MiniMax M2.5 vs o1
MiniMax M2.5 leads o1 on the Artificial Analysis Intelligence Index, 22.8 to 15.2, and MiniMax M2.5 costs 50.0x less per output token ($1.20 vs $60.00 per million). Updated October 22, 2026; 43 benchmarks have a result for both.
MiniMax M2.5 or o1: which to pick
Only MiniMax M2.5 has a coding score, 37.2 on the Vibe Coding Index; o1 has none, so the two cannot be ranked on coding.
Pick o1 for work measured by LMArena Text: math or LMArena Text: mathematical work, where it leads.
- Shared results
- 43
- MiniMax M2.5 only
- 25
- o1 only
- 26
- Like-for-like categories
- 7 of 9
Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.
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, six public coding benchmarks
No call
Only MiniMax M2.5 has a coding score, so no call is made.
One side not measured
Intelligence
AA Intelligence Index
MiniMax M2.5
MiniMax M2.5 leads, 22.8 against 15.2.
Same board, both measured
Reasoning
GPQA Diamond
MiniMax M2.5
MiniMax M2.5 leads, 82.1% against 73.2%.
Same board, both measured
Math
AIME
MiniMax M2.5
MiniMax M2.5 leads, 88.8% against 71.5%.
Same board, both measured
Knowledge
MMLU Pro
o1
o1 leads, 83.5% against 80.1%.
Same board, both measured
Web design
Design Arena: websites
No call
Only MiniMax M2.5 has a Design Arena: websites result, 1222.
Directional only
Long documents
Listed context window
MiniMax M2.5
MiniMax M2.5 takes 205K tokens against 200K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
MiniMax M2.5
MiniMax M2.5 $0.0009, o1 $0.045 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only MiniMax M2.5 has the number, $0.62.
Directional only
At a glance
- Coding index
- MiniMax M2.5 37.2 from 3 benchmarks, o1 not benchmarked.
- Widest category
- Agentic work, 32.7 points apart on average over 1 shared benchmark.
- Widest single gap
- ARC-AGI: MiniMax M2.5 63.7% against o1 30.7%, 33.0 points apart on a 0 to 100 scale.
- Output price
- MiniMax M2.5 $1.20 against o1 $60.00 per million output tokens, 50.0x apart.
- Context window
- MiniMax M2.5 takes 205K tokens, o1 200K.
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 | MiniMax M2.5 | Bars | o1 | Ties |
|---|---|---|---|---|
| Coding | 4 | 0 | ||
| Intelligence | 2 | 0 | ||
| Agentic work | 1 | 0 | ||
| Reasoning | 7 | 0 | ||
| Math | 1 | 2 | ||
| Knowledge | 3 | 5 | ||
| General | 8 | 10 | ||
| All shared boards | 26 | 17 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index40
| Benchmark | MiniMax M2.5 | o1 | Leader |
|---|---|---|---|
| Aider polyglot | Not measured | 61.7% | Only o1 measured |
| SWE-bench Verified | 75.8% | Not measured | Only MiniMax M2.5 measured |
| SWE-bench Multilingual | 68.3% | Not measured | Only MiniMax M2.5 measured |
| LMArena WebDev | 1386 | Not measured | Only MiniMax M2.5 measured |
| AA Coding Index | Not measured | 39.7 | Only o1 measured |
| LiveCodeBench (Vals AI) | 79.2% | 50.3% | MiniMax M2.5 |
| SWE-bench Verified (Vals AI) | 74.2% | Not measured | Only MiniMax M2.5 measured |
| Vibe Code Bench (Vals AI) | 14.8% | Not measured | Only MiniMax M2.5 measured |
| LiveCodeBench (Artificial Analysis run) | Not measured | 67.9% | Only o1 measured |
| Terminal-Bench Hard (Artificial Analysis run) | 34.8% | 12.9% | MiniMax M2.5 |
| Terminal-Bench | 42.7% | Not measured | Only MiniMax M2.5 measured |
| WeirdML | Not measured | 46.1% | Only o1 measured |
| ALE-Bench | 618.2 | Not measured | Only MiniMax M2.5 measured |
| LMArena Text: coding | 1380 | 1367 | MiniMax M2.5 |
| LMArena Text: software and IT | 1383 | 1366 | MiniMax M2.5 |
| LMArena WebDev: React | 1374 | Not measured | Only MiniMax M2.5 measured |
| LMArena WebDev: HTML | 1414 | Not measured | Only MiniMax M2.5 measured |
