DeepSeek V3.2 Exp vs MiniMax M2.5
MiniMax M2.5 leads DeepSeek V3.2 Exp on the Artificial Analysis Intelligence Index, 22.8 to 16.6, and DeepSeek V3.2 Exp costs 2.9x less per output token ($0.41 vs $1.20 per million). Updated October 22, 2026; 48 benchmarks have a result for both.
DeepSeek V3.2 Exp or MiniMax M2.5: which to pick
Only MiniMax M2.5 has a coding score, 37.2 on the Vibe Coding Index; DeepSeek V3.2 Exp has none, so the two cannot be ranked on coding.
Pick DeepSeek V3.2 Exp for output tokens 2.9x cheaper ($0.41 vs $1.20 per million) and work measured by LMArena Text: coding or LMArena Text: software and IT, where it leads.
- Shared results
- 48
- DeepSeek V3.2 Exp only
- 11
- MiniMax M2.5 only
- 20
- Like-for-like categories
- 8 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 16.6.
Same board, both measured
Reasoning
GPQA Diamond
No call
Only MiniMax M2.5 has a GPQA Diamond result, 82.1%.
Directional only
Math
AIME
No call
Only MiniMax M2.5 has a AIME result, 88.8%.
Directional only
Knowledge
MMLU Pro
No call
Only MiniMax M2.5 has a MMLU Pro result, 80.1%.
Directional only
Web design
Design Arena: websites
MiniMax M2.5
MiniMax M2.5 leads, 1222 against 1179.
Same board, both measured
Long documents
Listed context window
MiniMax M2.5
MiniMax M2.5 takes 205K tokens against 164K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
DeepSeek V3.2 Exp
DeepSeek V3.2 Exp $0.0005, MiniMax M2.5 $0.0009 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
- DeepSeek V3.2 Exp not benchmarked, MiniMax M2.5 37.2 from 3 benchmarks.
- Widest category
- Agentic work, 61.4 points apart on average over 1 shared benchmark.
- Widest single gap
- τ²-Bench Telecom: DeepSeek V3.2 Exp 33.9% against MiniMax M2.5 95.3%, 61.4 points apart on a 0 to 100 scale.
- Output price
- DeepSeek V3.2 Exp $0.41 against MiniMax M2.5 $1.20 per million output tokens, 2.9x apart.
- Context window
- DeepSeek V3.2 Exp takes 164K tokens, MiniMax M2.5 205K.
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 | DeepSeek V3.2 Exp | Bars | MiniMax M2.5 | Ties |
|---|---|---|---|---|
| Coding | 2 | 3 | ||
| Intelligence | 0 | 2 | ||
| Agentic work | 0 | 1 | ||
| Reasoning | 3 | 3 | ||
| Math | 2 | 0 | ||
| Knowledge | 4 | 0 | ||
| Web design | 0 | 7 | ||
| General | 19 | 2 | ||
| All shared boards | 30 | 18 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index23
| Benchmark | DeepSeek V3.2 Exp | MiniMax M2.5 | Leader |
|---|---|---|---|
| Aider polyglot | 74.2% | Not measured | Only DeepSeek V3.2 Exp measured |
| SWE-bench Verified | Not measured | 75.8% | Only MiniMax M2.5 measured |
| SWE-bench Multilingual | Not measured | 68.3% | Only MiniMax M2.5 measured |
| LMArena WebDev | 1272 | 1386 | MiniMax M2.5 |
| LiveCodeBench (Vals AI) | Not measured | 79.2% | Only MiniMax M2.5 measured |
| SWE-bench Verified (Vals AI) | Not measured | 74.2% | Only MiniMax M2.5 measured |
| Vibe Code Bench (Vals AI) | Not measured | 14.8% | Only MiniMax M2.5 measured |
| LiveCodeBench (Artificial Analysis run) | 78.9% | Not measured | Only DeepSeek V3.2 Exp measured |
| Terminal-Bench Hard (Artificial Analysis run) | 31.1% | 34.8% | MiniMax M2.5 |
| Terminal-Bench | Not measured | 42.7% | Only MiniMax M2.5 measured |
| WeirdML | 39.5% | Not measured | Only DeepSeek V3.2 Exp measured |
| ALE-Bench | Not measured | 618.2 | Only MiniMax M2.5 measured |
| LMArena Text: coding | 1438 | 1380 | DeepSeek V3.2 Exp |
| LMArena Text: software and IT | 1438 | 1383 | DeepSeek V3.2 Exp |
| LMArena WebDev: React | Not measured | 1374 | Only MiniMax M2.5 measured |
| LMArena WebDev: HTML | 1281 | 1414 | MiniMax M2.5 |
