Gemini 4 Argon vs MiniMax-M3.1-Flash
Full profiles: Gemini 4 Argon (Google) and MiniMax-M3.1-Flash (MiniMax): every benchmark, price and rank.
Updated · Data from 9 sources
As of 21 Oct 2026, Gemini 4 Argon (high) leads on quality (71.0 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. Gemini 4 Argon (high)'s current price runs until 30 Nov 2026; from 1 Dec 2026 MiniMax-M3.1-Flash costs 30× less ($0.262 vs $8.00 per 1M blended); on use case, pick Gemini 4 Argon for coding (72 vs 63), MiniMax-M3.1-Flash for reasoning (78 vs 75).
Gemini 4 Argon benchmarks high Google
MiniMax-M3.1-Flash benchmarks MiniMaxOpen in the comparison toolWhich 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 | Gemini 4 Argon | 72 vs 63 category score; Arena WebDev 1678 vs 1588 | High |
| Reasoning | MiniMax-M3.1-Flash | 78 vs 75 category score; CritPt 22.3% vs 27.1% | Medium |
| Knowledge | Gemini 4 Argon | 77 vs 69 category score; AA-Omniscience 42.4 vs 15.6 | High |
| Long documents | Either | 65 vs 65 category score; AA-LCR 79.7% vs 79.7% | Either |
| Chat quality (human preference) | – | Only Gemini 4 Argon has an Arena rating (73 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; from 1 Dec 2026: $0.262 vs $8.00 | – |
| Fastest first answer | MiniMax-M3.1-Flash | 47.4 s (Gemini 4 Argon (high)) 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
- Gemini 4 Argon (high) leads on quality: 71.0 vs 61.9.
- Gemini 4 Argon (high) is stronger in agents & tools, coding, composite, human preference, knowledge, maths.
- MiniMax-M3.1-Flash is stronger in reasoning, multimodal.
- MiniMax-M3.1-Flash is 15× cheaper ($0.262 vs $4.00 per 1M blended) until 30 Nov 2026, then $0.262 vs $8.00 from 1 Dec 2026.
At a glance
| Spec | Gemini 4 Argon | MiniMax-M3.1-Flash |
|---|---|---|
| Developer | MiniMax | |
| Released | 30 Sept 2026 | 19 Oct 2026 |
| Generally available | 13 Oct 2026 | 19 Oct 2026 |
| Context window (tokens) | 1,048,576 | 1,000,000 |
| Max output (tokens) | 65,536 (up to 1,048,576 with long decode) | – |
| Input types | text, image, video, audio, PDF | – |
| Reasoning effort settings | low, medium, high | – |
| Compared at | Gemini 4 Argon (high) | 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 |
| Announced price change | $4.00 / $20.00 / $0.200 from 1 Dec 2026 | None announced |
| API model ID | gemini-4-argon | – |
| Where to use it | Gemini API (AI Studio), Gemini Enterprise Agent Platform, Gemini app | – |
Limits, availability and announced prices from the vendors' own pages: ai.google.dev, ai.google.dev pricing (checked 20 Oct 2026). Everything else is from the day's data.
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 | Gemini 4 Argon (high) | MiniMax-M3.1-Flash | Leader |
|---|---|---|---|
| Reasoning | 74.9 | 77.6 | MiniMax-M3.1-Flash |
| Coding | 72.1 | 62.5 | Gemini 4 Argon |
| Agents & tools | 71.8 | – | not comparable |
| Maths | 70.4 | – | not comparable |
| Knowledge | 76.5 | 68.5 | Gemini 4 Argon |
| Human preference | 72.5 | – | not comparable |
| Multimodal | – | 62.2 | not comparable |
| Long context | 64.9 | 64.9 | level |
| Composite | 88.5 | 66.5 | Gemini 4 Argon |
Where sources disagree
Across the 20 benchmarks both have, Gemini 4 Argon leads 18, MiniMax-M3.1-Flash leads 1 and 1 is a tie. Every overall index that rates both puts Gemini 4 Argon ahead.
