Gemini 3.5 Flash Lite vs MiniMax M3
Updated October 21, 2026. 77 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.
Decision reading
Pick MiniMax M3 for coding: it scores 57.8 on the Vibe Coding Index against 33.6 for Gemini 3.5 Flash Lite.
Pick Gemini 3.5 Flash Lite when a solved task costs $0.41 against $0.56, or when what matters is ALE-Bench or MMMU Pro (Vals AI), where it leads.
- Shared results
- 77
- Gemini 3.5 Flash Lite only
- 6
- MiniMax M3 only
- 39
- Like-for-like categories
- 7 of 9
Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.
Which one for your work
Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.
Coding
Vibe Coding Index, four public coding benchmarks
MiniMax M3
MiniMax M3 scores 57.8 against 33.6.
1 and 2 benchmarks behind the scores
Intelligence
AA Intelligence Index
MiniMax M3
MiniMax M3 leads, 29.2 against 22.2.
Same board, both measured
Agentic work
AA Agentic Index
MiniMax M3
MiniMax M3 leads, 29.5 against 14.3.
Same board, both measured
Reasoning
GPQA Diamond
MiniMax M3
MiniMax M3 leads, 92.7% against 83.8%.
Same board, both measured
Knowledge
MMLU Pro
Gemini 3.5 Flash Lite
Gemini 3.5 Flash Lite leads, 85.8% against 84.2%.
Same board, both measured
Web design
Design Arena: websites
No call
Only MiniMax M3 has a Design Arena: websites result, 1257.
Directional only
Long documents
Listed context window
No call
Both take 1.05M tokens.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
MiniMax M3
Gemini 3.5 Flash Lite $0.0015, MiniMax M3 $0.0009 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
Gemini 3.5 Flash Lite
Gemini 3.5 Flash Lite $0.41, MiniMax M3 $0.56.
Published attempt cost and pass rate
At a glance
- Coding index
- Gemini 3.5 Flash Lite 33.6 from 1 benchmark, MiniMax M3 57.8 from 2 benchmarks.
- Widest category
- Agentic work, 9.7 points apart on average over 6 shared benchmarks.
- Widest single gap
- Humanity's Last Exam (Artificial Analysis run): Gemini 3.5 Flash Lite 18.8% against MiniMax M3 39.0%, 20.2 points apart on a 0 to 100 scale.
- Output price
- Gemini 3.5 Flash Lite $2.50 against MiniMax M3 $1.20 per million output tokens, 2.1x apart.
- Context window
- Both take 1.05M tokens.
Benchmark by benchmark
First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.
| Category | Gemini 3.5 Flash Lite | Bars | MiniMax M3 | Ties |
|---|---|---|---|---|
| Coding | 1 | 12 | 1 tie | |
| Intelligence | 0 | 2 | ||
| Agentic work | 0 | 6 | ||
| Reasoning | 5 | 7 | ||
| Math | 1 | 2 | 1 tie | |
| Knowledge | 2 | 8 | ||
| General | 21 | 8 | ||
| All shared boards | 30 | 45 | 2 ties |
CodingLike-for-likeFour of these boards feed the Vibe Coding Index112
| Benchmark | Gemini 3.5 Flash Lite | MiniMax M3 | Leader |
|---|---|---|---|
| LiveBench coding | Not measured | 70.9% | Only MiniMax M3 measured |
| LMArena WebDev | 1435 | 1482 | MiniMax M3 |
| AA Coding Index | 49.3 | 58.6 | MiniMax M3 |
| LiveCodeBench (Vals AI) | 79.0% | 82.2% | MiniMax M3 |
| SWE-bench Verified (Vals AI) | 75.0% | 75.0% | Tie |
| Terminal-Bench 4 (Vals AI) | Not measured | 1.0% | Only MiniMax M3 measured |
| Vibe Code Bench (Vals AI) | 37.2% | 47.6% | MiniMax M3 |
| Code migration (Vals AI) | 6.2% | 19.9% | MiniMax M3 |
| ProgramBench (Vals AI) | 0.0% | Not measured | Only Gemini 3.5 Flash Lite measured |
| Terminal-Bench 2.1 (Vals AI) | 50.2% | 53.6% | MiniMax M3 |
| SWE-bench Multimodal (Vals AI) | Not measured | 33.3% | Only MiniMax M3 measured |
| Vibe Code Bench 1-100 (Vals AI) | Not measured | 9.2% | Only MiniMax M3 measured |