| Neither model has a result on the other 23 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | DeepSeek V3.2 Exp | MiniMax M2.5 | Leader |
|---|---|---|---|
| AA Intelligence Index | 16.6 | 22.8 | MiniMax M2.5 |
| Epoch Capabilities Index | 144.9 | 146.6 | MiniMax M2.5 |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | DeepSeek V3.2 Exp | MiniMax M2.5 | Leader |
|---|---|---|---|
| τ²-Bench Telecom | 33.9% | 95.3% | MiniMax M2.5 |
| TheAgentCompany | 42.9% | Not measured | Only DeepSeek V3.2 Exp measured |
| Vending-Bench 2 | Not measured | -$23 | Only MiniMax M2.5 measured |
| Berkeley Function Calling Leaderboard (BFCL) | 56.7% | Not measured | Only DeepSeek V3.2 Exp measured |
| Neither model has a result on the other 37 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index33
| Benchmark | DeepSeek V3.2 Exp | MiniMax M2.5 | Leader |
|---|---|---|---|
| GPQA Diamond | Not measured | 82.1% | Only MiniMax M2.5 measured |
| GPQA Diamond (Artificial Analysis run) | 79.7% | 84.8% | MiniMax M2.5 |
| Humanity's Last Exam (Artificial Analysis run) | 14.9% | 20.5% | MiniMax M2.5 |
| ARC-AGI | Not measured | 63.7% | Only MiniMax M2.5 measured |
| ARC-AGI-2 | Not measured | 4.9% | Only MiniMax M2.5 measured |
| LMArena Text: hard prompts | 1429 | 1372 | DeepSeek V3.2 Exp |
| LMArena Text: expert | 1422 | 1378 | DeepSeek V3.2 Exp |
| LMArena Text: hard prompts in English | 1444 | 1384 | DeepSeek V3.2 Exp |
| Kagi LLM Benchmark | 52.2% | 55.2% | MiniMax M2.5 |
| Neither model has a result on the other 13 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | DeepSeek V3.2 Exp | MiniMax M2.5 | Leader |
|---|---|---|---|
| AIME | Not measured | 88.8% | Only MiniMax M2.5 measured |
| AA Math Index | 87.7 | Not measured | Only DeepSeek V3.2 Exp measured |
| AIME 2025 (Artificial Analysis run) | 87.7% | Not measured | Only DeepSeek V3.2 Exp measured |
| ProofBench | Not measured | 4.0% | Only MiniMax M2.5 measured |
| LMArena Text: math | 1422 | 1378 | DeepSeek V3.2 Exp |
| LMArena Text: mathematical work | 1433 | 1378 | DeepSeek V3.2 Exp |
| Neither model has a result on the other 7 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index40
| Benchmark | DeepSeek V3.2 Exp | MiniMax M2.5 | Leader |
|---|---|---|---|
| MMLU Pro | Not measured | 80.1% | Only MiniMax M2.5 measured |
| LegalBench (Vals AI) | Not measured | 80.0% | Only MiniMax M2.5 measured |
| CaseLaw (Vals AI) | Not measured | 53.5% | Only MiniMax M2.5 measured |
| CorpFin (Vals AI) | Not measured | 59.6% | Only MiniMax M2.5 measured |
| TaxEval (Vals AI) | Not measured | 68.2% | Only MiniMax M2.5 measured |
| MedQA (Vals AI) | Not measured | 92.5% | Only MiniMax M2.5 measured |
| MMLU Pro (Artificial Analysis run) | 85.0% | Not measured | Only DeepSeek V3.2 Exp measured |
| LMArena Text: science | 1443 | 1369 | DeepSeek V3.2 Exp |
| LMArena Text: medicine and healthcare | 1468 | 1357 | DeepSeek V3.2 Exp |
| LMArena Text: legal and government | 1419 | 1366 | DeepSeek V3.2 Exp |
| LMArena Text: business and finance | 1412 | 1356 | DeepSeek V3.2 Exp |
| Neither model has a result on the other 7 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index07
| Benchmark | DeepSeek V3.2 Exp | MiniMax M2.5 | Leader |
|---|---|---|---|
| Design Arena: websites | 1179 | 1222 | MiniMax M2.5 |
| Design Arena: UI components | 1164 | 1170 | MiniMax M2.5 |
| Design Arena: game dev | 1144 | 1176 | MiniMax M2.5 |
| Design Arena: data viz | 1152 | 1172 | MiniMax M2.5 |
| Design Arena: 3D | 1148 | 1170 | MiniMax M2.5 |
| Design Arena: all code categories | 1170 | 1207 | MiniMax M2.5 |
