arena Agent | Arena (LMArena) | 13.5 | – |
| LiveBench Long Agentic | LiveBench | 73.0%† | 34.7% |
| LiveBench Browser | LiveBench | 88.0%† | 92.0% |
| LiveBench Agentic Coding | LiveBench | 54.5% | – |
| HiL-Bench | Scale AI SEAL | 62.3%† | – |
| GDPval-AA v2.1 | Artificial Analysis | 54.7% | 47.9% |
| Analyst Agent (AA) | Artificial Analysis | 50.0% | – |
| CyberBench | Vals AI | 39.3% | – |
| Finance Agent v2 | Vals AI | 52.0% | – |
| Harvey's Legal Agent Benchmark | Vals AI | 6.3% | 7.5% |
| Legal Research Bench | Vals AI | 38.5% | 34.1% |
| SREBench | Vals AI | 50.8% | – |
| Tax Agent Bench | Vals AI | 21.8% | 32.1% |
| Terminal-Bench 4.0 (Vals) | Vals AI | 55.0% | 25.3% |
| Terminal-Bench Science | Vals AI | 52.9% | – |
| Arena Search | Arena (LMArena) | 1250 | – |
| AutomationBench | Artificial Analysis | 64.9% | 72.5% |
| GDP.pdf (AA) | Artificial Analysis | 31.0% | 20.8% |
| Harvey LAB-AA v1.1 | Harvey | 6.9% | – |
| AA-Briefcase v1.1 | Artificial Analysis | 1557 | 1474 |
| Terminal-Bench-Science 0.1 (AA) | Artificial Analysis | 58.1% | 3.3% |
| FACTS Search | 88.2%† | – | |
| Maths | |||
| FrontierMath Tiers 1–3 | Epoch AI Benchmarking Hub | 93.7% | – |
| FrontierMath Tier 4 | Epoch AI Benchmarking Hub | 100.0% | – |
| OTIS Mock AIME | Epoch AI Benchmarking Hub | 100.0% | – |
| ProofBench | Vals AI | 99.0%† | – |
| LiveBench Mathematics | LiveBench | 96.8% | – |
| Arena Maths | Arena (LMArena) | 1512 | – |
| Knowledge | |||
| SimpleQA Verified | Epoch AI Benchmarking Hub | 73.9% | – |
| LiveBench 2.0 Data Analysis | LiveBench | 82.7%† | 71.4% |
| LiveBench Research | LiveBench | 83.5%† | 72.7% |
| LiveBench 1.0 Data Analysis | LiveBench | 82.7% | – |
| AA-Omniscience | Artificial Analysis | 41.5 | 15.6 |
| PRBench Finance | Scale AI SEAL | 46.2%† | – |
| PRBench Legal | Scale AI SEAL | 47.9%† | – |
| BioMysteryBench | Vals AI | 79.6% | – |
| Excel Modeling Benchmark | Vals AI | 70.8% | – |
| MedCode | Vals AI | 48.8% | – |
| MedScribe | Vals AI | 86.5% | – |
| Public Benefits Bench | Vals AI | 59.3% | – |
| EBR-bench | Epoch AI Benchmarking Hub | 54.3% | – |
| GDP.pdf | Epoch AI Benchmarking Hub | 35.0% | – |
| AA-Omniscience: accuracy | Artificial Analysis | 62.1% | 56.2% |
| AA-Omniscience: non-hallucination | Artificial Analysis | 45.7% | 7.2% |
| Instruction following | |||
| LiveBench Language | LiveBench | 90.1% | – |
| LiveBench Instruction Following | LiveBench | 74.2% | – |
| MultiChallenge | Scale AI SEAL | 82.0%† | – |
| Arena Instruction Following | Arena (LMArena) | 1484 | – |
| Human preference | |||
| Arena Text | Arena (LMArena) | 1479 | – |
| Arena Creative Writing | Arena (LMArena) | 1454 | – |
| Arena Multi-turn | Arena (LMArena) | 1479 | – |
| Arena Longer Queries | Arena (LMArena) | 1487 | – |
| Multimodal | |||
| Arena Vision | Arena (LMArena) | 1288 | – |
| LiveBench Design | LiveBench | 82.1%† | 74.0% |
| MMMU-Pro | Artificial Analysis | 86.0% | 79.1% |
| SAGE | Vals AI | 46.5% | – |
| AA-3D | Artificial Analysis | 1118 | – |
| Long context | |||
| AA-LCR | Artificial Analysis | 83.0% | 79.7% |
| MLCR | Artificial Analysis | 38.3% | – |
| Composite | |||
| Epoch Capabilities Index | Epoch AI Benchmarking Hub | 168.4† | – |
| LiveBench 2.0 | LiveBench | 85.4%† | 73.1% |
| LiveBench 1.0 | LiveBench | 81.6% | – |
| AA Intelligence Index v4.3.2 | Artificial Analysis | 51.8 | 42.7 |
| Vals Index | Vals AI | 63.9 | 53.8 |
Data as of 2026-10-21. Best configuration of each model; every score links to its source on the model pages.