| SkillsBench (Vals AI) | Not measured | 51.5% | Only MiniMax M3 measured |
| CyberBench (Vals AI) | 59.1% | 65.0% | MiniMax M3 |
| SciCode | 41.3% | 47.1% | MiniMax M3 |
| Terminal-Bench Hard (Artificial Analysis run) | Not measured | 42.4% | Only MiniMax M3 measured |
| FrontierCode | Not measured | 14.7% | Only MiniMax M3 measured |
| WeirdML | 39.0% | Not measured | Only Gemini 3.5 Flash Lite measured |
| ALE-Bench | 765.3 | 640.0 | Gemini 3.5 Flash Lite |
| LMArena Text: coding | 1453 | 1470 | MiniMax M3 |
| LMArena Text: software and IT | 1451 | 1466 | MiniMax M3 |
| LMArena WebDev: React | 1408 | 1478 | MiniMax M3 |
| LMArena WebDev: HTML | Not measured | 1455 | Only MiniMax M3 measured |
| LMArena WebDev: from an image | 1448 | 1470 | MiniMax M3 |
| Neither model has a result on the other 14 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | Gemini 3.5 Flash Lite | MiniMax M3 | Leader |
|---|---|---|---|
| AA Intelligence Index | 22.2 | 29.2 | MiniMax M3 |
| Epoch Capabilities Index | 144.9 | 146.9 | MiniMax M3 |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index06
| Benchmark | Gemini 3.5 Flash Lite | MiniMax M3 | Leader |
|---|---|---|---|
| AA Agentic Index | 14.3 | 29.5 | MiniMax M3 |
| Design Arena: agents building web apps | Not measured | 1200 | Only MiniMax M3 measured |
| Design Arena: agents building full-stack apps | Not measured | 1197 | Only MiniMax M3 measured |
| Design Arena: agents building mobile apps | Not measured | 1169 | Only MiniMax M3 measured |
| Design Arena: agents building Android apps | Not measured | 1164 | Only MiniMax M3 measured |
| Design Arena: agents building games | Not measured | 1158 | Only MiniMax M3 measured |
| Design Arena: HTML slides | Not measured | 1180 | Only MiniMax M3 measured |
| Design Arena: PowerPoint slides | Not measured | 1205 | Only MiniMax M3 measured |
| Design Arena: spreadsheets | Not measured | 1021 | Only MiniMax M3 measured |
| LiveBench research | Not measured | 68.0% | Only MiniMax M3 measured |
| LiveBench browser | Not measured | 8.0% | Only MiniMax M3 measured |
| LiveBench long agentic | Not measured | 12.4% | Only MiniMax M3 measured |
| Finance Agent (Vals AI) | 47.4% | 48.3% | MiniMax M3 |
| Tax Agent Bench (Vals AI) | 7.2% | 20.6% | MiniMax M3 |
| Legal Research Bench (Vals AI) | 13.9% | 29.8% | MiniMax M3 |
| Excel Modeling Benchmark (Vals AI) | 43.2% | 47.8% | MiniMax M3 |
| τ²-Bench Telecom | Not measured | 88.9% | Only MiniMax M3 measured |
| APEX-Agents | 29.3% | 37.7% | MiniMax M3 |
| OSWorld 2.0 | Not measured | 4.6% | Only MiniMax M3 measured |
| Vending-Bench 2 | Not measured | $2,158 | Only MiniMax M3 measured |
| Neither model has a result on the other 19 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index57
| Benchmark | Gemini 3.5 Flash Lite | MiniMax M3 | Leader |
|---|---|---|---|
| GPQA Diamond | 83.8% | 92.7% | MiniMax M3 |
| LiveBench reasoning | Not measured | 74.5% | Only MiniMax M3 measured |
| MMMU Pro (Vals AI) | 83.6% | 81.2% | Gemini 3.5 Flash Lite |
| GPQA Diamond (Artificial Analysis run) | 83.8% | 92.9% | MiniMax M3 |
| Humanity's Last Exam (Artificial Analysis run) | 18.8% | 39.0% | MiniMax M3 |
| GPQA Diamond (Epoch AI run) | 83.3% | 90.9% | MiniMax M3 |
| ARC-AGI | 53.5% | Not measured | Only Gemini 3.5 Flash Lite measured |
| ARC-AGI-2 | 10.3% | Not measured | Only Gemini 3.5 Flash Lite measured |
| SimpleBench | Not measured | 45.8% | Only MiniMax M3 measured |
| Chess puzzles | 21.0% | 13.0% | Gemini 3.5 Flash Lite |
| Mystery game puzzles | 19.0% | 8.0% | Gemini 3.5 Flash Lite |
