MiniMax M2.5 vs Hy3
Hy3 costs 2.3x less per output token than MiniMax M2.5 ($0.528 vs $1.20 per million). Updated October 22, 2026; 42 benchmarks have a result for both.
MiniMax M2.5 or Hy3: which to pick
Only MiniMax M2.5 has a coding score, 37.2 on the Vibe Coding Index; Hy3 has none, so the two cannot be ranked on coding.
Pick Hy3 for output tokens 2.3x cheaper ($0.528 vs $1.20 per million) and a larger context window (262K against 205K tokens).
- Shared results
- 42
- MiniMax M2.5 only
- 26
- Hy3 only
- 2
- Like-for-like categories
- 6 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
No call
Only MiniMax M2.5 has a AA Intelligence Index result, 22.8.
Directional only
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
Hy3
Hy3 leads, 1230 against 1222.
Same board, both measured
Long documents
Listed context window
Hy3
Hy3 takes 262K tokens against 205K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Hy3
MiniMax M2.5 $0.0009, Hy3 $0.0004 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, Hy3 not benchmarked.
- Widest category
- Math, 16.6 points apart on average over 2 shared benchmarks.
- Widest single gap
- LMArena Text: Japanese: MiniMax M2.5 1171 against Hy3 1397, 37.6 points apart on a 0 to 100 scale.
- Output price
- MiniMax M2.5 $1.20 against Hy3 $0.528 per million output tokens, 2.3x apart.
- Context window
- MiniMax M2.5 takes 205K tokens, Hy3 262K.
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 | Hy3 | Ties |
|---|---|---|---|---|
| Coding | 0 | 6 | ||
| Reasoning | 0 | 5 | ||
| Math | 0 | 2 | ||
| Knowledge | 0 | 4 | ||
| Web design | 1 | 6 | ||
| General | 0 | 18 | ||
| All shared boards | 1 | 41 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index06
| Benchmark | MiniMax M2.5 | Hy3 | Leader |
|---|---|---|---|
| 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 | 1507 | Hy3 |
| LiveCodeBench (Vals AI) | 79.2% | Not measured | Only MiniMax M2.5 measured |
| 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 |
| SciCode | Not measured | 48.6% | Only Hy3 measured |
| Terminal-Bench Hard (Artificial Analysis run) | 34.8% | Not measured | Only MiniMax M2.5 measured |
| Terminal-Bench | 42.7% | Not measured | Only MiniMax M2.5 measured |
| ALE-Bench | 618.2 | 838.6 | Hy3 |
| LMArena Text: coding | 1380 | 1466 | Hy3 |
| LMArena Text: software and IT | 1383 | 1463 | Hy3 |
| LMArena WebDev: React | 1374 | 1511 | Hy3 |
| LMArena WebDev: HTML | 1414 | 1487 | Hy3 |
| Neither model has a result on the other 25 boards here | |||
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
| Benchmark | MiniMax M2.5 | Hy3 | Leader |
|---|---|---|---|
| AA Intelligence Index | 22.8 | Not measured | Only MiniMax M2.5 measured |
| Epoch Capabilities Index | 146.6 | Not measured | Only MiniMax M2.5 measured |
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
| Benchmark | MiniMax M2.5 | Hy3 | Leader |
|---|---|---|---|
| τ²-Bench Telecom | 95.3% | Not measured | Only MiniMax M2.5 measured |
| Vending-Bench 2 | -$23 | Not measured | Only MiniMax M2.5 measured |
| Neither model has a result on the other 39 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index05
| Benchmark | MiniMax M2.5 | Hy3 | Leader |
|---|---|---|---|
| GPQA Diamond | 82.1% | Not measured | Only MiniMax M2.5 measured |
| GPQA Diamond (Artificial Analysis run) | 84.8% | 89.7% | Hy3 |
| Humanity's Last Exam (Artificial Analysis run) | 20.5% | 33.5% | Hy3 |
| ARC-AGI | 63.7% | Not measured | Only MiniMax M2.5 measured |
| ARC-AGI-2 | 4.9% | Not measured | Only MiniMax M2.5 measured |
| LMArena Text: hard prompts | 1372 | 1447 | Hy3 |
| LMArena Text: expert | 1378 | 1461 | Hy3 |
| LMArena Text: hard prompts in English | 1384 | 1455 | Hy3 |
| Kagi LLM Benchmark | 55.2% | Not measured | Only MiniMax M2.5 measured |
| Neither model has a result on the other 13 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | MiniMax M2.5 | Hy3 | Leader |
|---|---|---|---|
| AIME | 88.8% | Not measured | Only MiniMax M2.5 measured |
| ProofBench | 4.0% | Not measured | Only MiniMax M2.5 measured |
| LMArena Text: math | 1378 | 1473 | Hy3 |
