Claude Haiku 4.5 vs MiniMax M2.5
Updated October 21, 2026. 57 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 49.8 for Claude Haiku 4.5, though on 2 benchmarks against 3.
Pick Claude Haiku 4.5 when a solved task costs $0.56 against $0.62, or when what matters is LMArena Text: coding or LMArena Text: software and IT, where it leads.
- Shared results
- 57
- Claude Haiku 4.5 only
- 37
- MiniMax M2.5 only
- 10
- Like-for-like categories
- 8 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 49.8.
3 and 2 benchmarks behind the scores
Intelligence
AA Intelligence Index
MiniMax M2.5
MiniMax M2.5 leads, 22.8 against 16.9.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only Claude Haiku 4.5 has a AA Agentic Index result, 8.0.
Directional only
Reasoning
GPQA Diamond
MiniMax M2.5
MiniMax M2.5 leads, 82.1% against 72.2%.
Same board, both measured
Math
AIME
MiniMax M2.5
MiniMax M2.5 leads, 88.8% against 82.7%.
Same board, both measured
Knowledge
MMLU Pro
MiniMax M2.5
MiniMax M2.5 leads, 80.1% against 78.7%.
Same board, both measured
Web design
Design Arena: websites
MiniMax M2.5
MiniMax M2.5 leads, 1222 against 1122.
Same board, both measured
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
Claude Haiku 4.5 $0.0035, MiniMax M2.5 $0.0007 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
Claude Haiku 4.5
Claude Haiku 4.5 $0.56, MiniMax M2.5 $0.62.
Published attempt cost and pass rate
At a glance
- Coding index
- Claude Haiku 4.5 49.8 from 3 benchmarks, MiniMax M2.5 59.4 from 2 benchmarks.
- Widest category
- Coding, 11.1 points apart on average over 11 shared benchmarks.
- Widest single gap
- LiveCodeBench (Vals AI): Claude Haiku 4.5 41.2% against MiniMax M2.5 79.2%, 38.0 points apart on a 0 to 100 scale.
- Output price
- Claude Haiku 4.5 $5.00 against MiniMax M2.5 $0.95 per million output tokens, 5.3x apart.
- Context window
- Claude Haiku 4.5 takes 200K 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 | Claude Haiku 4.5 | Bars | MiniMax M2.5 | Ties |
|---|---|---|---|---|
| Coding | 2 | 9 | ||
| Intelligence | 0 | 2 | ||
| Agentic work | 1 | 0 | ||
| Reasoning | 3 | 3 | ||
| Math | 2 | 1 | ||
| Knowledge | 7 | 3 | ||
| Web design | 0 | 7 | ||
| General | 17 | 0 | ||
| All shared boards | 32 | 25 |
CodingLike-for-likeFour of these boards feed the Vibe Coding Index29
| Benchmark | Claude Haiku 4.5 | MiniMax M2.5 | Leader |
|---|---|---|---|
| SWE-bench Verified | 66.6% | 75.8% | MiniMax M2.5 |
| SWE-bench Multilingual | 64.7% | 68.3% | MiniMax M2.5 |
| LiveBench coding | 48.1% | Not measured | Only Claude Haiku 4.5 measured |
| LMArena WebDev | 1330 | 1386 | MiniMax M2.5 |
| AA Coding Index | 43.9 | Not measured | Only Claude Haiku 4.5 measured |
| LiveCodeBench (Vals AI) | 41.2% | 79.2% | MiniMax M2.5 |
| SWE-bench Verified (Vals AI) | 66.6% | 74.2% | MiniMax M2.5 |
| Vibe Code Bench (Vals AI) | 11.4% | 14.8% | MiniMax M2.5 |
| Code migration (Vals AI) | 7.5% | Not measured | Only Claude Haiku 4.5 measured |
| ProgramBench (Vals AI) | 0.0% | Not measured | Only Claude Haiku 4.5 measured |