| SciCode | Not measured | 4.6% | Only o1 measured |
| Neither model has a result on the other 21 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | MiniMax M2.5 | o1 | Leader |
|---|---|---|---|
| AA Intelligence Index | 22.8 | 15.2 | MiniMax M2.5 |
| Epoch Capabilities Index | 146.6 | 141.7 | MiniMax M2.5 |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | MiniMax M2.5 | o1 | Leader |
|---|---|---|---|
| τ²-Bench Telecom | 95.3% | 62.6% | MiniMax M2.5 |
| METR time horizons | Not measured | 51.1% | Only o1 measured |
| Vending-Bench 2 | -$23 | Not measured | Only MiniMax M2.5 measured |
| Neither model has a result on the other 38 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index70
| Benchmark | MiniMax M2.5 | o1 | Leader |
|---|---|---|---|
| GPQA Diamond | 82.1% | 73.2% | MiniMax M2.5 |
| MMMU Pro (Vals AI) | Not measured | 77.4% | Only o1 measured |
| GPQA Diamond (Artificial Analysis run) | 84.8% | 74.7% | MiniMax M2.5 |
| Humanity's Last Exam (Artificial Analysis run) | 20.5% | 7.0% | MiniMax M2.5 |
| GPQA Diamond (Epoch AI run) | Not measured | 76.8% | Only o1 measured |
| ARC-AGI | 63.7% | 30.7% | MiniMax M2.5 |
| ARC-AGI-2 | 4.9% | Not measured | Only MiniMax M2.5 measured |
| SimpleBench | Not measured | 40.1% | Only o1 measured |
| Chess puzzles | Not measured | 10.0% | Only o1 measured |
| VPCT | Not measured | 37.0% | Only o1 measured |
| LMArena Text: hard prompts | 1372 | 1371 | MiniMax M2.5 |
| LMArena Text: expert | 1378 | 1361 | MiniMax M2.5 |
| LMArena Text: hard prompts in English | 1384 | 1372 | MiniMax M2.5 |
| Kagi LLM Benchmark | 55.2% | Not measured | Only MiniMax M2.5 measured |
| Neither model has a result on the other 8 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index12
| Benchmark | MiniMax M2.5 | o1 | Leader |
|---|---|---|---|
| AIME | 88.8% | 71.5% | MiniMax M2.5 |
| MATH 500 (Vals AI) | Not measured | 90.4% | Only o1 measured |
| MGSM (Vals AI) | Not measured | 89.3% | Only o1 measured |
| OTIS Mock AIME | Not measured | 73.3% | Only o1 measured |
| FrontierMath, tiers 1 to 3 | Not measured | 14.7% | Only o1 measured |
| ProofBench | 4.0% | Not measured | Only MiniMax M2.5 measured |
| MATH level 5 | Not measured | 94.7% | Only o1 measured |
| LMArena Text: math | 1378 | 1388 | o1 |
| LMArena Text: mathematical work | 1378 | 1390 | o1 |
| Neither model has a result on the other 4 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index35
| Benchmark | MiniMax M2.5 | o1 | Leader |
|---|---|---|---|
| MMLU Pro | 80.1% | 83.5% | o1 |
| LegalBench (Vals AI) | 80.0% | 80.4% | o1 |
| CaseLaw (Vals AI) | 53.5% | Not measured | Only MiniMax M2.5 measured |
| CorpFin (Vals AI) | 59.6% | Not measured | Only MiniMax M2.5 measured |
| TaxEval (Vals AI) | 68.2% | 74.3% | o1 |
| MedQA (Vals AI) | 92.5% | 96.5% | o1 |
| MMLU Pro (Artificial Analysis run) | Not measured | 84.1% | Only o1 measured |
| SimpleQA Verified | Not measured | 41.1% | Only o1 measured |
| GeoBench | Not measured | 80.0% | Only o1 measured |
| LMArena Text: science | 1369 | 1369 | MiniMax M2.5 |
| LMArena Text: medicine and healthcare | 1357 | 1355 | MiniMax M2.5 |
| LMArena Text: legal and government | 1366 | 1368 | o1 |
| LMArena Text: business and finance | 1356 | 1328 | MiniMax M2.5 |
| Neither model has a result on the other 5 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index7 boards, none shared
| Benchmark | MiniMax M2.5 | o1 | Leader |
|---|---|---|---|
| Design Arena: websites | 1222 | Not measured | Only MiniMax M2.5 measured |
| Design Arena: UI components | 1173 | Not measured | Only MiniMax M2.5 measured |
| Design Arena: game dev | 1176 | Not measured | Only MiniMax M2.5 measured |
| Design Arena: data viz | 1172 | Not measured | Only MiniMax M2.5 measured |