| Overall index | Gemini 4 Argon (high) | MiniMax-M3.1-Flash | Leader |
|---|---|---|---|
| BenchLeader Index | 71.0 | 61.9 | Gemini 4 Argon |
| AA Intelligence Index v4.3.2 | 52.6 | 42.7 | Gemini 4 Argon |
| Vals Index | 69.2 | 53.8 | Gemini 4 Argon |
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 | Gemini 4 Argon (high) | MiniMax-M3.1-Flash |
|---|---|---|
| Blended price per 1M tokens, until 30 Nov 2026 | $4.00 | $0.262 |
| Input / output per 1M | $2.00 / $10.00 | $0.150 / $0.600 |
| Blended price per 1M from 1 Dec 2026 | $8.00 | $0.262 |
| Input / output per 1M from 1 Dec 2026 | $4.00 / $20.00 | $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 | $1.99 | $0.220 |
| Output speed | 83 tok/s | 105 tok/s |
| Time to first answer | 47.4 s | 20.5 s |
| Time to a complete answer | 53.5 s | 25.3 s |
Per token is not per task: on Artificial Analysis' full suite Gemini 4 Argon (high) cost $1.99 and MiniMax-M3.1-Flash $0.220, because MiniMax-M3.1-Flash used about 1.7× as many tokens for the same work, which a per-token price hides.
Each model is compared at its best-ranked reasoning-effort setting. Gemini 4 Argon (high) scores 71.0 and takes 47 s to its first answer token; Gemini 4 Argon scores 63.3 in 4 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
92 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 | Gemini 4 Argon (high) | MiniMax-M3.1-Flash |
|---|---|---|---|
| BenchLeader Index | BenchLeader | 71.0 | 61.9 |
| Agents & tools score | BenchLeader | 71.8 | – |
| Coding score | BenchLeader | 72.1 | 62.5 |
| Composite score | BenchLeader | 88.5 | 66.5 |
| Human preference score | BenchLeader | 72.5 | – |
| Knowledge score | BenchLeader | 76.5 | 68.5 |
| Long context score | BenchLeader | 64.9 | 64.9 |
| Maths score | BenchLeader | 70.4 | – |
| Reasoning score | BenchLeader | 74.9 | 77.6 |
| Multimodal score | BenchLeader | – | 62.2 |
| Blended price $/M | BenchLeader | $4.00 | $0.262 |
| Output speed | BenchLeader | 83 tok/s | 105 tok/s |
| Time to first answer | BenchLeader | 47.4 s | 20.5 s |
| Context window | BenchLeader | 1,048,576 tokens | 1,000,000 tokens |
| Reasoning | |||
| GPQA Diamond | Epoch AI Benchmarking Hub | 96.4% | – |
| Arena Hard Prompts | Arena (LMArena) | 1549 | – |
| LiveBench 2.0 Reasoning | LiveBench | 95.1%† | 82.9% |
| Humanity's Last Exam (AA) | Artificial Analysis | 57.1% | 48.0% |
| ARC-AGI-1 | ARC Prize | 98.5% | – |
| ARC-AGI-2 | ARC Prize | 91.3% | – |
| ARC-AGI-3 | ARC Prize | 97.3% | – |
| CritPt | Artificial Analysis | 27.1% | 22.3% |
| MysteryMechanism | Vals AI | 45.5% | – |
| Chess Puzzles | Epoch AI Benchmarking Hub | 59.0% | – |
| Mystery Game Puzzles | Epoch AI Benchmarking Hub | 64.0% | – |
| LMCA | Epoch AI Benchmarking Hub | 63.7% | – |
| DTBench | Epoch AI Benchmarking Hub | 97.3% | – |
| Coding | |||
| SciCode | SciCode | 61.8% | – |
| FrontierCode | Cognition | 47.5%† | – |
| Arena Coding | Arena (LMArena) | 1559 | – |
| Arena WebDev | Arena (LMArena) | 1678 | 1588 |
| LiveBench 2.0 Coding | LiveBench | 89.7%† | 83.9% |
| SciCode (AA) | Artificial Analysis | 61.8% | 53.4% |
| IOI | Vals AI | 100.0% | – |
| Code Migration | Vals AI | 68.2% | – |
| ProgramBench | Vals AI | 2.5% | – |
| Vibe Code Bench 1-100 | Vals AI | 21.2% | – |
| Vibe Code Bench v1.1 | Vals AI | 91.9% | 73.9% |
| CursorBench | Cursor | 52.9% | – |
Show all 92 benchmarks
| Metric | Publisher | Gemini 4 Argon (high) | MiniMax-M3.1-Flash |
|---|---|---|---|
| Coding | |||
| ALE-Bench | Epoch AI Benchmarking Hub | 2100.1 | – |
| FrontierSWE | Epoch AI Benchmarking Hub | 55.0% | – |
