# MiniMax M2.5 As of October 21, 2026, MiniMax M2.5 ranks #85 of 213 models overall with 22.8 on the Artificial Analysis Intelligence Index. Its strongest category is coding, where it ranks #57 of 136. MiniMax M2.5 costs $0.27 per million input tokens and $0.95 per million output tokens. It was released on February 12, 2026. Page: https://llmbenchmark.ai/models/minimax-minimax-m2-5 Data from October 21, 2026. Every figure below names the board it was read from and the day. - Maker: MiniMax - Released: February 12, 2026 - Price per million input tokens: $0.27 - Price per million output tokens: $0.95 - Context window: 205K tokens - Overall rank: 85 of 213, by the Artificial Analysis Intelligence Index - Artificial Analysis Intelligence Index: 22.8 - Vibe Coding Index: 59.4 (from 2 of 4 coding benchmarks) Benchmark results (67 of 190): - SWE-bench Verified: 75.8% (source: SWE-bench (swebench.com), read October 21, 2026) - SWE-bench Multilingual: 68.3% (source: SWE-bench (swebench.com), read October 21, 2026) - LMArena WebDev: 1386 Elo (source: LMArena WebDev, read October 21, 2026) - GPQA Diamond: 82.1% (source: GPQA (Vals AI), read October 21, 2026) - AIME: 88.8% (source: AIME (Vals AI), read October 21, 2026) - MMLU Pro: 80.1% (source: MMLU Pro (Vals AI), read October 21, 2026) - AA Intelligence Index: 22.8 (source: Artificial Analysis (via OpenRouter), read October 21, 2026) - Design Arena: websites: 1222 Elo (source: Design Arena, read October 21, 2026) - Design Arena: UI components: 1172 Elo (source: Design Arena, read October 21, 2026) - Design Arena: game dev: 1176 Elo (source: Design Arena, read October 21, 2026) - Design Arena: data viz: 1171 Elo (source: Design Arena, read October 21, 2026) - Design Arena: 3D: 1170 Elo (source: Design Arena, read October 21, 2026) - Design Arena: all code categories: 1207 Elo (source: Design Arena, read October 21, 2026) - Design Arena: SVG: 1147 Elo (source: Design Arena, read October 21, 2026) - LiveCodeBench (Vals AI): 79.2% (source: Vals AI boards, read October 21, 2026) - SWE-bench Verified (Vals AI): 74.2% (source: Vals AI boards, read October 21, 2026) - Vibe Code Bench (Vals AI): 14.8% (source: Vals AI boards, read October 21, 2026) - LegalBench (Vals AI): 80.0% (source: Vals AI boards, read October 21, 2026) - CaseLaw (Vals AI): 53.5% (source: Vals AI boards, read October 21, 2026) - CorpFin (Vals AI): 59.6% (source: Vals AI boards, read October 21, 2026) - TaxEval (Vals AI): 68.2% (source: Vals AI boards, read October 21, 2026) - MedQA (Vals AI): 92.5% (source: Vals AI boards, read October 21, 2026) - GPQA Diamond (Artificial Analysis run): 84.8% (source: Artificial Analysis, read October 21, 2026) - Humanity's Last Exam (Artificial Analysis run): 20.5% (source: Artificial Analysis, read October 21, 2026) - Terminal-Bench Hard (Artificial Analysis run): 34.8% (source: Artificial Analysis, read October 21, 2026) - IFBench: 71.6% (source: Artificial Analysis, read October 21, 2026) - Long context reasoning (AA-LCR): 73.3% (source: Artificial Analysis, read October 21, 2026) - τ²-Bench Telecom: 95.3% (source: Artificial Analysis, read October 21, 2026) - Terminal-Bench: 42.7% (source: Epoch AI benchmarking hub, read October 21, 2026) - ARC-AGI: 63.7% (source: Epoch AI benchmarking hub, read October 21, 2026) - ARC-AGI-2: 4.9% (source: Epoch AI benchmarking hub, read October 21, 2026) - ProofBench: 4.0% (source: Epoch AI benchmarking hub, read October 21, 2026) - CL-bench: 11.4% (source: Epoch AI benchmarking hub, read October 21, 2026) - CL-bench Life: 6.3% (source: Epoch AI benchmarking hub, read October 21, 2026) - ALE-Bench: 618.2 (source: ALE-Bench (Sakana AI), read October 21, 2026) - Vending-Bench 2: -$23 (source: Epoch AI benchmarking hub, read October 21, 2026) - Epoch Capabilities Index: 146.6 (source: Epoch AI benchmarking hub, read October 21, 2026) - LMArena Text: 1359 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: coding: 1380 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: hard prompts: 1372 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: math: 1378 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: instruction following: 1353 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: creative writing: 1331 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: English: 1380 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: non-English: 1338 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: Chinese: 1393 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: German: 1361 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: Japanese: 1171 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: Korean: 1233 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: French: 1363 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: Spanish: 1353 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: Russian: 1359 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: Polish: 1334 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: multi-turn: 1364 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: longer queries: 1366 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: expert: 1378 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: hard prompts in English: 1384 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: software and IT: 1383 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: mathematical work: 1378 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: science: 1369 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: medicine and healthcare: 1357 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: legal and government: 1366 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: business and finance: 1356 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: writing and language: 1345 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: entertainment and media: 1329 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena WebDev: React: 1374 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena WebDev: HTML: 1414 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)