Model
MiniMax M2.5
MiniMax · open weights
Knowledge & Reasoning
Knowledge & Reasoning| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| CL-bench | 11.4 | overall | N/A | Independent | low | epoch.ai |
| CL-bench Life | 6.3 | overall | N/A | Independent | low | epoch.ai |
| GPQA Diamond | 85.2 | accuracy | N/A | Self-reported | low | artificialanalysis.ai |
| LMArena | 1404.0 | elo | N/A | Self-reported | low | lmarena.ai |
| MMLU-Pro | 76.5 | accuracy | N/A | Self-reported | low | artificialanalysis.ai |
Math
Math| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| AIME 2025 | 86.3 | accuracy | N/A | Self-reported | low | kaggle.com |
| EfficientOpt | 83.0 | solver_time_ratio | N/A | Independent | medium | arxiv.org |
| SELF-POT | 0.4 | success_rate | N/A | Independent | medium | arxiv.org |
Coding
Coding| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| LiveCodeBench | 65.0 | pass@1 | N/A | Self-reported | low | livecodebench.github.io |
| SWE-bench Verified | 80.2 | resolved_rate | N/A | Self-reported | low | swebench.com |
| Terminal-Bench 2.0 | 42.2 | accuracy | N/A | Self-reported | low | tbench.ai |
Agentic / Tool Use
Agentic / Tool Use| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| DyadMem | 64.5 | accuracy | N/A | Independent | medium | arxiv.org |
| Terminal-Bench | 42.7 | accuracy | cchuter | Independent | medium | tbench.ai |
| Terminal-Bench | 42.2 | accuracy | Terminus 2 | Independent | medium | tbench.ai |
| XiangqiBench | 0.8 | pass@3 | N/A | Independent | medium | arxiv.org |
Instruction Following
Instruction Following| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| IFEval | 87.5 | prompt_strict_accuracy | N/A | Self-reported | low | artificialanalysis.ai |
Abstract Reasoning
Abstract ReasoningReproduced by the community
Loading community runs…