MiniMax M2.5 vs Beam 1.0 501B A23B
Updated October 21, 2026. 28 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 M2.5 for coding: it scores 59.4 on the Vibe Coding Index against 33.8 for Beam 1.0 501B A23B.
Pick Beam 1.0 501B A23B when the context window is larger, 1.05M against 205K tokens, or when what matters is LMArena WebDev or LMArena Text: coding, where it leads.
- Shared results
- 28
- MiniMax M2.5 only
- 39
- Beam 1.0 501B A23B only
- 0
- Like-for-like categories
- 6 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 M2.5
MiniMax M2.5 scores 59.4 against 33.8.
2 and 1 benchmarks behind the scores
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
Beam 1.0 501B A23B
Beam 1.0 501B A23B leads, 1253 against 1222.
Same board, both measured
Long documents
Listed context window
Beam 1.0 501B A23B
Beam 1.0 501B A23B takes 1.05M tokens against 205K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
MiniMax M2.5
MiniMax M2.5 $0.0007, Beam 1.0 501B A23B $0.0008 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 59.4 from 2 benchmarks, Beam 1.0 501B A23B 33.8 from 1 benchmark.
- Widest category
- Math, 14.8 points apart on average over 2 shared benchmarks.
- Widest single gap
- LMArena Text: French: MiniMax M2.5 1363 against Beam 1.0 501B A23B 1461, 16.4 points apart on a 0 to 100 scale.
- Output price
- MiniMax M2.5 $0.95 against Beam 1.0 501B A23B $1.00 per million output tokens, 1.1x apart.
- Context window
- MiniMax M2.5 takes 205K tokens, Beam 1.0 501B A23B 1.05M.
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 | Beam 1.0 501B A23B | Ties |
|---|---|---|---|---|
| Coding | 0 | 5 | ||
| Reasoning | 0 | 3 | ||
| Math | 0 | 2 | ||
| Knowledge | 0 | 4 | ||
| Web design | 0 | 2 | ||
| General | 0 | 12 | ||
| All shared boards | 0 | 28 |
CodingLike-for-likeFour of these boards feed the Vibe Coding Index05
| Benchmark | MiniMax M2.5 | Beam 1.0 501B A23B | 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 | 1437 | Beam 1.0 501B A23B |
| 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 |
| 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 | Not measured | Only MiniMax M2.5 measured |
| LMArena Text: coding | 1380 | 1473 | Beam 1.0 501B A23B |
| LMArena Text: software and IT | 1383 | 1461 | Beam 1.0 501B A23B |
| LMArena WebDev: React | 1374 | 1443 | Beam 1.0 501B A23B |
| LMArena WebDev: HTML | 1414 | 1436 | Beam 1.0 501B A23B |
| 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 | Beam 1.0 501B A23B | 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 | Beam 1.0 501B A23B | 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 37 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index03
| Benchmark | MiniMax M2.5 | Beam 1.0 501B A23B | Leader |
|---|---|---|---|
| GPQA Diamond | 82.1% | Not measured | Only MiniMax M2.5 measured |
| GPQA Diamond (Artificial Analysis run) | 84.8% | Not measured | Only MiniMax M2.5 measured |
| Humanity's Last Exam (Artificial Analysis run) | 20.5% | Not measured | Only MiniMax M2.5 measured |
| 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 | 1442 | Beam 1.0 501B A23B |
| LMArena Text: expert | 1378 | 1447 | Beam 1.0 501B A23B |
| LMArena Text: hard prompts in English | 1384 | 1451 | Beam 1.0 501B A23B |
| 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 | Beam 1.0 501B A23B | 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 | 1459 | Beam 1.0 501B A23B |
| LMArena Text: mathematical work | 1378 | 1475 | Beam 1.0 501B A23B |
| 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 | Beam 1.0 501B A23B | 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 | 1430 | Beam 1.0 501B A23B |
| LMArena Text: medicine and healthcare | 1357 | 1376 | Beam 1.0 501B A23B |