| Design Arena: SVG | 1031 | 1150 | MiniMax M2.5 |
| Neither model has a result on the other 2 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index192
| Benchmark | DeepSeek V3.2 Exp | MiniMax M2.5 | Leader |
|---|---|---|---|
| IFBench | 54.1% | 71.6% | MiniMax M2.5 |
| Long context reasoning (AA-LCR) | 72.3% | 73.3% | MiniMax M2.5 |
| DTBench | 87.7% | Not measured | Only DeepSeek V3.2 Exp measured |
| LMCA | 29.1% | Not measured | Only DeepSeek V3.2 Exp measured |
| Fiction.LiveBench | 83.3% | Not measured | Only DeepSeek V3.2 Exp measured |
| CL-bench | 13.2% | 11.4% | DeepSeek V3.2 Exp |
| CL-bench Life | 9.5% | 6.3% | DeepSeek V3.2 Exp |
| LMArena Text | 1425 | 1359 | DeepSeek V3.2 Exp |
| LMArena Text: instruction following | 1401 | 1353 | DeepSeek V3.2 Exp |
| LMArena Text: creative writing | 1404 | 1331 | DeepSeek V3.2 Exp |
| LMArena Text: English | 1441 | 1380 | DeepSeek V3.2 Exp |
| LMArena Text: non-English | 1404 | 1338 | DeepSeek V3.2 Exp |
| LMArena Text: Chinese | 1461 | 1393 | DeepSeek V3.2 Exp |
| LMArena Text: German | 1440 | 1361 | DeepSeek V3.2 Exp |
| LMArena Text: Japanese | 1331 | 1171 | DeepSeek V3.2 Exp |
| LMArena Text: Korean | 1372 | 1233 | DeepSeek V3.2 Exp |
| LMArena Text: French | 1434 | 1363 | DeepSeek V3.2 Exp |
| LMArena Text: Spanish | 1441 | 1353 | DeepSeek V3.2 Exp |
| LMArena Text: Russian | 1412 | 1359 | DeepSeek V3.2 Exp |
| LMArena Text: Polish | 1435 | 1334 | DeepSeek V3.2 Exp |
| LMArena Text: multi-turn | 1422 | 1364 | DeepSeek V3.2 Exp |
| LMArena Text: longer queries | 1418 | 1366 | DeepSeek V3.2 Exp |
| LMArena Text: writing and language | 1407 | 1345 | DeepSeek V3.2 Exp |
| LMArena Text: entertainment and media | 1407 | 1329 | DeepSeek V3.2 Exp |
| Neither model has a result on the other 22 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | DeepSeek V3.2 Exp | MiniMax M2.5 | 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
DeepSeek V3.2 Exp costs less
Repository review
50K input + 3K output tokens
DeepSeek V3.2 Exp costs less
Agent loop
200K input + 10K output tokens
DeepSeek V3.2 Exp 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 | DeepSeek V3.2 Exp | MiniMax M2.5 |
|---|---|---|
| Maker | DeepSeek | MiniMax |
| Weights | Open weights | Open weights |
| Released | September 29, 2025 | February 12, 2026 |
| Context window | 164K | 205K |
| Input $/Mtok | $0.27 | $0.30 |
| Output $/Mtok | $0.41 | $1.20 |
| Coding index | Not benchmarked | 37.2 |
| Independent measurements behind it | 1 | 3 |
| Cost per solved task | Not computable | $0.62 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is DeepSeek V3.2 Exp better than MiniMax M2.5 for coding?
Only MiniMax M2.5 has a coding score, 37.2 on the Vibe Coding Index; DeepSeek V3.2 Exp has none, so the two cannot be ranked on coding. Pick DeepSeek V3.2 Exp for output tokens 2.9x cheaper ($0.41 vs $1.20 per million) and work measured by LMArena Text: coding or LMArena Text: software and IT, where it leads.
Which is cheaper, DeepSeek V3.2 Exp or MiniMax M2.5?
DeepSeek V3.2 Exp costs $0.27 per million input tokens and $0.41 per million output tokens; MiniMax M2.5 costs $0.30 and $1.20. Cost per solved task is known for MiniMax M2.5 only.
Which has the bigger context window, DeepSeek V3.2 Exp or MiniMax M2.5?
MiniMax M2.5, with 205K tokens against 164K.
How many benchmarks is the DeepSeek V3.2 Exp vs MiniMax M2.5 comparison based on?
48 benchmarks have a result for both models as of October 22, 2026. DeepSeek V3.2 Exp's coding index rests on 1 independent benchmark and MiniMax M2.5's on 3. Where only one model has a result, the page says so instead of naming a winner.