| LMArena Text: hard prompts | 1441 | 1447 | MiniMax M3 |
| LMArena Text: expert | 1434 | 1461 | MiniMax M3 |
| LMArena Text: hard prompts in English | 1440 | 1455 | MiniMax M3 |
| LMArena Vision: diagrams | 1284 | 1266 | Gemini 3.5 Flash Lite |
| LMArena Vision: homework | 1291 | 1268 | Gemini 3.5 Flash Lite |
| Neither model has a result on the other 5 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index12
| Benchmark | Gemini 3.5 Flash Lite | MiniMax M3 | Leader |
|---|---|---|---|
| OTIS Mock AIME | 71.1% | 71.1% | Tie |
| FrontierMath, tiers 1 to 3 | 26.0% | Not measured | Only Gemini 3.5 Flash Lite measured |
| FrontierMath, tier 4 | 0.0% | Not measured | Only Gemini 3.5 Flash Lite measured |
| ProofBench | 13.0% | 18.0% | MiniMax M3 |
| LMArena Text: math | 1434 | 1429 | Gemini 3.5 Flash Lite |
| LMArena Text: mathematical work | 1433 | 1448 | MiniMax M3 |
| Neither model has a result on the other 7 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index28
| Benchmark | Gemini 3.5 Flash Lite | MiniMax M3 | Leader |
|---|---|---|---|
| MMLU Pro | 85.8% | 84.2% | Gemini 3.5 Flash Lite |
| LegalBench (Vals AI) | 84.1% | 85.4% | MiniMax M3 |
| CorpFin (Vals AI) | 60.7% | 68.1% | MiniMax M3 |
| TaxEval (Vals AI) | 72.6% | 72.7% | MiniMax M3 |
| MortgageTax (Vals AI) | 68.7% | 68.4% | Gemini 3.5 Flash Lite |
| MedCode (Vals AI) | 43.5% | 46.3% | MiniMax M3 |
| LMArena Text: science | 1451 | 1452 | MiniMax M3 |
| LMArena Text: medicine and healthcare | 1438 | 1441 | MiniMax M3 |
| LMArena Text: legal and government | 1431 | 1437 | MiniMax M3 |
| LMArena Text: business and finance | 1423 | 1434 | MiniMax M3 |
| Neither model has a result on the other 7 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index9 boards, none shared
| Benchmark | Gemini 3.5 Flash Lite | MiniMax M3 | Leader |
|---|---|---|---|
| Design Arena: websites | Not measured | 1257 | Only MiniMax M3 measured |
| Design Arena: UI components | Not measured | 1246 | Only MiniMax M3 measured |
| Design Arena: game dev | Not measured | 1210 | Only MiniMax M3 measured |
| Design Arena: data viz | Not measured | 1235 | Only MiniMax M3 measured |
| Design Arena: 3D | Not measured | 1209 | Only MiniMax M3 measured |
| Design Arena: all code categories | Not measured | 1247 | Only MiniMax M3 measured |
| Design Arena: SVG | Not measured | 1161 | Only MiniMax M3 measured |
| Design Arena: ASCII art | Not measured | 1161 | Only MiniMax M3 measured |
| LiveBench design | Not measured | 66.2% | Only MiniMax M3 measured |
GeneralLike-for-likePublic boards, shown as published, kept out of the index218
| Benchmark | Gemini 3.5 Flash Lite | MiniMax M3 | Leader |
|---|---|---|---|
| LiveBench data analysis | Not measured | 76.2% | Only MiniMax M3 measured |
| Public Benefits Bench (Vals AI) | 51.8% | 64.1% | MiniMax M3 |
| SAGE (Vals AI) | 47.3% | 50.6% | MiniMax M3 |
| MedScribe (Vals AI) | 70.9% | 87.3% | MiniMax M3 |
| Vals Multimodal Index | Not measured | 60.0% | Only MiniMax M3 measured |
| IFBench | Not measured | 82.9% | Only MiniMax M3 measured |
| Long context reasoning (AA-LCR) | 76.0% | 83.0% | MiniMax M3 |
| DTBench | 83.5% | 78.9% | Gemini 3.5 Flash Lite |
| LMCA | 37.6% | 33.7% | Gemini 3.5 Flash Lite |
| Surface Evolver Bench | Not measured | 55.0% | Only MiniMax M3 measured |
| LMArena Text | 1435 | 1433 | Gemini 3.5 Flash Lite |
| LMArena Text: instruction following | 1419 | 1433 | MiniMax M3 |
| LMArena Text: creative writing | 1421 | 1404 | Gemini 3.5 Flash Lite |
| LMArena Vision | 1269 | 1251 | Gemini 3.5 Flash Lite |