| LMArena Text: mathematical work | 1378 | 1482 | Hy3 |
| Neither model has a result on the other 9 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index04
| Benchmark | MiniMax M2.5 | Hy3 | Leader |
|---|---|---|---|
| MMLU Pro | 80.1% | Not measured | Only MiniMax M2.5 measured |
| LegalBench (Vals AI) | 80.0% | Not measured | Only MiniMax M2.5 measured |
| 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% | Not measured | Only MiniMax M2.5 measured |
| MedQA (Vals AI) | 92.5% | Not measured | Only MiniMax M2.5 measured |
| LMArena Text: science | 1369 | 1457 | Hy3 |
| LMArena Text: medicine and healthcare | 1357 | 1452 | Hy3 |
| LMArena Text: legal and government | 1366 | 1422 | Hy3 |
| LMArena Text: business and finance | 1356 | 1424 | Hy3 |
| Neither model has a result on the other 8 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index16
| Benchmark | MiniMax M2.5 | Hy3 | Leader |
|---|---|---|---|
| Design Arena: websites | 1222 | 1230 | Hy3 |
| Design Arena: UI components | 1173 | 1204 | Hy3 |
| Design Arena: game dev | 1176 | 1208 | Hy3 |
| Design Arena: data viz | 1172 | 1164 | MiniMax M2.5 |
| Design Arena: 3D | 1170 | 1232 | Hy3 |
| Design Arena: all code categories | 1207 | 1227 | Hy3 |
| Design Arena: SVG | 1150 | 1200 | Hy3 |
| Design Arena: ASCII art | Not measured | 1152 | Only Hy3 measured |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index018
| Benchmark | MiniMax M2.5 | Hy3 | Leader |
|---|---|---|---|
| IFBench | 71.6% | Not measured | Only MiniMax M2.5 measured |
| Long context reasoning (AA-LCR) | 73.3% | 79.0% | Hy3 |
| 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 | 1438 | Hy3 |
| LMArena Text: instruction following | 1353 | 1426 | Hy3 |
| LMArena Text: creative writing | 1331 | 1403 | Hy3 |
| LMArena Text: English | 1380 | 1448 | Hy3 |
| LMArena Text: non-English | 1338 | 1426 | Hy3 |
| LMArena Text: Chinese | 1393 | 1485 | Hy3 |
| LMArena Text: German | 1361 | 1449 | Hy3 |
| LMArena Text: Japanese | 1171 | 1397 | Hy3 |
| LMArena Text: Korean | 1233 | 1396 | Hy3 |
| LMArena Text: French | 1363 | 1456 | Hy3 |
| LMArena Text: Spanish | 1353 | 1457 | Hy3 |
| LMArena Text: Russian | 1359 | 1432 | Hy3 |
| LMArena Text: Polish | 1334 | 1447 | Hy3 |
| LMArena Text: multi-turn | 1364 | 1436 | Hy3 |
| LMArena Text: longer queries | 1366 | 1442 | Hy3 |
| LMArena Text: writing and language | 1345 | 1414 | Hy3 |
| LMArena Text: entertainment and media | 1329 | 1400 | Hy3 |
| Neither model has a result on the other 25 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | MiniMax M2.5 | Hy3 | 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
Hy3 costs less
Repository review
50K input + 3K output tokens
Hy3 costs less
Agent loop
200K input + 10K output tokens
Hy3 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 | Tencent Hy3 |
|---|---|---|
| Maker | MiniMax | Tencent |
| Weights | Open weights | Open weights |
| Released | February 12, 2026 | July 6, 2026 |
| Context window | 205K | 262K |
| Input $/Mtok | $0.30 | $0.132 |
| Output $/Mtok | $1.20 | $0.528 |
| Coding index | 37.2 | Not benchmarked |
| Independent measurements behind it | 3 | 1 |
| Cost per solved task | $0.62 | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is MiniMax M2.5 better than Hy3 for coding?
Only MiniMax M2.5 has a coding score, 37.2 on the Vibe Coding Index; Hy3 has none, so the two cannot be ranked on coding. Pick Hy3 for output tokens 2.3x cheaper ($0.528 vs $1.20 per million) and a larger context window (262K against 205K tokens).
Which is cheaper, MiniMax M2.5 or Hy3?
MiniMax M2.5 costs $0.30 per million input tokens and $1.20 per million output tokens; Hy3 costs $0.132 and $0.528. Cost per solved task is known for MiniMax M2.5 only.
Which has the bigger context window, MiniMax M2.5 or Hy3?
Hy3, with 262K tokens against 205K.
How many benchmarks is the MiniMax M2.5 vs Hy3 comparison based on?
42 benchmarks have a result for both models as of October 22, 2026. MiniMax M2.5's coding index rests on 3 independent benchmarks and Hy3's on 1. Where only one model has a result, the page says so instead of naming a winner.