| Terminal-Bench 2.1 (Vals AI) | 43.8% | Not measured | Only Claude Haiku 4.5 measured |
| Terminal-Bench Hard (Artificial Analysis run) | Not measured | 34.8% | Only MiniMax M2.5 measured |
| Terminal-Bench | 35.5% | 42.7% | MiniMax M2.5 |
| WeirdML | 45.4% | Not measured | Only Claude Haiku 4.5 measured |
| ALE-Bench | Not measured | 618.2 | Only MiniMax M2.5 measured |
| LMArena Text: coding | 1454 | 1380 | Claude Haiku 4.5 |
| LMArena Text: software and IT | 1439 | 1383 | Claude Haiku 4.5 |
| LMArena WebDev: React | 1326 | 1374 | MiniMax M2.5 |
| LMArena WebDev: HTML | 1318 | 1414 | MiniMax M2.5 |
| Neither model has a result on the other 19 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | Claude Haiku 4.5 | MiniMax M2.5 | Leader |
|---|---|---|---|
| AA Intelligence Index | 16.9 | 22.8 | MiniMax M2.5 |
| Epoch Capabilities Index | 142.2 | 146.6 | MiniMax M2.5 |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Claude Haiku 4.5 | MiniMax M2.5 | Leader |
|---|---|---|---|
| AA Agentic Index | 8.0 | Not measured | Only Claude Haiku 4.5 measured |
| LiveBench research | 42.2% | Not measured | Only Claude Haiku 4.5 measured |
| LiveBench browser | 40.0% | Not measured | Only Claude Haiku 4.5 measured |
| LiveBench long agentic | 11.1% | Not measured | Only Claude Haiku 4.5 measured |
| Finance Agent (Vals AI) | 31.0% | Not measured | Only Claude Haiku 4.5 measured |
| Tax Agent Bench (Vals AI) | 5.9% | Not measured | Only Claude Haiku 4.5 measured |
| Legal Research Bench (Vals AI) | 10.6% | Not measured | Only Claude Haiku 4.5 measured |
| Excel Modeling Benchmark (Vals AI) | 22.7% | Not measured | Only Claude Haiku 4.5 measured |
| τ²-Bench Telecom | Not measured | 95.3% | Only MiniMax M2.5 measured |
| BALROG | 31.2% | Not measured | Only Claude Haiku 4.5 measured |
| DeepResearch Bench | 45.5% | Not measured | Only Claude Haiku 4.5 measured |
| Vending-Bench 2 | $459 | -$23 | Claude Haiku 4.5 |
| Neither model has a result on the other 27 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index33
| Benchmark | Claude Haiku 4.5 | MiniMax M2.5 | Leader |
|---|---|---|---|
| GPQA Diamond | 72.2% | 82.1% | MiniMax M2.5 |
| LiveBench reasoning | 61.7% | Not measured | Only Claude Haiku 4.5 measured |
| MMMU Pro (Vals AI) | 46.1% | Not measured | Only Claude Haiku 4.5 measured |
| GPQA Diamond (Artificial Analysis run) | Not measured | 84.8% | Only MiniMax M2.5 measured |
| Humanity's Last Exam (Artificial Analysis run) | Not measured | 20.5% | Only MiniMax M2.5 measured |
| GPQA Diamond (Epoch AI run) | 71.2% | Not measured | Only Claude Haiku 4.5 measured |
| ARC-AGI | 47.7% | 63.7% | MiniMax M2.5 |
| ARC-AGI-2 | 4.0% | 4.9% | MiniMax M2.5 |
| Chess puzzles | 8.0% | Not measured | Only Claude Haiku 4.5 measured |
| LMArena Text: hard prompts | 1421 | 1372 | Claude Haiku 4.5 |
| LMArena Text: expert | 1443 | 1378 | Claude Haiku 4.5 |
| LMArena Text: hard prompts in English | 1435 | 1384 | Claude Haiku 4.5 |
| Neither model has a result on the other 9 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index21
| Benchmark | Claude Haiku 4.5 | MiniMax M2.5 | Leader |