| Terminal-Bench 4.0 (AA) | Artificial Analysis | 57.1% | 25.8% |
| FrontierCode 1.1 (AA) | Artificial Analysis | 43.5% | 38.6% |
| Agents & tools | |||
| APEX-Agents | Mercor | 82.4%† | – |
| Arena Agent | Arena (LMArena) | 12 | – |
| LiveBench Long Agentic | LiveBench | 69.9%† | 34.7% |
| LiveBench Browser | LiveBench | 92.0%† | 92.0% |
| HiL-Bench | Scale AI SEAL | 62.0%† | – |
| GDPval-AA v2.1 | Artificial Analysis | 56.2% | 47.9% |
| Analyst Agent (AA) | Artificial Analysis | 48.8% | – |
| CUA-bench | Vals AI | 4.8% | – |
| CyberBench | Vals AI | 77.9% | – |
| Finance Agent v2 | Vals AI | 65.4% | – |
| Harvey's Legal Agent Benchmark | Vals AI | 27.1% | 7.5% |
| Legal Research Bench | Vals AI | 54.8% | 34.1% |
| SREBench | Vals AI | 44.3% | – |
| Tax Agent Bench | Vals AI | 44.6% | 32.1% |
| Terminal-Bench 4.0 (Vals) | Vals AI | 57.6% | 25.3% |
| Terminal-Bench Science | Vals AI | 44.3% | – |
| Time Horizon Index: KSP | Vals AI | 52.5% | – |
| Vending-Bench 2 | Andon Labs | 13718.2† | – |
| AutomationBench | Artificial Analysis | 77.5% | 72.5% |
| GDP.pdf (AA) | Artificial Analysis | 21.8% | 20.8% |
| Harvey LAB-AA v1.1 | Harvey | 3.9% | – |
| AA-Briefcase v1.1 | Artificial Analysis | 1486 | 1474 |
| Terminal-Bench-Science 0.1 (AA) | Artificial Analysis | 52.9% | 3.3% |
| FACTS Search | 84.0%† | – | |
| Maths | |||
| FrontierMath Tiers 1–3 | Epoch AI Benchmarking Hub | 86.0% | – |
| FrontierMath Tier 4 | Epoch AI Benchmarking Hub | 78.0% | – |
| OTIS Mock AIME | Epoch AI Benchmarking Hub | 100.0% | – |
| ProofBench | Vals AI | 99.0%† | – |
| Arena Maths | Arena (LMArena) | 1529 | – |
| Knowledge | |||
| SimpleQA Verified | Epoch AI Benchmarking Hub | 76.0% | – |
| LiveBench 2.0 Data Analysis | LiveBench | 85.2%† | 71.4% |
| LiveBench Research | LiveBench | 83.1%† | 72.7% |
| AA-Omniscience | Artificial Analysis | 42.4 | 15.6 |
| LegalBench | Vals AI | 88.3% | – |
| PRBench Finance | Scale AI SEAL | 49.9%† | – |
| PRBench Legal | Scale AI SEAL | 49.4%† | – |
| BioMysteryBench | Vals AI | 76.3% | – |
| Excel Modeling Benchmark | Vals AI | 75.2% | – |
| MedCode | Vals AI | 58.8% | – |
| MedScribe | Vals AI | 87.4% | – |
| Public Benefits Bench | Vals AI | 69.8% | – |
| EBR-bench | Epoch AI Benchmarking Hub | 64.8% | – |
| GDP.pdf | Epoch AI Benchmarking Hub | 28.4% | – |
| AA-Omniscience: accuracy | Artificial Analysis | 49.9% | 56.2% |
| AA-Omniscience: non-hallucination | Artificial Analysis | 84.9% | 7.2% |
| Instruction following | |||
| Arena Instruction Following | Arena (LMArena) | 1525 | – |
| Human preference | |||
| Arena Text | Arena (LMArena) | 1524 | – |
| Arena Creative Writing | Arena (LMArena) | 1516 | – |
| Arena Multi-turn | Arena (LMArena) | 1552 | – |
| Arena Longer Queries | Arena (LMArena) | 1543 | – |
| Multimodal | |||
| LiveBench Design | LiveBench | 73.7%† | 74.0% |
| MMMU-Pro | Artificial Analysis | – | 79.1% |
| SAGE | Vals AI | 53.6% | – |
| AudioMC | Scale AI SEAL | 58.4% | – |
| AudioMC (text output) | Scale AI SEAL | 58.4% | – |
| Blueprint-Bench 2 | Epoch AI Benchmarking Hub | 54.5%† | – |
| AA-3D | Artificial Analysis | 1154 | – |
| Long context | |||
| AA-LCR | Artificial Analysis | 79.7% | 79.7% |
| MLCR | Artificial Analysis | 13.9% | – |
| Composite | |||
| Epoch Capabilities Index | Epoch AI Benchmarking Hub | 166.4† | – |
| LiveBench 2.0 | LiveBench | 84.1%† | 73.1% |
| AA Intelligence Index v4.3.2 | Artificial Analysis | 52.6 | 42.7 |
| Vals Index | Vals AI | 69.2 | 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
- Gemini 4 Argon: list price moves to $4.00 / $20.00 per 1M input / output tokens (announced).