| LMArena Text: legal and government | 1366 | 1433 | Beam 1.0 501B A23B |
| LMArena Text: business and finance | 1356 | 1430 | Beam 1.0 501B A23B |
| Neither model has a result on the other 7 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | MiniMax M2.5 | Beam 1.0 501B A23B | Leader |
|---|---|---|---|
| Design Arena: websites | 1222 | 1253 | Beam 1.0 501B A23B |
| Design Arena: UI components | 1172 | Not measured | Only MiniMax M2.5 measured |
| Design Arena: game dev | 1176 | 1222 | Beam 1.0 501B A23B |
| Design Arena: data viz | 1171 | 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 | 1147 | 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 index012
| Benchmark | MiniMax M2.5 | Beam 1.0 501B A23B | Leader |
|---|---|---|---|
| IFBench | 71.6% | Not measured | Only MiniMax M2.5 measured |
| Long context reasoning (AA-LCR) | 73.3% | Not measured | Only MiniMax M2.5 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 | 1425 | Beam 1.0 501B A23B |
| LMArena Text: instruction following | 1353 | 1430 | Beam 1.0 501B A23B |
| LMArena Text: creative writing | 1331 | 1390 | Beam 1.0 501B A23B |
| LMArena Text: English | 1380 | 1436 | Beam 1.0 501B A23B |
| LMArena Text: non-English | 1338 | 1413 | Beam 1.0 501B A23B |
| LMArena Text: Chinese | 1393 | 1424 | Beam 1.0 501B A23B |
| LMArena Text: German | 1361 | Not measured | Only MiniMax M2.5 measured |
| LMArena Text: Japanese | 1171 | Not measured | Only MiniMax M2.5 measured |
| LMArena Text: Korean | 1233 | Not measured | Only MiniMax M2.5 measured |
| LMArena Text: French | 1363 | 1461 | Beam 1.0 501B A23B |
| LMArena Text: Spanish | 1353 | Not measured | Only MiniMax M2.5 measured |
| LMArena Text: Russian | 1359 | 1412 | Beam 1.0 501B A23B |
| LMArena Text: Polish | 1334 | Not measured | Only MiniMax M2.5 measured |
| LMArena Text: multi-turn | 1364 | 1414 | Beam 1.0 501B A23B |
| LMArena Text: longer queries | 1366 | 1429 | Beam 1.0 501B A23B |
| LMArena Text: writing and language | 1345 | 1400 | Beam 1.0 501B A23B |
| LMArena Text: entertainment and media | 1329 | 1399 | Beam 1.0 501B A23B |
| 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 | Beam 1.0 501B A23B | 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 | Reflection Beam 1.0 501B A23B |
|---|---|---|
| Maker | MiniMax | Reflection |
| Weights | Open weights | Open weights |
| Released | February 12, 2026 | October 16, 2026 |
| Context window | 205K | 1.05M |
| Input $/Mtok | $0.27 | $0.30 |
| Output $/Mtok | $0.95 | $1.00 |
| Coding index | 59.4 | 33.8 |
| Independent measurements behind it | 2 | 1 |
| Cost per solved task | $0.62 | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is MiniMax M2.5 better than Beam 1.0 501B A23B for coding?
Pick MiniMax M2.5 for coding: it scores 59.4 on the Vibe Coding Index against 33.8 for Beam 1.0 501B A23B. Pick Beam 1.0 501B A23B when the context window is larger, 1.05M against 205K tokens, or when what matters is LMArena WebDev or LMArena Text: coding, where it leads.
Which is cheaper, MiniMax M2.5 or Beam 1.0 501B A23B?
MiniMax M2.5 costs $0.27 per million input tokens and $0.95 per million output tokens; Beam 1.0 501B A23B costs $0.30 and $1.00. Cost per solved task is known for MiniMax M2.5 only.
Which has the bigger context window, MiniMax M2.5 or Beam 1.0 501B A23B?
Beam 1.0 501B A23B, with 1.05M tokens against 205K.
How many benchmarks is the MiniMax M2.5 vs Beam 1.0 501B A23B comparison based on?
28 benchmarks have a result for both models as of October 21, 2026. MiniMax M2.5's coding index rests on 2 independent benchmarks and Beam 1.0 501B A23B's on 1. Where only one model has a result, the page says so instead of naming a winner.