MiniMax M2.5
MiniMax / MiniMax
39scores
38benchmarks
$0.15 / $1.15 per 1M tokenscost in/out
Metadata
MiniMax Closed/API
Aliases: minimax-m2.5, minimax-m2.5-20260211, minimax-minimax-m2.5, minimax-minimax-m2.5-20260211, minimax/minimax-m2.5, minimax/minimax-m2.5-20260211
| Benchmark | Category | Rank | Score | Sampled |
|---|---|---|---|---|
| APEX-Agents | Agentic | 31 | 18.70 | 2026-05-06 |
| ARC-AGI-1 | Agentic | 48 | 63.67 | 2026-05-05 |
| ARC-AGI-2 | Agentic | 68 | 4.86 | 2026-05-05 |
| AutoBench | Agentic | 22 | 2.79 | 2026-05-06 |
| Claw-Eval-Live | Agentic | 11 | 50.5 | 2026-05-27 |
| Gert Labs Rankings | Agentic | 36 | 0.45 | 2026-05-11 |
| HiL-Bench | Agentic | 9 | 7.33% | 2026-05-05 |
| PinchBench | Agentic | 14 | 0.88 | 2026-05-06 |
| Tau2-Bench Telecom | Agentic | 19 | 95.3% | 2026-05-11 |
| Terminal-Bench Hard | Agentic | 65 | 34.8% | 2026-05-11 |
| Vending-Bench 2 | Agentic | 40 | -23.16 | 2026-05-28 |
| WildClawBench | Agentic | 12 | 27.10 | 2026-05-06 |
| ALE-Bench | Coding | 59 | 618.17 | 2026-05-06 |
| Arena AI Code | Coding | 42 | 1383 | 2026-05-06 |
| Multi-SWE-Bench | Coding | 2 | 0.51 | 2026-05-06 |
| SciCode | Coding | 63 | 42.6% | 2026-05-11 |
| SWE Atlas - Codebase QnA | Coding | 9 | 10.30 | 2026-05-06 |
| SWE Atlas - Refactoring | Coding | 10 | 19.52 | 2026-05-06 |
| SWE Atlas - Test Writing | Coding | 10 | 18.60 | 2026-05-06 |
| Vibe Code Bench v1.1 | Coding | 30 | 14.853% | 2026-05-28 |
| VIBE-Pro | Coding | 2 | 0.54 | 2026-05-06 |
| SecCodeBench | Cybersecurity | 25 | 46.31% | 2026-05-28 |
| GSMA Open Telco Leaderboard | Domain | 19 | 64.68 | 2026-05-06 |
| MageBench Season 1 | Game | 14 | 1606 rating / 8 games | 2026-05-28 |
| ALL Bench LLM | General Knowledge | 5 | 50.28 | 2026-05-06 |
| AIIQ Composite IQ | Intelligence | 22 | 112 | 2026-05-12 |
| Artificial Analysis Intelligence Index | Intelligence | 62 | 41.93 | 2026-05-11 |
| Humanity's Last Exam | Intelligence | 74 | 19.1% | 2026-05-11 |
| LiveMathematicianBench | Math | 8 | 22.0% | 2026-05-28 |
| Medical Chronology LLM Benchmark | Medical | 7 | 0.89 | 2026-05-06 |
| ALL Bench Multimodal | Multimodal | 9 | 41.68 | 2026-05-06 |
| ALL Bench Multimodal | Multimodal | 10 | 5.28 | 2026-05-06 |
| GDPval-MM | Multimodal | 3 | 0.59 | 2026-05-06 |
| Artificial Analysis Openness Index | Openness | 185 | 27.78 | 2026-05-11 |
| GPQA Diamond | Reasoning | 55 | 84.8% | 2026-05-11 |
| InvisibleBench | Safety | 2 | 0.02 | 2026-05-06 |
| LiveSecBench | Safety | 14 | 61.65 | 2026-05-27 |
| CritPt | Science | 87 | 1.1% | 2026-05-11 |
| BFCL_v3_MultiTurn | Tool Use | 1 | 0.77 | 2026-05-06 |
No matching rows.