| Design Arena: 3D | 1170 | Not measured | Only MiniMax M2.5 measured |
| Design Arena: all code categories | 1207 | Not measured | Only MiniMax M2.5 measured |
| Design Arena: SVG | 1150 | Not measured | Only MiniMax M2.5 measured |
| Neither model has a result on the other 2 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index810
| Benchmark | MiniMax M2.5 | o1 | Leader |
|---|---|---|---|
| IFBench | 71.6% | 70.3% | MiniMax M2.5 |
| Long context reasoning (AA-LCR) | 73.3% | 65.0% | MiniMax M2.5 |
| DTBench | Not measured | 74.7% | Only o1 measured |
| LMCA | Not measured | 22.3% | Only o1 measured |
| Fiction.LiveBench | Not measured | 83.3% | Only o1 measured |
| Creative writing (Lech Mazur) | Not measured | 70.2% | Only o1 measured |
| CL-bench | 11.4% | Not measured | Only MiniMax M2.5 measured |
| CL-bench Life | 6.3% | Not measured | Only MiniMax M2.5 measured |
| LMArena Text | 1359 | 1366 | o1 |
| LMArena Text: instruction following | 1353 | 1367 | o1 |
| LMArena Text: creative writing | 1331 | 1347 | o1 |
| LMArena Vision | Not measured | 1168 | Only o1 measured |
| LMArena Text: English | 1380 | 1372 | MiniMax M2.5 |
| LMArena Text: non-English | 1338 | 1358 | o1 |
| LMArena Text: Chinese | 1393 | 1394 | o1 |
| LMArena Text: German | 1361 | 1337 | MiniMax M2.5 |
| LMArena Text: Japanese | 1171 | 1346 | o1 |
| LMArena Text: Korean | 1233 | 1396 | o1 |
| LMArena Text: French | 1363 | 1344 | MiniMax M2.5 |
| LMArena Text: Spanish | 1353 | 1345 | MiniMax M2.5 |
| LMArena Text: Russian | 1359 | 1356 | MiniMax M2.5 |
| LMArena Text: Polish | 1334 | Not measured | Only MiniMax M2.5 measured |
| LMArena Text: multi-turn | 1364 | 1355 | MiniMax M2.5 |
| LMArena Text: longer queries | 1366 | 1378 | o1 |
| LMArena Text: writing and language | 1345 | 1360 | o1 |
| LMArena Text: entertainment and media | 1329 | 1358 | o1 |
| LMArena Vision: English | Not measured | 1162 | Only o1 measured |
| LMArena Vision: Chinese | Not measured | 1235 | Only o1 measured |
| Neither model has a result on the other 18 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | MiniMax M2.5 | o1 | 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 M2.5 costs less
Repository review
50K input + 3K output tokens
MiniMax M2.5 costs less
Agent loop
200K input + 10K output tokens
MiniMax M2.5 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 | MiniMax M2.5 | OpenAI o1 |
|---|---|---|
| Maker | MiniMax | OpenAI |
| Weights | Open weights | No public weights listed |
| Released | February 12, 2026 | December 17, 2024 |
| Context window | 205K | 200K |
| Input $/Mtok | $0.30 | $15.00 |
| Output $/Mtok | $1.20 | $60.00 |
| Coding index | 37.2 | Not benchmarked |
| Independent measurements behind it | 3 | 0 |
| Cost per solved task | $0.62 | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is MiniMax M2.5 better than o1 for coding?
Only MiniMax M2.5 has a coding score, 37.2 on the Vibe Coding Index; o1 has none, so the two cannot be ranked on coding. Pick o1 for work measured by LMArena Text: math or LMArena Text: mathematical work, where it leads.
Which is cheaper, MiniMax M2.5 or o1?
MiniMax M2.5 costs $0.30 per million input tokens and $1.20 per million output tokens; o1 costs $15.00 and $60.00. Cost per solved task is known for MiniMax M2.5 only.
Which has the bigger context window, MiniMax M2.5 or o1?
MiniMax M2.5, with 205K tokens against 200K.
How many benchmarks is the MiniMax M2.5 vs o1 comparison based on?
43 benchmarks have a result for both models as of October 22, 2026. MiniMax M2.5's coding index rests on 3 independent benchmarks and o1's on 0. Where only one model has a result, the page says so instead of naming a winner.