|---|---|---|---|
| AIME | 82.7% | 88.8% | MiniMax M2.5 |
| MGSM (Vals AI) | 92.2% | Not measured | Only Claude Haiku 4.5 measured |
| OTIS Mock AIME | 66.7% | Not measured | Only Claude Haiku 4.5 measured |
| ProofBench | Not measured | 4.0% | Only MiniMax M2.5 measured |
| MATH level 5 | 96.4% | Not measured | Only Claude Haiku 4.5 measured |
| LMArena Text: math | 1398 | 1378 | Claude Haiku 4.5 |
| LMArena Text: mathematical work | 1430 | 1378 | Claude Haiku 4.5 |
| Neither model has a result on the other 6 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index73
| Benchmark | Claude Haiku 4.5 | MiniMax M2.5 | Leader |
|---|---|---|---|
| MMLU Pro | 78.7% | 80.1% | MiniMax M2.5 |
| LegalBench (Vals AI) | 81.2% | 80.0% | Claude Haiku 4.5 |
| CaseLaw (Vals AI) | 56.5% | 53.5% | Claude Haiku 4.5 |
| CorpFin (Vals AI) | 60.6% | 59.6% | Claude Haiku 4.5 |
| TaxEval (Vals AI) | 67.5% | 68.2% | MiniMax M2.5 |
| MortgageTax (Vals AI) | 62.2% | Not measured | Only Claude Haiku 4.5 measured |
| MedQA (Vals AI) | 79.6% | 92.5% | MiniMax M2.5 |
| MedCode (Vals AI) | 32.7% | Not measured | Only Claude Haiku 4.5 measured |
| SimpleQA Verified | 13.2% | Not measured | Only Claude Haiku 4.5 measured |
| LMArena Text: science | 1406 | 1369 | Claude Haiku 4.5 |
| LMArena Text: medicine and healthcare | 1394 | 1357 | Claude Haiku 4.5 |
| LMArena Text: legal and government | 1400 | 1366 | Claude Haiku 4.5 |
| LMArena Text: business and finance | 1400 | 1356 | Claude Haiku 4.5 |
| Neither model has a result on the other 4 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index07
| Benchmark | Claude Haiku 4.5 | MiniMax M2.5 | Leader |
|---|---|---|---|
| Design Arena: websites | 1122 | 1222 | MiniMax M2.5 |
| Design Arena: UI components | 1100 | 1172 | MiniMax M2.5 |
| Design Arena: game dev | 1097 | 1176 | MiniMax M2.5 |
| Design Arena: data viz | 1124 | 1171 | MiniMax M2.5 |
| Design Arena: 3D | 1072 | 1170 | MiniMax M2.5 |
| Design Arena: all code categories | 1115 | 1207 | MiniMax M2.5 |
| Design Arena: SVG | 1025 | 1147 | MiniMax M2.5 |
| Design Arena: ASCII art | 1139 | Not measured | Only Claude Haiku 4.5 measured |
| LiveBench design | 59.9% | Not measured | Only Claude Haiku 4.5 measured |
GeneralLike-for-likePublic boards, shown as published, kept out of the index170
| Benchmark | Claude Haiku 4.5 | MiniMax M2.5 | Leader |
|---|---|---|---|
| LiveBench data analysis | 59.3% | Not measured | Only Claude Haiku 4.5 measured |
| Public Benefits Bench (Vals AI) | 54.3% | Not measured | Only Claude Haiku 4.5 measured |
| SAGE (Vals AI) | 31.8% | Not measured | Only Claude Haiku 4.5 measured |
| MedScribe (Vals AI) | 85.2% | Not measured | Only Claude Haiku 4.5 measured |
| Vals Multimodal Index | 42.9% | Not measured | Only Claude Haiku 4.5 measured |
| IFBench | Not measured | 71.6% | Only MiniMax M2.5 measured |
| Long context reasoning (AA-LCR) | Not measured | 73.3% | Only MiniMax M2.5 measured |
| DTBench | 73.6% | Not measured | Only Claude Haiku 4.5 measured |
| LMCA | 30.9% | Not measured | Only Claude Haiku 4.5 measured |