What changed
- GPT-6.1 Sol (max): 5 score revisions.
- MiniMax-M3.1-Flash: 1 new result (Terminal-Bench-Science 0.1 (AA)).
- MiniMax-M3.1-Flash: BenchLeader Index 62.5 → 61.9.
- GPT-6.1 Sol (max): 2 score revisions.
- MiniMax-M3.1-Flash: 16 new results (FrontierCode 1.1 (AA), Arena WebDev, LiveBench 2.0…).
- GPT-6.1 Sol (max): BenchLeader Index 69.3 → 70.0.
- GPT-6.1 Sol (max): 2 new results (LMCA, DTBench).
- MiniMax-M3.1-Flash: first results.
- GPT-6.1 Sol (max): 2 score revisions.
- GPT-6.1 Sol (max): 2 new results (ProgramBench, Terminal-Bench Science); 1 score revision.
Related comparisons
- GPT-6.1 Sol vs Claude Opus 5.5
- GPT-6.1 Sol vs Gemini 4 Argon
- GPT-6.1 Sol vs Muse Wonder Full
- 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
- GPT-6.1 Sol vs Claude Fable 5.1
Rankings: Best LLM overall · Best LLM for coding · Best LLM for agents · Best cheap LLMs
GPT-6.1 Sol vs MiniMax-M3.1-Flash: questions
- Is GPT-6.1 Sol better than MiniMax-M3.1-Flash?
- GPT-6.1 Sol (max) leads on quality: 69.9 vs 61.9. The BenchLeader Index combines every independent quality benchmark; GPT-6.1 Sol (max) is ahead overall as of 2026-10-21, but check the category scores for your use.
- Which is cheaper, GPT-6.1 Sol or MiniMax-M3.1-Flash, and will that change?
- MiniMax-M3.1-Flash is cheaper today: $0.262 against $4.00 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
- Is GPT-6.1 Sol better than MiniMax-M3.1-Flash for coding?
- GPT-6.1 Sol scores higher in coding (72 vs 63 on the category index, where 50 is average). On Arena WebDev, the top shared coding benchmark, it is 1753 for GPT-6.1 Sol against 1588 for MiniMax-M3.1-Flash.
- Which is better for long documents?
- GPT-6.1 Sol scores higher on long-context benchmarks (67 vs 65). Both take about 1.1M tokens: GPT-6.1 Sol 1,050,000, MiniMax-M3.1-Flash 1,000,000.
- Which has lower latency?
- MiniMax-M3.1-Flash answers first: 20.5 s against 245.3 s to the first answer token, as Artificial Analysis measures it. Reasoning effort drives most of this: a higher setting thinks longer before it answers.
- Which is faster, GPT-6.1 Sol or MiniMax-M3.1-Flash?
- MiniMax-M3.1-Flash streams faster: 105 against 54 output tokens per second.
- Do independent benchmarks agree on GPT-6.1 Sol vs MiniMax-M3.1-Flash?
- Across the 21 benchmarks both have, GPT-6.1 Sol leads 18, MiniMax-M3.1-Flash leads 3. Every overall index that rates both puts GPT-6.1 Sol ahead.
- When was MiniMax-M3.1-Flash released?
- MiniMax-M3.1-Flash was released on 19 Oct 2026.