| LMArena Text: English | 1438 | 1443 | MiniMax M3 |
| LMArena Text: non-English | 1427 | 1420 | Gemini 3.5 Flash Lite |
| LMArena Text: Chinese | 1468 | 1466 | Gemini 3.5 Flash Lite |
| LMArena Text: German | 1454 | 1428 | Gemini 3.5 Flash Lite |
| LMArena Text: Japanese | 1426 | 1380 | Gemini 3.5 Flash Lite |
| LMArena Text: Korean | 1407 | 1373 | Gemini 3.5 Flash Lite |
| LMArena Text: French | 1451 | 1444 | Gemini 3.5 Flash Lite |
| LMArena Text: Spanish | 1441 | 1433 | Gemini 3.5 Flash Lite |
| LMArena Text: Russian | 1443 | 1426 | Gemini 3.5 Flash Lite |
| LMArena Text: Polish | 1437 | 1423 | Gemini 3.5 Flash Lite |
| LMArena Text: multi-turn | 1445 | 1443 | Gemini 3.5 Flash Lite |
| LMArena Text: longer queries | 1435 | 1446 | MiniMax M3 |
| LMArena Text: writing and language | 1428 | 1419 | Gemini 3.5 Flash Lite |
| LMArena Text: entertainment and media | 1414 | 1403 | Gemini 3.5 Flash Lite |
| LMArena Vision: English | 1269 | 1263 | Gemini 3.5 Flash Lite |
| LMArena Vision: Chinese | 1311 | 1311 | MiniMax M3 |
| LMArena Vision: reading text | 1280 | 1259 | Gemini 3.5 Flash Lite |
| LMArena Vision: humor | 1287 | 1235 | Gemini 3.5 Flash Lite |
| LMArena Vision: recognizing things | Not measured | 1197 | Only MiniMax M3 measured |
| LMArena Vision: creative writing | 1260 | 1234 | Gemini 3.5 Flash Lite |
| LMArena Document | Not measured | 1435 | Only MiniMax M3 measured |
| Neither model has a result on the other 11 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Gemini 3.5 Flash Lite | MiniMax M3 | Leader |
|---|---|---|---|
| Neither model has a result on 5 boards here | |||
What each workload costs
Three fixed token mixes at each model's listed price, so per-token rates become a bill.
Chat turn
1K input + 500 output tokens
MiniMax M3 costs less
Repository review
50K input + 3K output tokens
MiniMax M3 costs less
Agent loop
200K input + 10K output tokens
MiniMax M3 costs less
Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.
Specification differences
The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.
| Specification | Google Gemini 3.5 Flash Lite | MiniMax M3 |
|---|---|---|
| Maker | MiniMax | |
| Weights | No public weights listed | Open weights |
| Released | July 21, 2026 | May 31, 2026 |
| Context window | 1.05M | 1.05M |
| Input $/Mtok | $0.30 | $0.30 |
| Output $/Mtok | $2.50 | $1.20 |
| Coding index | 33.6 | 57.8 |
| Independent measurements behind it | 1 | 2 |
| Cost per solved task | $0.41 | $0.56 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Gemini 3.5 Flash Lite better than MiniMax M3 for coding?
Pick MiniMax M3 for coding: it scores 57.8 on the Vibe Coding Index against 33.6 for Gemini 3.5 Flash Lite. Pick Gemini 3.5 Flash Lite when a solved task costs $0.41 against $0.56, or when what matters is ALE-Bench or MMMU Pro (Vals AI), where it leads.
Which is cheaper, Gemini 3.5 Flash Lite or MiniMax M3?
Gemini 3.5 Flash Lite costs $0.30 per million input tokens and $2.50 per million output tokens; MiniMax M3 costs $0.30 and $1.20. Per solved SWE-bench Verified task, Gemini 3.5 Flash Lite costs $0.41 and MiniMax M3 $0.56.
Which has the bigger context window, Gemini 3.5 Flash Lite or MiniMax M3?
Neither: both take 1.05M tokens.
How many benchmarks is the Gemini 3.5 Flash Lite vs MiniMax M3 comparison based on?
77 benchmarks have a result for both models as of October 21, 2026. Gemini 3.5 Flash Lite's coding index rests on 1 independent benchmark and MiniMax M3's on 2. Where only one model has a result, the page says so instead of naming a winner.