- Gemini 4 Argon (high): 1 new result (MLCR).
- MiniMax-M3.1-Flash: 1 new result (Terminal-Bench-Science 0.1 (AA)).
- MiniMax-M3.1-Flash: BenchLeader Index 62.5 → 61.9.
- Gemini 4 Argon (high): 1 new result (Harvey LAB-AA v1.1); 2 score revisions.
- MiniMax-M3.1-Flash: 16 new results (FrontierCode 1.1 (AA), Arena WebDev, LiveBench 2.0…).
- Gemini 4 Argon (high): 3 new results (LMCA, DTBench, ALE-Bench).
- MiniMax-M3.1-Flash: first results.
- Gemini 4 Argon (high): 5 new results (Analyst Agent (AA), FrontierCode 1.1 (AA), Terminal-Bench-Science 0.1 (AA)…); 1 score revision.
- Gemini 4 Argon (high): 6 new results (EBR-bench, Time Horizon Index: KSP, Vibe Code Bench 1-100…); 1 score revision.
Related comparisons
- Gemini 4 Argon vs Claude Opus 5.5
- Gemini 4 Argon vs Muse Wonder Full
- Gemini 4 Argon vs GPT-6 Astra
- MiniMax-M3.1-Flash vs Claude Opus 5.5
- MiniMax-M3.1-Flash vs Muse Wonder Full
- MiniMax-M3.1-Flash vs GPT-6 Astra
- Gemini 4 Argon vs GPT-6.1 Sol
- Gemini 4 Argon vs Claude Sonnet 5.5
Rankings: Best LLM overall · Best LLM for coding · Best LLM for agents · Best cheap LLMs
Gemini 4 Argon vs MiniMax-M3.1-Flash: questions
- Is Gemini 4 Argon better than MiniMax-M3.1-Flash?
- Gemini 4 Argon (high) leads on quality: 71.0 vs 61.9. The BenchLeader Index combines every independent quality benchmark; Gemini 4 Argon (high) is ahead overall as of 2026-10-21, but check the category scores for your use.
- Which is cheaper, Gemini 4 Argon 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. Yes, that changes: Gemini 4 Argon's list price changes on 1 Dec 2026, and from then MiniMax-M3.1-Flash is cheaper ($0.262 vs $8.00 blended).
- Is Gemini 4 Argon better than MiniMax-M3.1-Flash for coding?
- Gemini 4 Argon 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 1678 for Gemini 4 Argon against 1588 for MiniMax-M3.1-Flash.
- Which is better for long documents?
- They are level on long-context benchmarks (65 vs 65). Both take about 1M tokens: Gemini 4 Argon 1,048,576, MiniMax-M3.1-Flash 1,000,000.
- Which has lower latency?
- MiniMax-M3.1-Flash answers first: 20.5 s against 47.4 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, Gemini 4 Argon or MiniMax-M3.1-Flash?
- MiniMax-M3.1-Flash streams faster: 105 against 83 output tokens per second.
- Do independent benchmarks agree on Gemini 4 Argon vs MiniMax-M3.1-Flash?
- Across the 20 benchmarks both have, Gemini 4 Argon leads 18, MiniMax-M3.1-Flash leads 1 and 1 is a tie. Every overall index that rates both puts Gemini 4 Argon ahead.
- When was MiniMax-M3.1-Flash released?
- MiniMax-M3.1-Flash was released on 19 Oct 2026.