| CL-bench | Not measured | 11.4% | Only MiniMax M2.5 measured |
| ExploitBench | 13.7% | Not measured | Only Claude Haiku 4.5 measured |
| CL-bench Life | Not measured | 6.3% | Only MiniMax M2.5 measured |
| LMArena Text | 1397 | 1359 | Claude Haiku 4.5 |
| LMArena Text: instruction following | 1414 | 1353 | Claude Haiku 4.5 |
| LMArena Text: creative writing | 1371 | 1331 | Claude Haiku 4.5 |
| LMArena Text: English | 1414 | 1380 | Claude Haiku 4.5 |
| LMArena Text: non-English | 1377 | 1338 | Claude Haiku 4.5 |
| LMArena Text: Chinese | 1418 | 1393 | Claude Haiku 4.5 |
| LMArena Text: German | 1374 | 1361 | Claude Haiku 4.5 |
| LMArena Text: Japanese | 1338 | 1171 | Claude Haiku 4.5 |
| LMArena Text: Korean | 1346 | 1233 | Claude Haiku 4.5 |
| LMArena Text: French | 1411 | 1363 | Claude Haiku 4.5 |
| LMArena Text: Spanish | 1421 | 1353 | Claude Haiku 4.5 |
| LMArena Text: Russian | 1381 | 1359 | Claude Haiku 4.5 |
| LMArena Text: Polish | 1343 | 1334 | Claude Haiku 4.5 |
| LMArena Text: multi-turn | 1409 | 1364 | Claude Haiku 4.5 |
| LMArena Text: longer queries | 1427 | 1366 | Claude Haiku 4.5 |
| LMArena Text: writing and language | 1386 | 1345 | Claude Haiku 4.5 |
| LMArena Text: entertainment and media | 1369 | 1329 | Claude Haiku 4.5 |
| LMArena Document | 1420 | Not measured | Only Claude Haiku 4.5 measured |
| Neither model has a result on the other 16 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Claude Haiku 4.5 | 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
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 | Anthropic Claude Haiku 4.5 | MiniMax M2.5 |
|---|---|---|
| Maker | Anthropic | MiniMax |
| Weights | No public weights listed | Open weights |
| Released | October 15, 2025 | February 12, 2026 |
| Context window | 200K | 205K |
| Input $/Mtok | $1.00 | $0.27 |
| Output $/Mtok | $5.00 | $0.95 |
| Coding index | 49.8 | 59.4 |
| Independent measurements behind it | 3 | 2 |
| Cost per solved task | $0.56 | $0.62 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Claude Haiku 4.5 better than MiniMax M2.5 for coding?
Pick MiniMax M2.5 for coding: it scores 59.4 on the Vibe Coding Index against 49.8 for Claude Haiku 4.5, though on 2 benchmarks against 3. Pick Claude Haiku 4.5 when a solved task costs $0.56 against $0.62, or when what matters is LMArena Text: coding or LMArena Text: software and IT, where it leads.
Which is cheaper, Claude Haiku 4.5 or MiniMax M2.5?
Claude Haiku 4.5 costs $1.00 per million input tokens and $5.00 per million output tokens; MiniMax M2.5 costs $0.27 and $0.95. Per solved SWE-bench Verified task, Claude Haiku 4.5 costs $0.56 and MiniMax M2.5 $0.62.
Which has the bigger context window, Claude Haiku 4.5 or MiniMax M2.5?
MiniMax M2.5, with 205K tokens against 200K.
How many benchmarks is the Claude Haiku 4.5 vs MiniMax M2.5 comparison based on?
57 benchmarks have a result for both models as of October 21, 2026. Claude Haiku 4.5's coding index rests on 3 independent benchmarks and MiniMax M2.5's on 2. Where only one model has a result, the page says so instead of naming a winner.